Save 20% checkpoint at 6,001,000,448 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": 20,
|
| 54 |
+
"step": 5723,
|
| 55 |
"total_steps": 28611,
|
| 56 |
+
"tokens_seen": 6001000448,
|
| 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": 1842.5009796619415
|
| 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 sha256:2ac25fe8fe1f6fa63fa680abb136b5fd110f1e363ff37052bc53254adbc2e6d8
|
| 3 |
size 12811532
|
training_metrics.jsonl
CHANGED
|
@@ -428,3 +428,146 @@
|
|
| 428 |
{"step": 4270, "total_steps": 28611, "tokens": 4477419520, "loss": 2.825702428817749, "ce_loss": 2.823436677455902, "z_loss": 22.65763282775879, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24787376821041107, "tokens_per_second": 3940433.700354241, "eta_seconds": 6477.304367208481, "data_wait_seconds": 1.2874603271484375e-05}
|
| 429 |
{"step": 4280, "total_steps": 28611, "tokens": 4487905280, "loss": 2.7833526730537415, "ce_loss": 2.781288266181946, "z_loss": 20.643744945526123, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25412625074386597, "tokens_per_second": 3974595.132938318, "eta_seconds": 6418.99408686161, "data_wait_seconds": 1.2755393981933594e-05}
|
| 430 |
{"step": 4290, "total_steps": 28611, "tokens": 4498391040, "loss": 2.806715250015259, "ce_loss": 2.8045395016670227, "z_loss": 21.75728750228882, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28592950105667114, "tokens_per_second": 2688625.772867199, "eta_seconds": 9485.298085498809, "data_wait_seconds": 1.4603137969970703e-05}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 428 |
{"step": 4270, "total_steps": 28611, "tokens": 4477419520, "loss": 2.825702428817749, "ce_loss": 2.823436677455902, "z_loss": 22.65763282775879, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24787376821041107, "tokens_per_second": 3940433.700354241, "eta_seconds": 6477.304367208481, "data_wait_seconds": 1.2874603271484375e-05}
|
| 429 |
{"step": 4280, "total_steps": 28611, "tokens": 4487905280, "loss": 2.7833526730537415, "ce_loss": 2.781288266181946, "z_loss": 20.643744945526123, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25412625074386597, "tokens_per_second": 3974595.132938318, "eta_seconds": 6418.99408686161, "data_wait_seconds": 1.2755393981933594e-05}
|
| 430 |
{"step": 4290, "total_steps": 28611, "tokens": 4498391040, "loss": 2.806715250015259, "ce_loss": 2.8045395016670227, "z_loss": 21.75728750228882, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28592950105667114, "tokens_per_second": 2688625.772867199, "eta_seconds": 9485.298085498809, "data_wait_seconds": 1.4603137969970703e-05}
|
| 431 |
+
{"step": 4300, "total_steps": 28611, "tokens": 4508876800, "loss": 2.813985288143158, "ce_loss": 2.8113414645195007, "z_loss": 26.438339710235596, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2755333483219147, "tokens_per_second": 2448398.6233075145, "eta_seconds": 10411.67516323924, "data_wait_seconds": 0.24375534057617188}
|
| 432 |
+
{"step": 4310, "total_steps": 28611, "tokens": 4519362560, "loss": 2.8453184962272644, "ce_loss": 2.8428094387054443, "z_loss": 25.09046697616577, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32264789938926697, "tokens_per_second": 4436656.514420747, "eta_seconds": 5743.389260172844, "data_wait_seconds": 0.280813992023468}
|
| 433 |
+
{"step": 4320, "total_steps": 28611, "tokens": 4529848320, "loss": 2.8210391998291016, "ce_loss": 2.819019138813019, "z_loss": 20.20037031173706, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2666853666305542, "tokens_per_second": 4459827.6110341335, "eta_seconds": 5711.19824295044, "data_wait_seconds": 1.4901161193847656e-05}
