Save 75% checkpoint at 22,501,392,384 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": 75,
|
| 54 |
+
"step": 21459,
|
| 55 |
"total_steps": 28611,
|
| 56 |
+
"tokens_seen": 22501392384,
|
| 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": 6870.196833848953
|
| 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 sha256:5b58067af01b07813442f6d5f39068c3d491b4510b1c9e9b60112473891c267c
|
| 3 |
size 12811532
|
training_metrics.jsonl
CHANGED
|
@@ -2001,3 +2001,146 @@
|
|
| 2001 |
{"step": 20000, "total_steps": 28611, "tokens": 20971520000, "loss": 2.7924068570137024, "ce_loss": 2.79136198759079, "z_loss": 10.448696851730347, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29861411452293396, "tokens_per_second": 3935089.8767564, "eta_seconds": 2294.5569780588153, "data_wait_seconds": 1.4066696166992188e-05}
|
| 2002 |
{"step": 20010, "total_steps": 28611, "tokens": 20982005760, "loss": 2.7804075479507446, "ce_loss": 2.779368281364441, "z_loss": 10.392492294311523, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3252759575843811, "tokens_per_second": 4413926.494453094, "eta_seconds": 2043.2606178045273, "data_wait_seconds": 1.8775463104248047e-05}
|
| 2003 |
{"step": 20020, "total_steps": 28611, "tokens": 20992491520, "loss": 2.7646827697753906, "ce_loss": 2.763590395450592, "z_loss": 10.923757791519165, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3760130703449249, "tokens_per_second": 2843211.1753075863, "eta_seconds": 3168.3599495649337, "data_wait_seconds": 1.5914440155029297e-05}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2001 |
{"step": 20000, "total_steps": 28611, "tokens": 20971520000, "loss": 2.7924068570137024, "ce_loss": 2.79136198759079, "z_loss": 10.448696851730347, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29861411452293396, "tokens_per_second": 3935089.8767564, "eta_seconds": 2294.5569780588153, "data_wait_seconds": 1.4066696166992188e-05}
|
| 2002 |
{"step": 20010, "total_steps": 28611, "tokens": 20982005760, "loss": 2.7804075479507446, "ce_loss": 2.779368281364441, "z_loss": 10.392492294311523, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3252759575843811, "tokens_per_second": 4413926.494453094, "eta_seconds": 2043.2606178045273, "data_wait_seconds": 1.8775463104248047e-05}
|
| 2003 |
{"step": 20020, "total_steps": 28611, "tokens": 20992491520, "loss": 2.7646827697753906, "ce_loss": 2.763590395450592, "z_loss": 10.923757791519165, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3760130703449249, "tokens_per_second": 2843211.1753075863, "eta_seconds": 3168.3599495649337, "data_wait_seconds": 1.5914440155029297e-05}
|
| 2004 |
+
{"step": 20030, "total_steps": 28611, "tokens": 21002977280, "loss": 2.778001844882965, "ce_loss": 2.776727557182312, "z_loss": 12.743677854537964, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33601370453834534, "tokens_per_second": 8963741.886715235, "eta_seconds": 1003.8029619455338, "data_wait_seconds": 2.0205974578857422e-05}
|
| 2005 |
+
{"step": 20040, "total_steps": 28611, "tokens": 21013463040, "loss": 2.809057891368866, "ce_loss": 2.8080894351005554, "z_loss": 9.684754848480225, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35114166140556335, "tokens_per_second": 3838720.3834280754, "eta_seconds": 2341.2345777511596, "data_wait_seconds": 1.3053417205810547e-05}
|
| 2006 |
+
{"step": 20050, "total_steps": 28611, "tokens": 21023948800, "loss": 2.76467627286911, "ce_loss": 2.7635581493377686, "z_loss": 11.181169986724854, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37386614084243774, "tokens_per_second": 2672047.8746593143, "eta_seconds": 3359.5427765846252, "data_wait_seconds": 0.5656177401542664}
|
| 2007 |
+
{"step": 20060, "total_steps": 28611, "tokens": 21034434560, "loss": 2.7559841871261597, "ce_loss": 2.754850149154663, "z_loss": 11.339896202087402, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2928573191165924, "tokens_per_second": 4550539.645152712, "eta_seconds": 1970.3978154659274, "data_wait_seconds": 1.3470649719238281e-05}
|
| 2008 |
+
{"step": 20070, "total_steps": 28611, "tokens": 21044920320, "loss": 2.7958606481552124, "ce_loss": 2.7948816418647766, "z_loss": 9.790621280670166, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3546585142612457, "tokens_per_second": 2860529.963249278, "eta_seconds": 3130.8490842819215, "data_wait_seconds": 1.3947486877441406e-05}
|
| 2009 |
+
{"step": 20080, "total_steps": 28611, "tokens": 21055406080, "loss": 2.8161585330963135, "ce_loss": 2.81501841545105, "z_loss": 11.401703834533691, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.4234886169433594, "tokens_per_second": 4130332.795466637, "eta_seconds": 2165.7823470830917, "data_wait_seconds": 1.633167266845703e-05}
|
| 2010 |
+
{"step": 20090, "total_steps": 28611, "tokens": 21065891840, "loss": 2.779862344264984, "ce_loss": 2.778614103794098, "z_loss": 12.481950283050537, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30100783705711365, "tokens_per_second": 2882000.629278641, "eta_seconds": 3100.2477949619292, "data_wait_seconds": 1.996755599975586e-05}
|
| 2011 |
+
{"step": 20100, "total_steps": 28611, "tokens": 21076377600, "loss": 2.7472800612449646, "ce_loss": 2.7463884949684143, "z_loss": 8.915552377700806, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3181593418121338, "tokens_per_second": 4142847.5182637074, "eta_seconds": 2154.177844262123, "data_wait_seconds": 1.2040138244628906e-05}
|
| 2012 |
+
{"step": 20110, "total_steps": 28611, "tokens": 21086863360, "loss": 2.803278386592865, "ce_loss": 2.802120327949524, "z_loss": 11.580070495605469, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34393563866615295, "tokens_per_second": 2773779.8405881813, "eta_seconds": 3213.6453101158145, "data_wait_seconds": 1.6868114471435547e-05}
|
| 2013 |
+
{"step": 20120, "total_steps": 28611, "tokens": 21097349120, "loss": 2.8248627185821533, "ce_loss": 2.8237932920455933, "z_loss": 10.693819999694824, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3268093764781952, "tokens_per_second": 4482963.70621996, "eta_seconds": 1986.0653352260588, "data_wait_seconds": 1.245737075805664e-05}
|
| 2014 |
+
{"step": 20130, "total_steps": 28611, "tokens": 21107834880, "loss": 2.7450647950172424, "ce_loss": 2.743871569633484, "z_loss": 11.93221664428711, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3421590030193329, "tokens_per_second": 2733609.416534706, "eta_seconds": 3253.1981351137165, "data_wait_seconds": 1.4960765838623047e-05}
|
| 2015 |
+