|
| 434 |
+
{"step": 4330, "total_steps": 28611, "tokens": 4540334080, "loss": 2.8092445135116577, "ce_loss": 2.8067787289619446, "z_loss": 24.658154010772705, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27939343452453613, "tokens_per_second": 4075574.805748742, "eta_seconds": 6247.087851285934, "data_wait_seconds": 1.4662742614746094e-05}
|
| 435 |
+
{"step": 4340, "total_steps": 28611, "tokens": 4550819840, "loss": 2.823467195034027, "ce_loss": 2.821645200252533, "z_loss": 18.220465183258057, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2786826491355896, "tokens_per_second": 4035428.5511019505, "eta_seconds": 6306.638260030746, "data_wait_seconds": 1.704692840576172e-05}
|
| 436 |
+
{"step": 4350, "total_steps": 28611, "tokens": 4561305600, "loss": 2.7976104617118835, "ce_loss": 2.79529345035553, "z_loss": 23.170156478881836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24075180292129517, "tokens_per_second": 4442990.918638766, "eta_seconds": 5725.760597276688, "data_wait_seconds": 0.5360022187232971}
|
| 437 |
+
{"step": 4360, "total_steps": 28611, "tokens": 4571791360, "loss": 2.8469218611717224, "ce_loss": 2.844725489616394, "z_loss": 21.963784217834473, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2781186103820801, "tokens_per_second": 7082885.978343476, "eta_seconds": 3590.2055537462234, "data_wait_seconds": 1.3649463653564453e-05}
|
| 438 |
+
{"step": 4370, "total_steps": 28611, "tokens": 4582277120, "loss": 2.81890469789505, "ce_loss": 2.816380262374878, "z_loss": 25.244498252868652, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3169446289539337, "tokens_per_second": 3935941.7586153075, "eta_seconds": 6458.055625534058, "data_wait_seconds": 1.4722347259521484e-05}
|
| 439 |
+
{"step": 4380, "total_steps": 28611, "tokens": 4592762880, "loss": 2.864306390285492, "ce_loss": 2.862175762653351, "z_loss": 21.305965423583984, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28790897130966187, "tokens_per_second": 4088623.1879972382, "eta_seconds": 6214.327877068519, "data_wait_seconds": 1.519918441772461e-05}
|
| 440 |
+
{"step": 4390, "total_steps": 28611, "tokens": 4603248640, "loss": 2.8226616978645325, "ce_loss": 2.8203330636024475, "z_loss": 23.28635311126709, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.261942058801651, "tokens_per_second": 4075909.8307662695, "eta_seconds": 6231.138653826713, "data_wait_seconds": 1.9550323486328125e-05}
|
| 441 |
+
{"step": 4400, "total_steps": 28611, "tokens": 4613734400, "loss": 2.8401377201080322, "ce_loss": 2.8372939229011536, "z_loss": 28.437367916107178, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2619682550430298, "tokens_per_second": 8494766.659270361, "eta_seconds": 2988.5545482635503, "data_wait_seconds": 1.5795230865478516e-05}
|
| 442 |
+
{"step": 4410, "total_steps": 28611, "tokens": 4624220160, "loss": 2.8420597910881042, "ce_loss": 2.8398083448410034, "z_loss": 22.51428747177124, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24239084124565125, "tokens_per_second": 3943217.648701576, "eta_seconds": 6435.502687597275, "data_wait_seconds": 1.33514404296875e-05}
|
| 443 |
+
{"step": 4420, "total_steps": 28611, "tokens": 4634705920, "loss": 2.840710699558258, "ce_loss": 2.8388746976852417, "z_loss": 18.36010456085205, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2473345547914505, "tokens_per_second": 2896803.749486165, "eta_seconds": 8756.582844281196, "data_wait_seconds": 1.52587890625e-05}
|
| 444 |
+
{"step": 4430, "total_steps": 28611, "tokens": 4645191680, "loss": 2.817770004272461, "ce_loss": 2.8151691555976868, "z_loss": 26.008590698242188, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25477486848831177, "tokens_per_second": 2753681.3105931836, "eta_seconds": 9207.897863292694, "data_wait_seconds": 1.722574234008789e-05}
|
| 445 |
+
{"step": 4440, "total_steps": 28611, "tokens": 4655677440, "loss": 2.809393346309662, "ce_loss": 2.8069573044776917, "z_loss": 24.360872745513916, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2830348014831543, "tokens_per_second": 4134557.7603305504, "eta_seconds": 6130.070485210419, "data_wait_seconds": 3.0875205993652344e-05}
|
| 446 |
+
{"step": 4450, "total_steps": 28611, "tokens": 4666163200, "loss": 2.822762668132782, "ce_loss": 2.8206299543380737, "z_loss": 21.3268141746521, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29750919342041016, "tokens_per_second": 4215652.511123003, "eta_seconds": 6009.661533808708, "data_wait_seconds": 1.531839370727539e-05}
|
| 447 |
+
{"step": 4460, "total_steps": 28611, "tokens": 4676648960, "loss": 2.8818262815475464, "ce_loss": 2.879610598087311, "z_loss": 22.156717777252197, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3019655644893646, "tokens_per_second": 2876266.7153303004, "eta_seconds": 8804.523878479004, "data_wait_seconds": 1.3887882232666016e-05}
|
| 448 |
+
{"step": 4470, "total_steps": 28611, "tokens": 4687134720, "loss": 2.805036723613739, "ce_loss": 2.8027461767196655, "z_loss": 22.905757904052734, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27942439913749695, "tokens_per_second": 1274003.807517383, "eta_seconds": 19869.385842204094, "data_wait_seconds": 0.5374723076820374}
|
| 449 |
+
{"step": 4480, "total_steps": 28611, "tokens": 4697620480, "loss": 2.816640317440033, "ce_loss": 2.8145176768302917, "z_loss": 21.225852489471436, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2592627704143524, "tokens_per_second": 4564854.985498591, "eta_seconds": 5543.042996191978, "data_wait_seconds": 1.3828277587890625e-05}
|
| 450 |
+
{"step": 4490, "total_steps": 28611, "tokens": 4708106240, "loss": 2.8427014350891113, "ce_loss": 2.8403168320655823, "z_loss": 23.846176147460938, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23748761415481567, "tokens_per_second": 1669939.1170117534, "eta_seconds": 15145.88252849579, "data_wait_seconds": 1.8835067749023438e-05}
|
| 451 |
+
{"step": 4500, "total_steps": 28611, "tokens": 4718592000, "loss": 2.8447237610816956, "ce_loss": 2.842775046825409, "z_loss": 19.487250328063965, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24079006910324097, "tokens_per_second": 3462001.8700783793, "eta_seconds": 7302.773621964454, "data_wait_seconds": 1.5854835510253906e-05}
|
| 452 |
+
{"step": 4510, "total_steps": 28611, "tokens": 4729077760, "loss": 2.8237192034721375, "ce_loss": 2.8216204047203064, "z_loss": 20.987806797027588, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29478657245635986, "tokens_per_second": 2809966.619447204, "eta_seconds": 8993.605120110513, "data_wait_seconds": 1.7404556274414062e-05}
|
| 453 |
+
{"step": 4520, "total_steps": 28611, "tokens": 4739563520, "loss": 2.8767427802085876, "ce_loss": 2.874576687812805, "z_loss": 21.6608247756958, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2909846603870392, "tokens_per_second": 4116827.6603561365, "eta_seconds": 6136.094706916809, "data_wait_seconds": 1.5854835510253906e-05}
|
| 454 |
+
{"step": 4530, "total_steps": 28611, "tokens": 4750049280, "loss": 2.8661959171295166, "ce_loss": 2.8640522360801697, "z_loss": 21.436707019805908, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2514670193195343, "tokens_per_second": 2997768.4726865147, "eta_seconds": 8423.185074520112, "data_wait_seconds": 1.4722347259521484e-05}