{"step": 20140, "total_steps": 28611, "tokens": 21118320640, "loss": 2.7932867407798767, "ce_loss": 2.7919751405715942, "z_loss": 13.11545467376709, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31684115529060364, "tokens_per_second": 2997854.9076090385, "eta_seconds": 2962.947697520256, "data_wait_seconds": 0.16881346702575684}
|
| 2016 |
+
{"step": 20150, "total_steps": 28611, "tokens": 21128806400, "loss": 2.765238642692566, "ce_loss": 2.7640514373779297, "z_loss": 11.871814727783203, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.41100457310676575, "tokens_per_second": 3693241.272923697, "eta_seconds": 2402.2263590097427, "data_wait_seconds": 1.8358230590820312e-05}
|
| 2017 |
+
{"step": 20160, "total_steps": 28611, "tokens": 21139292160, "loss": 2.7316744327545166, "ce_loss": 2.7304080724716187, "z_loss": 12.663779497146606, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3130604028701782, "tokens_per_second": 4384966.157057498, "eta_seconds": 2020.8857853412628, "data_wait_seconds": 1.7642974853515625e-05}
|
| 2018 |
+
{"step": 20170, "total_steps": 28611, "tokens": 21149777920, "loss": 2.7984837889671326, "ce_loss": 2.7972270846366882, "z_loss": 12.567079067230225, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3834102153778076, "tokens_per_second": 2854295.9692575196, "eta_seconds": 3100.950325870514, "data_wait_seconds": 1.4185905456542969e-05}
|
| 2019 |
+
{"step": 20180, "total_steps": 28611, "tokens": 21160263680, "loss": 2.8102275133132935, "ce_loss": 2.809226334095001, "z_loss": 10.011227130889893, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2967173755168915, "tokens_per_second": 2785522.5491961273, "eta_seconds": 3173.747151517868, "data_wait_seconds": 1.704692840576172e-05}
|
| 2020 |
+
{"step": 20190, "total_steps": 28611, "tokens": 21170749440, "loss": 2.8118202090263367, "ce_loss": 2.8106040358543396, "z_loss": 12.162276268005371, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34450241923332214, "tokens_per_second": 3986693.134751341, "eta_seconds": 2214.8829111099244, "data_wait_seconds": 1.6629695892333984e-05}
|
| 2021 |
+
{"step": 20200, "total_steps": 28611, "tokens": 21181235200, "loss": 2.7894694209098816, "ce_loss": 2.7885058522224426, "z_loss": 9.63543152809143, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3075774610042572, "tokens_per_second": 2855884.1865520705, "eta_seconds": 3088.2109216928484, "data_wait_seconds": 1.2576580047607422e-05}
|
| 2022 |
+
{"step": 20210, "total_steps": 28611, "tokens": 21191720960, "loss": 2.8046979904174805, "ce_loss": 2.8037338256835938, "z_loss": 9.641919612884521, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38560235500335693, "tokens_per_second": 2309541.9998237668, "eta_seconds": 3814.213803720474, "data_wait_seconds": 0.28828108310699463}
|
| 2023 |
+
{"step": 20220, "total_steps": 28611, "tokens": 21202206720, "loss": 2.790006101131439, "ce_loss": 2.7888227105140686, "z_loss": 11.83312177658081, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3302514851093292, "tokens_per_second": 3944420.0598849547, "eta_seconds": 2230.6450840473176, "data_wait_seconds": 1.430511474609375e-05}
|
| 2024 |
+
{"step": 20230, "total_steps": 28611, "tokens": 21212692480, "loss": 2.7956841588020325, "ce_loss": 2.7946759462356567, "z_loss": 10.081753730773926, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3702376186847687, "tokens_per_second": 2844961.3447740367, "eta_seconds": 3089.0104964494703, "data_wait_seconds": 1.722574234008789e-05}
|
| 2025 |
+
{"step": 20240, "total_steps": 28611, "tokens": 21223178240, "loss": 2.7959359288215637, "ce_loss": 2.794592499732971, "z_loss": 13.434831380844116, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35761401057243347, "tokens_per_second": 3448525.3915610975, "eta_seconds": 2545.328422832489, "data_wait_seconds": 1.4662742614746094e-05}
|
| 2026 |
+
{"step": 20250, "total_steps": 28611, "tokens": 21233664000, "loss": 2.7692151069641113, "ce_loss": 2.768043637275696, "z_loss": 11.715518474578857, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3877907991409302, "tokens_per_second": 2869583.513591034, "eta_seconds": 3055.1973464012144, "data_wait_seconds": 1.3947486877441406e-05}
|
| 2027 |
+
{"step": 20260, "total_steps": 28611, "tokens": 21244149760, "loss": 2.8108681440353394, "ce_loss": 2.809707760810852, "z_loss": 11.603499174118042, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3743075728416443, "tokens_per_second": 2700695.71415176, "eta_seconds": 3242.371263861656, "data_wait_seconds": 1.9431114196777344e-05}
|
| 2028 |
+
{"step": 20270, "total_steps": 28611, "tokens": 21254635520, "loss": 2.7801195979118347, "ce_loss": 2.778980314731598, "z_loss": 11.392572402954102, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3461422026157379, "tokens_per_second": 3909963.0825367766, "eta_seconds": 2236.8938609838483, "data_wait_seconds": 1.627206802368164e-05}
|
| 2029 |
+
{"step": 20280, "total_steps": 28611, "tokens": 21265121280, "loss": 2.812379240989685, "ce_loss": 2.811157464981079, "z_loss": 12.218219995498657, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.44168490171432495, "tokens_per_second": 2795658.417063837, "eta_seconds": 3124.73319439888, "data_wait_seconds": 0.5410112738609314}
|
| 2030 |
+
{"step": 20290, "total_steps": 28611, "tokens": 21275607040, "loss": 2.7881407141685486, "ce_loss": 2.7869147062301636, "z_loss": 12.260009288787842, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33049315214157104, "tokens_per_second": 4315782.093877964, "eta_seconds": 2021.6963475465775, "data_wait_seconds": 1.436471939086914e-05}
|
| 2031 |
+
{"step": 20300, "total_steps": 28611, "tokens": 21286092800, "loss": 2.7677310705184937, "ce_loss": 2.7665737867355347, "z_loss": 11.572688102722168, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2954467236995697, "tokens_per_second": 2585398.678076945, "eta_seconds": 3370.743247413635, "data_wait_seconds": 1.710653305053711e-05}
|
| 2032 |
+
{"step": 20310, "total_steps": 28611, "tokens": 21296578560, "loss": 2.798029839992523, "ce_loss": 2.7970237731933594, "z_loss": 10.060407876968384, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31703436374664307, "tokens_per_second": 3828046.551534031, "eta_seconds": 2273.8044741153717, "data_wait_seconds": 1.341104507446289e-05}
|
| 2033 |
+
{"step": 20320, "total_steps": 28611, "tokens": 21307064320, "loss": 2.7712196111679077, "ce_loss": 2.770264685153961, "z_loss": 9.548940181732178, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3077528178691864, "tokens_per_second": 2994645.654098117, "eta_seconds": 2903.0959319353105, "data_wait_seconds": 1.6450881958007812e-05}
|
| 2034 |
+