|
| 455 |
+
{"step": 4540, "total_steps": 28611, "tokens": 4760535040, "loss": 2.8323405981063843, "ce_loss": 2.8299620747566223, "z_loss": 23.78566312789917, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.32822147011756897, "tokens_per_second": 2773439.6279115053, "eta_seconds": 9100.711132121087, "data_wait_seconds": 0.2839112877845764}
|
| 456 |
+
{"step": 4550, "total_steps": 28611, "tokens": 4771020800, "loss": 2.900282382965088, "ce_loss": 2.898561954498291, "z_loss": 17.204466342926025, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2738020718097687, "tokens_per_second": 3899341.0654114196, "eta_seconds": 6470.269389820099, "data_wait_seconds": 1.5079975128173828e-05}
|
| 457 |
+
{"step": 4560, "total_steps": 28611, "tokens": 4781506560, "loss": 2.8248809576034546, "ce_loss": 2.822308361530304, "z_loss": 25.72583532333374, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26712438464164734, "tokens_per_second": 4365114.342458754, "eta_seconds": 5777.466384029389, "data_wait_seconds": 1.531839370727539e-05}
|
| 458 |
+
{"step": 4570, "total_steps": 28611, "tokens": 4791992320, "loss": 2.8323585987091064, "ce_loss": 2.830134391784668, "z_loss": 22.24259901046753, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27263033390045166, "tokens_per_second": 2878396.878892634, "eta_seconds": 8757.935988903046, "data_wait_seconds": 1.436471939086914e-05}
|
| 459 |
+
{"step": 4580, "total_steps": 28611, "tokens": 4802478080, "loss": 2.841510534286499, "ce_loss": 2.8395901918411255, "z_loss": 19.203777313232422, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.311726838350296, "tokens_per_second": 2693614.517524723, "eta_seconds": 9354.838894748687, "data_wait_seconds": 1.5676021575927734e-05}
|
| 460 |
+
{"step": 4590, "total_steps": 28611, "tokens": 4812963840, "loss": 2.8999544382095337, "ce_loss": 2.8976431488990784, "z_loss": 23.113037109375, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2668812870979309, "tokens_per_second": 4416761.655265858, "eta_seconds": 5702.785448241233, "data_wait_seconds": 1.8417835235595703e-05}
|
| 461 |
+
{"step": 4600, "total_steps": 28611, "tokens": 4823449600, "loss": 2.869915246963501, "ce_loss": 2.8679837584495544, "z_loss": 19.314618587493896, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3672197759151459, "tokens_per_second": 3979736.41637846, "eta_seconds": 6326.388409137726, "data_wait_seconds": 1.5676021575927734e-05}
|
| 462 |
+
{"step": 4610, "total_steps": 28611, "tokens": 4833935360, "loss": 2.8789435029029846, "ce_loss": 2.877033770084381, "z_loss": 19.097105979919434, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2868017852306366, "tokens_per_second": 2777254.081963997, "eta_seconds": 9061.7825496912, "data_wait_seconds": 1.3709068298339844e-05}
|
| 463 |
+
{"step": 4620, "total_steps": 28611, "tokens": 4844421120, "loss": 2.8624090552330017, "ce_loss": 2.860216975212097, "z_loss": 21.920615196228027, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26749539375305176, "tokens_per_second": 2968341.7424913156, "eta_seconds": 8474.89574933052, "data_wait_seconds": 1.5437602996826172e-05}
|
| 464 |
+
{"step": 4630, "total_steps": 28611, "tokens": 4854906880, "loss": 2.834871530532837, "ce_loss": 2.8330237865448, "z_loss": 18.478076457977295, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3219383656978607, "tokens_per_second": 2761545.1749942782, "eta_seconds": 9105.735906004906, "data_wait_seconds": 1.4126300811767578e-05}
|
| 465 |
+