{"step": 20330, "total_steps": 28611, "tokens": 21317550080, "loss": 2.7947599291801453, "ce_loss": 2.7935556173324585, "z_loss": 12.04247260093689, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29129886627197266, "tokens_per_second": 2915450.4519556677, "eta_seconds": 2978.358918833733, "data_wait_seconds": 0.2529250383377075}
|
| 2035 |
+
{"step": 20340, "total_steps": 28611, "tokens": 21328035840, "loss": 2.8208720684051514, "ce_loss": 2.8198291063308716, "z_loss": 10.429406642913818, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.354257732629776, "tokens_per_second": 3561345.726737221, "eta_seconds": 2435.251380085945, "data_wait_seconds": 1.2636184692382812e-05}
|
| 2036 |
+
{"step": 20350, "total_steps": 28611, "tokens": 21338521600, "loss": 2.833525776863098, "ce_loss": 2.8323302268981934, "z_loss": 11.955726385116577, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3528955578804016, "tokens_per_second": 4175618.020158964, "eta_seconds": 2074.4920378684997, "data_wait_seconds": 1.4424324035644531e-05}
|
| 2037 |
+
{"step": 20360, "total_steps": 28611, "tokens": 21349007360, "loss": 2.7982534766197205, "ce_loss": 2.797154664993286, "z_loss": 10.987821340560913, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3438619375228882, "tokens_per_second": 2902590.994476028, "eta_seconds": 2980.716398715973, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2038 |
+
{"step": 20370, "total_steps": 28611, "tokens": 21359493120, "loss": 2.7930922508239746, "ce_loss": 2.792003571987152, "z_loss": 10.886979579925537, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3423091173171997, "tokens_per_second": 2868464.6826492855, "eta_seconds": 3012.5226460933686, "data_wait_seconds": 1.6808509826660156e-05}
|
| 2039 |
+
{"step": 20380, "total_steps": 28611, "tokens": 21369978880, "loss": 2.801968038082123, "ce_loss": 2.8009104132652283, "z_loss": 10.57640552520752, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37561091780662537, "tokens_per_second": 3990042.3378243665, "eta_seconds": 2163.092099094391, "data_wait_seconds": 1.6510486602783203e-05}
|
| 2040 |
+
{"step": 20390, "total_steps": 28611, "tokens": 21380464640, "loss": 2.764015793800354, "ce_loss": 2.76255202293396, "z_loss": 14.637808322906494, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35184893012046814, "tokens_per_second": 4602519.419594741, "eta_seconds": 1872.961852002144, "data_wait_seconds": 1.6868114471435547e-05}
|
| 2041 |
+
{"step": 20400, "total_steps": 28611, "tokens": 21390950400, "loss": 2.7921575903892517, "ce_loss": 2.791057586669922, "z_loss": 11.00016713142395, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3717021644115448, "tokens_per_second": 4019264.9530327627, "eta_seconds": 2142.1472922563553, "data_wait_seconds": 1.4722347259521484e-05}
|
| 2042 |
+
{"step": 20410, "total_steps": 28611, "tokens": 21401436160, "loss": 2.827184319496155, "ce_loss": 2.8261796832084656, "z_loss": 10.046700477600098, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35661810636520386, "tokens_per_second": 4228401.763819051, "eta_seconds": 2033.716816973686, "data_wait_seconds": 1.3530254364013672e-05}
|
| 2043 |
+
{"step": 20420, "total_steps": 28611, "tokens": 21411921920, "loss": 2.7840893268585205, "ce_loss": 2.7832109332084656, "z_loss": 8.783959865570068, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2769106924533844, "tokens_per_second": 4002853.947437568, "eta_seconds": 2145.690581965446, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2044 |
+
{"step": 20430, "total_steps": 28611, "tokens": 21422407680, "loss": 2.8119309544563293, "ce_loss": 2.810713469982147, "z_loss": 12.174898386001587, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3716428875923157, "tokens_per_second": 3958829.073110014, "eta_seconds": 2166.9034195661548, "data_wait_seconds": 1.4781951904296875e-05}
|
| 2045 |
+
{"step": 20440, "total_steps": 28611, "tokens": 21432893440, "loss": 2.8257917761802673, "ce_loss": 2.8246535658836365, "z_loss": 11.381763219833374, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.340905100107193, "tokens_per_second": 3020499.0069160317, "eta_seconds": 2836.589078950882, "data_wait_seconds": 0.27747708559036255}
|
| 2046 |
+
{"step": 20450, "total_steps": 28611, "tokens": 21443379200, "loss": 2.740056812763214, "ce_loss": 2.7387375831604004, "z_loss": 13.19221019744873, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2758171558380127, "tokens_per_second": 3809952.856103813, "eta_seconds": 2246.0720799446103, "data_wait_seconds": 1.341104507446289e-05}
|
| 2047 |
+
{"step": 20460, "total_steps": 28611, "tokens": 21453864960, "loss": 2.8211912512779236, "ce_loss": 2.8200345039367676, "z_loss": 11.567758321762085, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3672094941139221, "tokens_per_second": 2902972.0635154066, "eta_seconds": 2944.204349541664, "data_wait_seconds": 1.519918441772461e-05}
|
| 2048 |
+
{"step": 20470, "total_steps": 28611, "tokens": 21464350720, "loss": 2.7780330777168274, "ce_loss": 2.7767470479011536, "z_loss": 12.860316753387451, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27737659215927124, "tokens_per_second": 4212185.510334686, "eta_seconds": 2026.6099854946135, "data_wait_seconds": 1.2993812561035156e-05}
|
| 2049 |
+
{"step": 20480, "total_steps": 28611, "tokens": 21474836480, "loss": 2.7778362035751343, "ce_loss": 2.7767319679260254, "z_loss": 11.042051076889038, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35616689920425415, "tokens_per_second": 4566098.098750016, "eta_seconds": 1867.2335266590117, "data_wait_seconds": 1.6629695892333984e-05}
|
| 2050 |
+
{"step": 20490, "total_steps": 28611, "tokens": 21485322240, "loss": 2.847707152366638, "ce_loss": 2.8465837240219116, "z_loss": 11.233983755111694, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2960832118988037, "tokens_per_second": 3989004.423869776, "eta_seconds": 2134.739596939087, "data_wait_seconds": 1.341104507446289e-05}
|
| 2051 |
+
{"step": 20500, "total_steps": 28611, "tokens": 21495808000, "loss": 2.819626748561859, "ce_loss": 2.818529725074768, "z_loss": 10.970785856246948, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38081538677215576, "tokens_per_second": 2875637.6443951386, "eta_seconds": 2957.604882025719, "data_wait_seconds": 1.4722347259521484e-05}
|
| 2052 |
+
{"step": 20510, "total_steps": 28611, "tokens": 21506293760, "loss": 2.819964349269867, "ce_loss": 2.818742096424103, "z_loss": 12.221961259841919, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.4402807056903839, "tokens_per_second": 4416135.000064263, "eta_seconds": 1923.5177764892578, "data_wait_seconds": 1.4781951904296875e-05}
|
| 2053 |
+
{"step": 20520, "total_steps": 28611, "tokens": 21516779520, "loss": 2.798095166683197, "ce_loss": 2.796993911266327, "z_loss": 11.013078927993774, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28508347272872925, "tokens_per_second": 2747155.672134998, "eta_seconds": 3088.295469403267, "data_wait_seconds": 1.5139579772949219e-05}
|
| 2054 |
+
{"step": 20530, "total_steps": 28611, "tokens": 21527265280, "loss": 2.748683512210846, "ce_loss": 2.747622013092041, "z_loss": 10.61449408531189, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38783442974090576, "tokens_per_second": 2764850.8015430192, "eta_seconds": 3064.737761354447, "data_wait_seconds": 2.008676528930664e-05}
|
| 2055 |
+
{"step": 20540, "total_steps": 28611, "tokens": 21537751040, "loss": 2.803886115550995, "ce_loss": 2.8028839826583862, "z_loss": 10.020922422409058, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3036850690841675, "tokens_per_second": 3010161.762728801, "eta_seconds": 2811.49571454525, "data_wait_seconds": 1.8596649169921875e-05}
|
| 2056 |
+
{"step": 20550, "total_steps": 28611, "tokens": 21548236800, "loss": 2.878433644771576, "ce_loss": 2.877483546733856, "z_loss": 9.501105070114136, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.301291286945343, "tokens_per_second": 4004019.373043475, "eta_seconds": 2111.021538233757, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2057 |
+
{"step": 20560, "total_steps": 28611, "tokens": 21558722560, "loss": 2.7835439443588257, "ce_loss": 2.782383680343628, "z_loss": 11.602551698684692, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33693718910217285, "tokens_per_second": 2662404.832658003, "eta_seconds": 3170.849629044533, "data_wait_seconds": 1.3530254364013672e-05}
|
| 2058 |
+
{"step": 20570, "total_steps": 28611, "tokens": 21569208320, "loss": 2.806921124458313, "ce_loss": 2.805626690387726, "z_loss": 12.944941282272339, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35187584161758423, "tokens_per_second": 3902843.5713746934, "eta_seconds": 2160.3734461307527, "data_wait_seconds": 1.71661376953125e-05}
|
| 2059 |
+
{"step": 20580, "total_steps": 28611, "tokens": 21579694080, "loss": 2.8218936920166016, "ce_loss": 2.8207831978797913, "z_loss": 11.10534381866455, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.40450549125671387, "tokens_per_second": 2831623.889577365, "eta_seconds": 2973.9521152496336, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2060 |
+
{"step": 20590, "total_steps": 28611, "tokens": 21590179840, "loss": 2.776590943336487, "ce_loss": 2.775649905204773, "z_loss": 9.410509586334229, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31883907318115234, "tokens_per_second": 2899057.131587985, "eta_seconds": 2901.1598303318024, "data_wait_seconds": 0.25234705209732056}
|
| 2061 |
+
{"step": 20600, "total_steps": 28611, "tokens": 21600665600, "loss": 2.813141107559204, "ce_loss": 2.8118537068367004, "z_loss": 12.874208688735962, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29380741715431213, "tokens_per_second": 3645559.018434911, "eta_seconds": 2304.2124111890794, "data_wait_seconds": 1.3113021850585938e-05}
|
| 2062 |
+
{"step": 20610, "total_steps": 28611, "tokens": 21611151360, "loss": 2.7879841327667236, "ce_loss": 2.78684538602829, "z_loss": 11.38692331314087, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37722718715667725, "tokens_per_second": 2730944.805074511, "eta_seconds": 3072.071087050438, "data_wait_seconds": 0.2959284782409668}
|
| 2063 |
+
{"step": 20620, "total_steps": 28611, "tokens": 21621637120, "loss": 2.84572434425354, "ce_loss": 2.8445144295692444, "z_loss": 12.09937310218811, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33984774351119995, "tokens_per_second": 4399262.907297868, "eta_seconds": 1904.6760770082471, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2064 |
+
{"step": 20630, "total_steps": 28611, "tokens": 21632122880, "loss": 2.7844980359077454, "ce_loss": 2.7831764817237854, "z_loss": 13.215800523757935, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33631598949432373, "tokens_per_second": 2799205.8887744313, "eta_seconds": 2989.6639934778214, "data_wait_seconds": 1.627206802368164e-05}
|
| 2065 |
+
{"step": 20640, "total_steps": 28611, "tokens": 21642608640, "loss": 2.816398501396179, "ce_loss": 2.8152878880500793, "z_loss": 11.106656074523926, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33420658111572266, "tokens_per_second": 4131854.278334845, "eta_seconds": 2022.8688460350036, "data_wait_seconds": 1.3530254364013672e-05}
|
| 2066 |
+
{"step": 20650, "total_steps": 28611, "tokens": 21653094400, "loss": 2.834351658821106, "ce_loss": 2.833158254623413, "z_loss": 11.934048652648926, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31929633021354675, "tokens_per_second": 3012322.0415628925, "eta_seconds": 2771.1889435529706, "data_wait_seconds": 1.7702579498291016e-05}
|
| 2067 |
+
{"step": 20660, "total_steps": 28611, "tokens": 21663580160, "loss": 2.7479724287986755, "ce_loss": 2.746720016002655, "z_loss": 12.524406433105469, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29312431812286377, "tokens_per_second": 4262548.615707878, "eta_seconds": 1955.9255571365356, "data_wait_seconds": 1.239776611328125e-05}
|
| 2068 |
+
{"step": 20670, "total_steps": 28611, "tokens": 21674065920, "loss": 2.7821056842803955, "ce_loss": 2.781109035015106, "z_loss": 9.966135740280151, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3103060722351074, "tokens_per_second": 2884146.1064268826, "eta_seconds": 2887.0735769748685, "data_wait_seconds": 1.52587890625e-05}
|
| 2069 |
+
{"step": 20680, "total_steps": 28611, "tokens": 21684551680, "loss": 2.806885302066803, "ce_loss": 2.805690109729767, "z_loss": 11.951549768447876, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3569244146347046, "tokens_per_second": 2825755.2927603796, "eta_seconds": 2943.020677447319, "data_wait_seconds": 1.728534698486328e-05}
|
| 2070 |
+
{"step": 20690, "total_steps": 28611, "tokens": 21695037440, "loss": 2.811924934387207, "ce_loss": 2.8108248114585876, "z_loss": 11.00108814239502, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3141617774963379, "tokens_per_second": 4016370.0609389585, "eta_seconds": 2067.979386854172, "data_wait_seconds": 1.4662742614746094e-05}
|
| 2071 |
+
{"step": 20700, "total_steps": 28611, "tokens": 21705523200, "loss": 2.828307092189789, "ce_loss": 2.8270750641822815, "z_loss": 12.319937229156494, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3959447741508484, "tokens_per_second": 4284760.4442893015, "eta_seconds": 1935.9973197698594, "data_wait_seconds": 1.4781951904296875e-05}