{"step": 4640, "total_steps": 28611, "tokens": 4865392640, "loss": 2.8343751430511475, "ce_loss": 2.831794261932373, "z_loss": 25.808589458465576, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2951001524925232, "tokens_per_second": 2728256.611658986, "eta_seconds": 9212.995283722878, "data_wait_seconds": 1.7940998077392578e-05}
|
| 466 |
+
{"step": 4650, "total_steps": 28611, "tokens": 4875878400, "loss": 2.8194404244422913, "ce_loss": 2.8172603249549866, "z_loss": 21.801403522491455, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25041332840919495, "tokens_per_second": 4334972.658916761, "eta_seconds": 5795.8680510520935, "data_wait_seconds": 1.7881393432617188e-05}
|
| 467 |
+
{"step": 4660, "total_steps": 28611, "tokens": 4886364160, "loss": 2.8628475666046143, "ce_loss": 2.861047923564911, "z_loss": 17.996880531311035, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2819095849990845, "tokens_per_second": 3800489.470823299, "eta_seconds": 6608.212960147858, "data_wait_seconds": 1.7821788787841797e-05}
|
| 468 |
+
{"step": 4670, "total_steps": 28611, "tokens": 4896849920, "loss": 2.837507486343384, "ce_loss": 2.835231602191925, "z_loss": 22.758077144622803, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2622587978839874, "tokens_per_second": 2857608.7779407413, "eta_seconds": 8784.952723336219, "data_wait_seconds": 1.3709068298339844e-05}
|
| 469 |
+
{"step": 4680, "total_steps": 28611, "tokens": 4907335680, "loss": 2.8523043990135193, "ce_loss": 2.8501628041267395, "z_loss": 21.416071891784668, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28148889541625977, "tokens_per_second": 2801210.1960578, "eta_seconds": 8958.082578492164, "data_wait_seconds": 1.5735626220703125e-05}
|
| 470 |
+
{"step": 4690, "total_steps": 28611, "tokens": 4917821440, "loss": 2.8420247435569763, "ce_loss": 2.8401339650154114, "z_loss": 18.90713119506836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2608320116996765, "tokens_per_second": 4305950.834652454, "eta_seconds": 5825.191103935242, "data_wait_seconds": 1.627206802368164e-05}
|
| 471 |
+
{"step": 4700, "total_steps": 28611, "tokens": 4928307200, "loss": 2.883677065372467, "ce_loss": 2.881744384765625, "z_loss": 19.326571941375732, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24689917266368866, "tokens_per_second": 4145540.4015815477, "eta_seconds": 6048.065706086159, "data_wait_seconds": 1.710653305053711e-05}
|
| 472 |
+
{"step": 4710, "total_steps": 28611, "tokens": 4938792960, "loss": 2.8450271487236023, "ce_loss": 2.8431044816970825, "z_loss": 19.226659774780273, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3103141784667969, "tokens_per_second": 2966077.623753188, "eta_seconds": 8449.547906398773, "data_wait_seconds": 1.4603137969970703e-05}
|
| 473 |
+
{"step": 4720, "total_steps": 28611, "tokens": 4949278720, "loss": 2.8369073271751404, "ce_loss": 2.834620773792267, "z_loss": 22.865559577941895, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.22647877037525177, "tokens_per_second": 2983373.067876989, "eta_seconds": 8397.048792099953, "data_wait_seconds": 1.8358230590820312e-05}
|
| 474 |
+
{"step": 4730, "total_steps": 28611, "tokens": 4959764480, "loss": 2.841127932071686, "ce_loss": 2.839178681373596, "z_loss": 19.49203109741211, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.321210116147995, "tokens_per_second": 4432382.851338464, "eta_seconds": 5649.5669024705885, "data_wait_seconds": 1.341104507446289e-05}
|
| 475 |
+
{"step": 4740, "total_steps": 28611, "tokens": 4970250240, "loss": 2.8311197757720947, "ce_loss": 2.8290963768959045, "z_loss": 20.234142303466797, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26759248971939087, "tokens_per_second": 2937845.1989076515, "eta_seconds": 8520.039689397812, "data_wait_seconds": 1.8417835235595703e-05}