|
| 2072 |
+
{"step": 20710, "total_steps": 28611, "tokens": 21716008960, "loss": 2.8020922541618347, "ce_loss": 2.8011052012443542, "z_loss": 9.870290279388428, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3416856825351715, "tokens_per_second": 3078039.450351112, "eta_seconds": 2691.5831033468244, "data_wait_seconds": 1.33514404296875e-05}
|
| 2073 |
+
{"step": 20720, "total_steps": 28611, "tokens": 21726494720, "loss": 2.7868261337280273, "ce_loss": 2.7858559489250183, "z_loss": 9.702461242675781, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32404637336730957, "tokens_per_second": 2962182.669841292, "eta_seconds": 2793.316327261925, "data_wait_seconds": 1.7344951629638672e-05}
|
| 2074 |
+
{"step": 20730, "total_steps": 28611, "tokens": 21736980480, "loss": 2.7750375866889954, "ce_loss": 2.773830831050873, "z_loss": 12.067532539367676, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3101648688316345, "tokens_per_second": 3904168.4245630847, "eta_seconds": 2116.6677656650545, "data_wait_seconds": 1.7881393432617188e-05}
|
| 2075 |
+
{"step": 20740, "total_steps": 28611, "tokens": 21747466240, "loss": 2.798950970172882, "ce_loss": 2.797881543636322, "z_loss": 10.693875789642334, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3176267445087433, "tokens_per_second": 3089526.413277602, "eta_seconds": 2671.39379696846, "data_wait_seconds": 1.8417835235595703e-05}
|
| 2076 |
+
{"step": 20750, "total_steps": 28611, "tokens": 21757952000, "loss": 2.7930139899253845, "ce_loss": 2.791975498199463, "z_loss": 10.385165691375732, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2916361689567566, "tokens_per_second": 3026281.935506334, "eta_seconds": 2723.756778669357, "data_wait_seconds": 1.7344951629638672e-05}
|
| 2077 |
+
{"step": 20760, "total_steps": 28611, "tokens": 21768437760, "loss": 2.772820293903351, "ce_loss": 2.7717881202697754, "z_loss": 10.321417093276978, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29251912236213684, "tokens_per_second": 4249787.571912738, "eta_seconds": 1937.1251001834871, "data_wait_seconds": 1.4603137969970703e-05}
|
| 2078 |
+
{"step": 20770, "total_steps": 28611, "tokens": 21778923520, "loss": 2.7886162996292114, "ce_loss": 2.7874051332473755, "z_loss": 12.11160159111023, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3312230110168457, "tokens_per_second": 3155519.8600163627, "eta_seconds": 2605.556225514412, "data_wait_seconds": 1.633167266845703e-05}
|
| 2079 |
+
{"step": 20780, "total_steps": 28611, "tokens": 21789409280, "loss": 2.7826457023620605, "ce_loss": 2.781303286552429, "z_loss": 13.424249172210693, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34563079476356506, "tokens_per_second": 3089632.7626757203, "eta_seconds": 2657.7264311790464, "data_wait_seconds": 0.2722504734992981}
|
| 2080 |
+
{"step": 20790, "total_steps": 28611, "tokens": 21799895040, "loss": 2.805159270763397, "ce_loss": 2.8041648268699646, "z_loss": 9.944295883178711, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.36822378635406494, "tokens_per_second": 4407614.560792568, "eta_seconds": 1860.623877811432, "data_wait_seconds": 1.3768672943115234e-05}
|
| 2081 |
+
{"step": 20800, "total_steps": 28611, "tokens": 21810380800, "loss": 2.7998316287994385, "ce_loss": 2.7986872792243958, "z_loss": 11.44359540939331, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29636865854263306, "tokens_per_second": 3242059.4239353305, "eta_seconds": 2526.3038288354874, "data_wait_seconds": 1.341104507446289e-05}
|
| 2082 |
+
{"step": 20810, "total_steps": 28611, "tokens": 21820866560, "loss": 2.8217602372169495, "ce_loss": 2.820704758167267, "z_loss": 10.555155038833618, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.39053836464881897, "tokens_per_second": 4506180.421441241, "eta_seconds": 1815.271607208252, "data_wait_seconds": 1.4185905456542969e-05}
|
| 2083 |
+
{"step": 20820, "total_steps": 28611, "tokens": 21831352320, "loss": 2.7665536403656006, "ce_loss": 2.7654027342796326, "z_loss": 11.509119987487793, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3439067006111145, "tokens_per_second": 4562634.895969808, "eta_seconds": 1790.5126757383348, "data_wait_seconds": 1.7404556274414062e-05}
|
| 2084 |
+
{"step": 20830, "total_steps": 28611, "tokens": 21841838080, "loss": 2.7896862626075745, "ce_loss": 2.788498818874359, "z_loss": 11.87357783317566, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34368816018104553, "tokens_per_second": 4633989.321184641, "eta_seconds": 1760.67946870327, "data_wait_seconds": 0.25455600023269653}
|
| 2085 |
+
{"step": 20840, "total_steps": 28611, "tokens": 21852323840, "loss": 2.828324556350708, "ce_loss": 2.827390134334564, "z_loss": 9.34387993812561, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3505334258079529, "tokens_per_second": 7004705.448090155, "eta_seconds": 1163.2871869325638, "data_wait_seconds": 1.2874603271484375e-05}
|
| 2086 |
+
{"step": 20850, "total_steps": 28611, "tokens": 21862809600, "loss": 2.7916101217269897, "ce_loss": 2.790681540966034, "z_loss": 9.286101579666138, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3568296432495117, "tokens_per_second": 4280431.385745321, "eta_seconds": 1901.209855413437, "data_wait_seconds": 1.3768672943115234e-05}
|
| 2087 |
+
{"step": 20860, "total_steps": 28611, "tokens": 21873295360, "loss": 2.774255871772766, "ce_loss": 2.7732847332954407, "z_loss": 9.711050033569336, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35850846767425537, "tokens_per_second": 3043086.4174844846, "eta_seconds": 2670.812281012535, "data_wait_seconds": 1.3470649719238281e-05}
|
| 2088 |
+
{"step": 20870, "total_steps": 28611, "tokens": 21883781120, "loss": 2.730310618877411, "ce_loss": 2.7290915846824646, "z_loss": 12.190335750579834, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3105577230453491, "tokens_per_second": 2971453.4788028426, "eta_seconds": 2731.668819284439, "data_wait_seconds": 0.2942503094673157}
|
| 2089 |
+
{"step": 20880, "total_steps": 28611, "tokens": 21894266880, "loss": 2.7931008338928223, "ce_loss": 2.791871726512909, "z_loss": 12.290825605392456, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3547567129135132, "tokens_per_second": 4400720.829151875, "eta_seconds": 1842.0939138650895, "data_wait_seconds": 1.341104507446289e-05}
|
| 2090 |
+
{"step": 20890, "total_steps": 28611, "tokens": 21904752640, "loss": 2.7737621665000916, "ce_loss": 2.7726365327835083, "z_loss": 11.256428956985474, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3568231463432312, "tokens_per_second": 2960221.592322567, "eta_seconds": 2734.949071717262, "data_wait_seconds": 1.4603137969970703e-05}