|
| 476 |
+
{"step": 4750, "total_steps": 28611, "tokens": 4980736000, "loss": 2.829771935939789, "ce_loss": 2.827690601348877, "z_loss": 20.812942028045654, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29304930567741394, "tokens_per_second": 4224278.694851919, "eta_seconds": 5922.921697020531, "data_wait_seconds": 1.3470649719238281e-05}
|
| 477 |
+
{"step": 4760, "total_steps": 28611, "tokens": 4991221760, "loss": 2.83541339635849, "ce_loss": 2.833153247833252, "z_loss": 22.60180425643921, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.258876770734787, "tokens_per_second": 2748495.9743546415, "eta_seconds": 9099.371586990357, "data_wait_seconds": 1.4483928680419922e-05}
|
| 478 |
+
{"step": 4770, "total_steps": 28611, "tokens": 5001707520, "loss": 2.8389998078346252, "ce_loss": 2.836946129798889, "z_loss": 20.53701400756836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2619488537311554, "tokens_per_second": 2950414.6476837643, "eta_seconds": 8473.080363678933, "data_wait_seconds": 1.5497207641601562e-05}
|
| 479 |
+
{"step": 4780, "total_steps": 28611, "tokens": 5012193280, "loss": 2.839593291282654, "ce_loss": 2.837414503097534, "z_loss": 21.787513732910156, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29430532455444336, "tokens_per_second": 2344525.3173293187, "eta_seconds": 10658.283137869834, "data_wait_seconds": 0.2870953679084778}
|
| 480 |
+
{"step": 4790, "total_steps": 28611, "tokens": 5022679040, "loss": 2.834601044654846, "ce_loss": 2.8325594663619995, "z_loss": 20.41670560836792, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2885136008262634, "tokens_per_second": 3672083.651739195, "eta_seconds": 6802.167724084854, "data_wait_seconds": 1.4722347259521484e-05}
|
| 481 |
+
{"step": 4800, "total_steps": 28611, "tokens": 5033164800, "loss": 2.8233262300491333, "ce_loss": 2.821133315563202, "z_loss": 21.929470539093018, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2574891149997711, "tokens_per_second": 2639614.194938788, "eta_seconds": 9458.822877931596, "data_wait_seconds": 1.8596649169921875e-05}
|
| 482 |
+
{"step": 4810, "total_steps": 28611, "tokens": 5043650560, "loss": 2.862584412097931, "ce_loss": 2.8606690168380737, "z_loss": 19.15417718887329, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3010118007659912, "tokens_per_second": 4000530.9526247727, "eta_seconds": 6238.461262154579, "data_wait_seconds": 1.424551010131836e-05}
|
| 483 |
+
{"step": 4820, "total_steps": 28611, "tokens": 5054136320, "loss": 2.834984064102173, "ce_loss": 2.833019495010376, "z_loss": 19.645596981048584, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25613054633140564, "tokens_per_second": 2861315.5023068218, "eta_seconds": 8718.602193951607, "data_wait_seconds": 1.5854835510253906e-05}
|
| 484 |
+
{"step": 4830, "total_steps": 28611, "tokens": 5064622080, "loss": 2.8391632437705994, "ce_loss": 2.837156891822815, "z_loss": 20.063238620758057, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2692011892795563, "tokens_per_second": 4452629.966069051, "eta_seconds": 5600.327457261085, "data_wait_seconds": 1.329183578491211e-05}
|
| 485 |
+
{"step": 4840, "total_steps": 28611, "tokens": 5075107840, "loss": 2.8602797985076904, "ce_loss": 2.858471393585205, "z_loss": 18.08486557006836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2610670328140259, "tokens_per_second": 2968307.4847221184, "eta_seconds": 8397.2769749403, "data_wait_seconds": 1.4960765838623047e-05}
|
| 486 |
+