|
| 2091 |
+
{"step": 20900, "total_steps": 28611, "tokens": 21915238400, "loss": 2.758348226547241, "ce_loss": 2.7571195363998413, "z_loss": 12.286661624908447, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33132532238960266, "tokens_per_second": 4110825.209153079, "eta_seconds": 1966.8969427347183, "data_wait_seconds": 1.4483928680419922e-05}
|
| 2092 |
+
{"step": 20910, "total_steps": 28611, "tokens": 21925724160, "loss": 2.7734642028808594, "ce_loss": 2.77219820022583, "z_loss": 12.65976858139038, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2999300956726074, "tokens_per_second": 4161094.247507935, "eta_seconds": 1940.6154476881027, "data_wait_seconds": 1.6629695892333984e-05}
|
| 2093 |
+
{"step": 20920, "total_steps": 28611, "tokens": 21936209920, "loss": 2.7798887491226196, "ce_loss": 2.778849244117737, "z_loss": 10.394944429397583, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31251630187034607, "tokens_per_second": 8411857.861195868, "eta_seconds": 958.7178182363509, "data_wait_seconds": 1.239776611328125e-05}
|
| 2094 |
+
{"step": 20930, "total_steps": 28611, "tokens": 21946695680, "loss": 2.773733973503113, "ce_loss": 2.772729992866516, "z_loss": 10.03950834274292, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.40910816192626953, "tokens_per_second": 4196433.080198923, "eta_seconds": 1919.275752067566, "data_wait_seconds": 1.4007091522216797e-05}
|
| 2095 |
+
{"step": 20940, "total_steps": 28611, "tokens": 21957181440, "loss": 2.800086796283722, "ce_loss": 2.798980414867401, "z_loss": 11.06389570236206, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.304279625415802, "tokens_per_second": 4003199.349941186, "eta_seconds": 2009.2995109319686, "data_wait_seconds": 1.4126300811767578e-05}
|
| 2096 |
+
{"step": 20950, "total_steps": 28611, "tokens": 21967667200, "loss": 2.8039124608039856, "ce_loss": 2.8029590845108032, "z_loss": 9.533538579940796, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3191576898097992, "tokens_per_second": 3064554.1797443056, "eta_seconds": 2621.308113622665, "data_wait_seconds": 0.2495560646057129}
|
| 2097 |
+
{"step": 20960, "total_steps": 28611, "tokens": 21978152960, "loss": 2.811550736427307, "ce_loss": 2.810363233089447, "z_loss": 11.874687433242798, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38645583391189575, "tokens_per_second": 4349172.252993757, "eta_seconds": 1844.639510536194, "data_wait_seconds": 2.0563602447509766e-05}
|
| 2098 |
+
{"step": 20970, "total_steps": 28611, "tokens": 21988638720, "loss": 2.7834277153015137, "ce_loss": 2.7823628783226013, "z_loss": 10.648452281951904, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29218053817749023, "tokens_per_second": 4522412.399858879, "eta_seconds": 1771.6582451105119, "data_wait_seconds": 1.71661376953125e-05}
|
| 2099 |
+
{"step": 20980, "total_steps": 28611, "tokens": 21999124480, "loss": 2.75441175699234, "ce_loss": 2.753248631954193, "z_loss": 11.63086199760437, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30036529898643494, "tokens_per_second": 3010649.708931849, "eta_seconds": 2657.7929116964337, "data_wait_seconds": 1.4543533325195312e-05}
|
| 2100 |
+
{"step": 20990, "total_steps": 28611, "tokens": 22009610240, "loss": 2.8017061948776245, "ce_loss": 2.8006752133369446, "z_loss": 10.309760093688965, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3518034815788269, "tokens_per_second": 2837366.071579189, "eta_seconds": 2816.4140595197678, "data_wait_seconds": 1.8417835235595703e-05}
|
| 2101 |
+
{"step": 21000, "total_steps": 28611, "tokens": 22020096000, "loss": 2.7913365364074707, "ce_loss": 2.7900993824005127, "z_loss": 12.371025800704956, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3555220365524292, "tokens_per_second": 2632375.585569587, "eta_seconds": 3031.752755856514, "data_wait_seconds": 1.8715858459472656e-05}
|
| 2102 |
+
{"step": 21010, "total_steps": 28611, "tokens": 22030581760, "loss": 2.789371073246002, "ce_loss": 2.7880964279174805, "z_loss": 12.74621844291687, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3272797167301178, "tokens_per_second": 4082241.833517951, "eta_seconds": 1952.414016866684, "data_wait_seconds": 1.4543533325195312e-05}
|
| 2103 |
+
{"step": 21020, "total_steps": 28611, "tokens": 22041067520, "loss": 2.7581709027290344, "ce_loss": 2.7571755051612854, "z_loss": 9.953750133514404, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3304370939731598, "tokens_per_second": 2764605.3986200755, "eta_seconds": 2879.1596876621247, "data_wait_seconds": 1.7523765563964844e-05}
|
| 2104 |
+
{"step": 21030, "total_steps": 28611, "tokens": 22051553280, "loss": 2.7154483795166016, "ce_loss": 2.714145064353943, "z_loss": 13.032800912857056, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37909945845603943, "tokens_per_second": 4028114.9107953254, "eta_seconds": 1973.442871427536, "data_wait_seconds": 1.3828277587890625e-05}
|
| 2105 |
+
{"step": 21040, "total_steps": 28611, "tokens": 22062039040, "loss": 2.7821589708328247, "ce_loss": 2.780836820602417, "z_loss": 13.221200227737427, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34924057126045227, "tokens_per_second": 2923843.077249138, "eta_seconds": 2715.1829582691194, "data_wait_seconds": 1.8775463104248047e-05}
|
| 2106 |
+
{"step": 21050, "total_steps": 28611, "tokens": 22072524800, "loss": 2.8005743622779846, "ce_loss": 2.7992523908615112, "z_loss": 13.219559669494629, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3389388918876648, "tokens_per_second": 4126302.272842332, "eta_seconds": 1921.4014417171477, "data_wait_seconds": 1.436471939086914e-05}
|
| 2107 |
+
{"step": 21060, "total_steps": 28611, "tokens": 22083010560, "loss": 2.804387152194977, "ce_loss": 2.803356409072876, "z_loss": 10.30792760848999, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34223395586013794, "tokens_per_second": 2923755.415158574, "eta_seconds": 2708.09156434536, "data_wait_seconds": 1.8477439880371094e-05}
|
| 2108 |
+
{"step": 21070, "total_steps": 28611, "tokens": 22093496320, "loss": 2.767723560333252, "ce_loss": 2.766714632511139, "z_loss": 10.089649677276611, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.38770294189453125, "tokens_per_second": 2944705.2149615423, "eta_seconds": 2685.264241671562, "data_wait_seconds": 0.5769273638725281}
|
| 2109 |
+
{"step": 21080, "total_steps": 28611, "tokens": 22103982080, "loss": 2.766188383102417, "ce_loss": 2.7650344371795654, "z_loss": 11.538944244384766, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2993936836719513, "tokens_per_second": 4382176.459057523, "eta_seconds": 1802.0328322649002, "data_wait_seconds": 1.4185905456542969e-05}
|
| 2110 |
+
{"step": 21090, "total_steps": 28611, "tokens": 22114467840, "loss": 2.765583336353302, "ce_loss": 2.7643763422966003, "z_loss": 12.070204496383667, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3229614496231079, "tokens_per_second": 4567886.942674352, "eta_seconds": 1726.4744497776032, "data_wait_seconds": 1.1682510375976562e-05}
|
| 2111 |
+
{"step": 21100, "total_steps": 28611, "tokens": 22124953600, "loss": 2.803582787513733, "ce_loss": 2.802516996860504, "z_loss": 10.657689094543457, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34016022086143494, "tokens_per_second": 4199495.618127612, "eta_seconds": 1875.4286352872846, "data_wait_seconds": 1.52587890625e-05}
|
| 2112 |
+
{"step": 21110, "total_steps": 28611, "tokens": 22135439360, "loss": 2.800447404384613, "ce_loss": 2.7994646430015564, "z_loss": 9.82776927947998, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2956405282020569, "tokens_per_second": 4020487.3670492456, "eta_seconds": 1956.3221714019776, "data_wait_seconds": 1.3709068298339844e-05}
|
| 2113 |
+
{"step": 21120, "total_steps": 28611, "tokens": 22145925120, "loss": 2.8171483874320984, "ce_loss": 2.815781056880951, "z_loss": 13.672789573669434, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3584989607334137, "tokens_per_second": 4069823.770632414, "eta_seconds": 1930.0302073717116, "data_wait_seconds": 1.4603137969970703e-05}
|
| 2114 |
+
{"step": 21130, "total_steps": 28611, "tokens": 22156410880, "loss": 2.810912787914276, "ce_loss": 2.8097692131996155, "z_loss": 11.436083793640137, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3129065930843353, "tokens_per_second": 4043723.7126066396, "eta_seconds": 1939.894417500496, "data_wait_seconds": 1.5735626220703125e-05}
|
| 2115 |
+
{"step": 21140, "total_steps": 28611, "tokens": 22166896640, "loss": 2.794067859649658, "ce_loss": 2.7930082082748413, "z_loss": 10.596333742141724, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37038061022758484, "tokens_per_second": 8611955.631673804, "eta_seconds": 909.6553246498107, "data_wait_seconds": 1.823902130126953e-05}
|
| 2116 |
+
{"step": 21150, "total_steps": 28611, "tokens": 22177382400, "loss": 2.7966049313545227, "ce_loss": 2.795652210712433, "z_loss": 9.527234554290771, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37140220403671265, "tokens_per_second": 2840016.553740287, "eta_seconds": 2754.711244797707, "data_wait_seconds": 1.4722347259521484e-05}
|
| 2117 |
+
{"step": 21160, "total_steps": 28611, "tokens": 22187868160, "loss": 2.8201608657836914, "ce_loss": 2.8191553354263306, "z_loss": 10.055147647857666, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2825658917427063, "tokens_per_second": 2958292.5593298534, "eta_seconds": 2641.03012778759, "data_wait_seconds": 1.4662742614746094e-05}
|
| 2118 |
+
{"step": 21170, "total_steps": 28611, "tokens": 22198353920, "loss": 2.7898901104927063, "ce_loss": 2.7887256145477295, "z_loss": 11.645158290863037, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3167031705379486, "tokens_per_second": 4083901.3818854983, "eta_seconds": 1910.5392825126648, "data_wait_seconds": 1.6927719116210938e-05}
|
| 2119 |
+
{"step": 21180, "total_steps": 28611, "tokens": 22208839680, "loss": 2.810899078845978, "ce_loss": 2.80968177318573, "z_loss": 12.173495769500732, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2970929443836212, "tokens_per_second": 2754059.2896130104, "eta_seconds": 2829.2667065620426, "data_wait_seconds": 1.6510486602783203e-05}
|
| 2120 |
+
{"step": 21190, "total_steps": 28611, "tokens": 22219325440, "loss": 2.864236295223236, "ce_loss": 2.863118290901184, "z_loss": 11.179711103439331, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3840278387069702, "tokens_per_second": 2903822.5012726374, "eta_seconds": 2679.7376535892486, "data_wait_seconds": 1.329183578491211e-05}
|
| 2121 |
+
{"step": 21200, "total_steps": 28611, "tokens": 22229811200, "loss": 2.781132936477661, "ce_loss": 2.7801204323768616, "z_loss": 10.125498533248901, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3058556616306305, "tokens_per_second": 2925632.843416305, "eta_seconds": 2656.1763392448424, "data_wait_seconds": 1.3649463653564453e-05}
|
| 2122 |
+
{"step": 21210, "total_steps": 28611, "tokens": 22240296960, "loss": 2.7985796332359314, "ce_loss": 2.7973119020462036, "z_loss": 12.67746615409851, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3357684016227722, "tokens_per_second": 2780983.7300918796, "eta_seconds": 2790.563242793083, "data_wait_seconds": 1.3947486877441406e-05}
|
| 2123 |
+
{"step": 21220, "total_steps": 28611, "tokens": 22250782720, "loss": 2.8008816838264465, "ce_loss": 2.79985511302948, "z_loss": 10.266124248504639, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32537227869033813, "tokens_per_second": 4112605.761817562, "eta_seconds": 1884.4561489343641, "data_wait_seconds": 1.6510486602783203e-05}
|
| 2124 |
+
{"step": 21230, "total_steps": 28611, "tokens": 22261268480, "loss": 2.810728967189789, "ce_loss": 2.809515416622162, "z_loss": 12.1360342502594, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35124334692955017, "tokens_per_second": 3028142.431286233, "eta_seconds": 2555.87035009861, "data_wait_seconds": 1.8358230590820312e-05}
|
| 2125 |
+
{"step": 21240, "total_steps": 28611, "tokens": 22271754240, "loss": 2.8176381587982178, "ce_loss": 2.816622018814087, "z_loss": 10.161787748336792, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32826370000839233, "tokens_per_second": 4350933.300051057, "eta_seconds": 1776.412820649147, "data_wait_seconds": 1.5676021575927734e-05}
|
| 2126 |
+
{"step": 21250, "total_steps": 28611, "tokens": 22282240000, "loss": 2.8344646096229553, "ce_loss": 2.8332486748695374, "z_loss": 12.15908432006836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2856318950653076, "tokens_per_second": 2932963.885449165, "eta_seconds": 2631.661431050301, "data_wait_seconds": 1.3530254364013672e-05}
|
| 2127 |
+
{"step": 21260, "total_steps": 28611, "tokens": 22292725760, "loss": 2.782346487045288, "ce_loss": 2.781363606452942, "z_loss": 9.828808307647705, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34004396200180054, "tokens_per_second": 2835791.064569725, "eta_seconds": 2718.141781425476, "data_wait_seconds": 2.205371856689453e-05}
|
| 2128 |
+