{"step": 4850, "total_steps": 28611, "tokens": 5085593600, "loss": 2.8051169514656067, "ce_loss": 2.8026236295700073, "z_loss": 24.93299674987793, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31349286437034607, "tokens_per_second": 2977746.1605246845, "eta_seconds": 8367.13843050003, "data_wait_seconds": 0.2765176296234131}
|
| 487 |
+
{"step": 4860, "total_steps": 28611, "tokens": 5096079360, "loss": 2.8559051156044006, "ce_loss": 2.85371333360672, "z_loss": 21.91750478744507, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2913394570350647, "tokens_per_second": 4124286.2857434363, "eta_seconds": 6038.55475845337, "data_wait_seconds": 1.7702579498291016e-05}
|
| 488 |
+
{"step": 4870, "total_steps": 28611, "tokens": 5106565120, "loss": 2.7955305576324463, "ce_loss": 2.7934420704841614, "z_loss": 20.88484239578247, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2578749358654022, "tokens_per_second": 4531445.4685293, "eta_seconds": 5493.664877772331, "data_wait_seconds": 1.1742115020751953e-05}
|
| 489 |
+
{"step": 4880, "total_steps": 28611, "tokens": 5117050880, "loss": 2.8706705570220947, "ce_loss": 2.8691070675849915, "z_loss": 15.63450002670288, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26181694865226746, "tokens_per_second": 2875115.978195895, "eta_seconds": 8654.870705986023, "data_wait_seconds": 1.4662742614746094e-05}
|
| 490 |
+
{"step": 4890, "total_steps": 28611, "tokens": 5127536640, "loss": 2.8328532576560974, "ce_loss": 2.8305504322052, "z_loss": 23.02844524383545, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2713852822780609, "tokens_per_second": 3748117.661274309, "eta_seconds": 6636.203434324265, "data_wait_seconds": 1.5556812286376953e-05}
|
| 491 |
+
{"step": 4900, "total_steps": 28611, "tokens": 5138022400, "loss": 2.813059151172638, "ce_loss": 2.811010479927063, "z_loss": 20.48648738861084, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2798348367214203, "tokens_per_second": 2944787.0395815903, "eta_seconds": 8442.982532119751, "data_wait_seconds": 1.627206802368164e-05}
|
| 492 |
+
{"step": 4910, "total_steps": 28611, "tokens": 5148508160, "loss": 2.8261823058128357, "ce_loss": 2.8243913650512695, "z_loss": 17.909254550933838, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2408258020877838, "tokens_per_second": 4438427.770805567, "eta_seconds": 5599.347575163841, "data_wait_seconds": 1.3887882232666016e-05}
|
| 493 |
+
{"step": 4920, "total_steps": 28611, "tokens": 5158993920, "loss": 2.842713475227356, "ce_loss": 2.8406059741973877, "z_loss": 21.07567548751831, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24620001018047333, "tokens_per_second": 2936594.4752171542, "eta_seconds": 8459.395475149155, "data_wait_seconds": 1.4901161193847656e-05}
|
| 494 |
+
{"step": 4930, "total_steps": 28611, "tokens": 5169479680, "loss": 2.828835368156433, "ce_loss": 2.826643228530884, "z_loss": 21.92126989364624, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25275108218193054, "tokens_per_second": 3077644.633845336, "eta_seconds": 8068.289620876312, "data_wait_seconds": 0.2524033188819885}
|
| 495 |
+
{"step": 4940, "total_steps": 28611, "tokens": 5179965440, "loss": 2.8159507513046265, "ce_loss": 2.81389844417572, "z_loss": 20.52348232269287, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.22394289076328278, "tokens_per_second": 4230951.837793294, "eta_seconds": 5866.491382455826, "data_wait_seconds": 1.3768672943115234e-05}
|
| 496 |
+
{"step": 4950, "total_steps": 28611, "tokens": 5190451200, "loss": 2.8276001811027527, "ce_loss": 2.825625419616699, "z_loss": 19.74818468093872, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25733962655067444, "tokens_per_second": 3116703.1490727873, "eta_seconds": 7960.4490865230555, "data_wait_seconds": 0.00012159347534179688}