{"step": 21270, "total_steps": 28611, "tokens": 22303211520, "loss": 2.8184803128242493, "ce_loss": 2.817471742630005, "z_loss": 10.085754632949829, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33723610639572144, "tokens_per_second": 4126577.1568915923, "eta_seconds": 1865.3707717895509, "data_wait_seconds": 1.3172626495361328e-05}
|
| 2129 |
+
{"step": 21280, "total_steps": 28611, "tokens": 22313697280, "loss": 2.783905327320099, "ce_loss": 2.7827577590942383, "z_loss": 11.47532033920288, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37718337774276733, "tokens_per_second": 3038403.4879121454, "eta_seconds": 2529.983488559723, "data_wait_seconds": 1.728534698486328e-05}
|
| 2130 |
+
{"step": 21290, "total_steps": 28611, "tokens": 22324183040, "loss": 2.8082545399665833, "ce_loss": 2.8072938323020935, "z_loss": 9.606462478637695, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33242592215538025, "tokens_per_second": 2664668.6373599437, "eta_seconds": 2880.8928766489025, "data_wait_seconds": 1.9431114196777344e-05}
|
| 2131 |
+
{"step": 21300, "total_steps": 28611, "tokens": 22334668800, "loss": 2.759221374988556, "ce_loss": 2.758285939693451, "z_loss": 9.354151010513306, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3249620199203491, "tokens_per_second": 2769865.36197437, "eta_seconds": 2767.6937808036805, "data_wait_seconds": 1.4066696166992188e-05}
|
| 2132 |
+
{"step": 21310, "total_steps": 28611, "tokens": 22345154560, "loss": 2.802938997745514, "ce_loss": 2.801849126815796, "z_loss": 10.898849964141846, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3918766677379608, "tokens_per_second": 2829950.3587068925, "eta_seconds": 2705.225323987007, "data_wait_seconds": 1.7404556274414062e-05}
|
| 2133 |
+
{"step": 21320, "total_steps": 28611, "tokens": 22355640320, "loss": 2.7870572209358215, "ce_loss": 2.785829544067383, "z_loss": 12.27621054649353, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3190610110759735, "tokens_per_second": 4412124.276031534, "eta_seconds": 1732.7634349584578, "data_wait_seconds": 1.4185905456542969e-05}
|
| 2134 |
+
{"step": 21330, "total_steps": 28611, "tokens": 22366126080, "loss": 2.7489922642707825, "ce_loss": 2.748069167137146, "z_loss": 9.230479955673218, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33323538303375244, "tokens_per_second": 3030071.1825668165, "eta_seconds": 2519.6377893447875, "data_wait_seconds": 1.537799835205078e-05}
|
| 2135 |
+
{"step": 21340, "total_steps": 28611, "tokens": 22376611840, "loss": 2.934876501560211, "ce_loss": 2.9338337779045105, "z_loss": 10.426844358444214, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35180971026420593, "tokens_per_second": 2878463.756384274, "eta_seconds": 2648.703176856041, "data_wait_seconds": 1.8596649169921875e-05}
|
| 2136 |
+
{"step": 21350, "total_steps": 28611, "tokens": 22387097600, "loss": 2.8022266626358032, "ce_loss": 2.8011739253997803, "z_loss": 10.527608394622803, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30254361033439636, "tokens_per_second": 3832209.643790383, "eta_seconds": 1986.7676989793779, "data_wait_seconds": 1.5437602996826172e-05}
|
| 2137 |
+
{"step": 21360, "total_steps": 28611, "tokens": 22397583360, "loss": 2.7714486718177795, "ce_loss": 2.7702134251594543, "z_loss": 12.352917909622192, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.41355961561203003, "tokens_per_second": 2971454.8841263084, "eta_seconds": 2558.7548431634905, "data_wait_seconds": 0.2744078040122986}
|
| 2138 |
+
{"step": 21370, "total_steps": 28611, "tokens": 22408069120, "loss": 2.8172672986984253, "ce_loss": 2.8160940408706665, "z_loss": 11.73270869255066, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3300844132900238, "tokens_per_second": 3583896.651148835, "eta_seconds": 2118.570805764198, "data_wait_seconds": 1.4901161193847656e-05}
|
| 2139 |
+
{"step": 21380, "total_steps": 28611, "tokens": 22418554880, "loss": 2.8250003457069397, "ce_loss": 2.8238419890403748, "z_loss": 11.58339262008667, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3473578095436096, "tokens_per_second": 3152598.7992754118, "eta_seconds": 2405.0802334070204, "data_wait_seconds": 1.7464160919189453e-05}
|
| 2140 |
+
{"step": 21390, "total_steps": 28611, "tokens": 22429040640, "loss": 2.7938775420188904, "ce_loss": 2.7926185727119446, "z_loss": 12.589849948883057, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.37640899419784546, "tokens_per_second": 2256226.3782209046, "eta_seconds": 3355.9430778265, "data_wait_seconds": 1.7642974853515625e-05}
|
| 2141 |
+
{"step": 21400, "total_steps": 28611, "tokens": 22439526400, "loss": 2.79570996761322, "ce_loss": 2.7948006987571716, "z_loss": 9.092745542526245, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.47153905034065247, "tokens_per_second": 4087107.5434159976, "eta_seconds": 1850.0324387550354, "data_wait_seconds": 1.2695789337158203e-05}
|
| 2142 |
+
{"step": 21410, "total_steps": 28611, "tokens": 22450012160, "loss": 2.7985708713531494, "ce_loss": 2.797470271587372, "z_loss": 11.006359815597534, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28472229838371277, "tokens_per_second": 2935394.578203344, "eta_seconds": 2572.3273566246035, "data_wait_seconds": 1.4543533325195312e-05}
|
| 2143 |
+
{"step": 21420, "total_steps": 28611, "tokens": 22460497920, "loss": 2.8052310943603516, "ce_loss": 2.804298996925354, "z_loss": 9.320524454116821, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3244243860244751, "tokens_per_second": 3978540.8128603026, "eta_seconds": 1895.2451088666917, "data_wait_seconds": 1.1920928955078125e-05}
|
| 2144 |
+
{"step": 21430, "total_steps": 28611, "tokens": 22470983680, "loss": 2.8168949484825134, "ce_loss": 2.8157830834388733, "z_loss": 11.118449687957764, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.34776702523231506, "tokens_per_second": 2201855.392050024, "eta_seconds": 3419.763297438622, "data_wait_seconds": 0.29806792736053467}
|
| 2145 |
+
{"step": 21440, "total_steps": 28611, "tokens": 22481469440, "loss": 2.778375208377838, "ce_loss": 2.7772164940834045, "z_loss": 11.587365865707397, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2924649119377136, "tokens_per_second": 3138963.851055385, "eta_seconds": 2395.484259390831, "data_wait_seconds": 1.817941665649414e-05}
|
| 2146 |
+
{"step": 21450, "total_steps": 28611, "tokens": 22491955200, "loss": 2.8209659457206726, "ce_loss": 2.8198007941246033, "z_loss": 11.651555299758911, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.35403141379356384, "tokens_per_second": 4085625.282733799, "eta_seconds": 1837.8711253166198, "data_wait_seconds": 1.4483928680419922e-05}
|