|
| 497 |
+
{"step": 4960, "total_steps": 28611, "tokens": 5200936960, "loss": 2.846683084964752, "ce_loss": 2.8448368310928345, "z_loss": 18.462337970733643, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29607123136520386, "tokens_per_second": 4531076.189378438, "eta_seconds": 5473.284919404983, "data_wait_seconds": 1.7642974853515625e-05}
|
| 498 |
+
{"step": 4970, "total_steps": 28611, "tokens": 5211422720, "loss": 2.8546435236930847, "ce_loss": 2.8528131246566772, "z_loss": 18.303651809692383, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3055627942085266, "tokens_per_second": 2887138.5058238115, "eta_seconds": 8586.143396306037, "data_wait_seconds": 1.4722347259521484e-05}
|
| 499 |
+
{"step": 4980, "total_steps": 28611, "tokens": 5221908480, "loss": 2.877906322479248, "ce_loss": 2.875846743583679, "z_loss": 20.596380710601807, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29288190603256226, "tokens_per_second": 2899785.7762093223, "eta_seconds": 8545.079315614701, "data_wait_seconds": 0.2434038519859314}
|
| 500 |
+
{"step": 4990, "total_steps": 28611, "tokens": 5232394240, "loss": 2.863915205001831, "ce_loss": 2.8618366718292236, "z_loss": 20.784944534301758, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2746165096759796, "tokens_per_second": 3931515.5743795903, "eta_seconds": 6299.965808963776, "data_wait_seconds": 1.4185905456542969e-05}
|
| 501 |
+
{"step": 5000, "total_steps": 28611, "tokens": 5242880000, "loss": 2.855845272541046, "ce_loss": 2.8534059524536133, "z_loss": 24.39375877380371, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29067516326904297, "tokens_per_second": 3102540.6428906964, "eta_seconds": 7979.888351416588, "data_wait_seconds": 1.7821788787841797e-05}
|
| 502 |
+
{"step": 5010, "total_steps": 28611, "tokens": 5253365760, "loss": 2.8349189162254333, "ce_loss": 2.8332778215408325, "z_loss": 16.41084098815918, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27667152881622314, "tokens_per_second": 2898983.178959168, "eta_seconds": 8536.593918728828, "data_wait_seconds": 0.25095051527023315}
|
| 503 |
+
{"step": 5020, "total_steps": 28611, "tokens": 5263851520, "loss": 2.8173860907554626, "ce_loss": 2.815152645111084, "z_loss": 22.334418296813965, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2897082269191742, "tokens_per_second": 3209142.1429925496, "eta_seconds": 7708.27695183754, "data_wait_seconds": 1.4960765838623047e-05}
|
| 504 |
+
{"step": 5030, "total_steps": 28611, "tokens": 5274337280, "loss": 2.8600621223449707, "ce_loss": 2.857922673225403, "z_loss": 21.393859386444092, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29339301586151123, "tokens_per_second": 3063578.409192087, "eta_seconds": 8071.107493710518, "data_wait_seconds": 1.537799835205078e-05}
|
| 505 |
+
{"step": 5040, "total_steps": 28611, "tokens": 5284823040, "loss": 2.8258169293403625, "ce_loss": 2.824123799800873, "z_loss": 16.931479454040527, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28724756836891174, "tokens_per_second": 3060923.4322095797, "eta_seconds": 8074.6825078725815, "data_wait_seconds": 0.28238803148269653}
|
| 506 |
+
{"step": 5050, "total_steps": 28611, "tokens": 5295308800, "loss": 2.8107555508613586, "ce_loss": 2.80853134393692, "z_loss": 22.241833209991455, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28100138902664185, "tokens_per_second": 4225390.708662007, "eta_seconds": 5846.914720892907, "data_wait_seconds": 1.4841556549072266e-05}
|
| 507 |
+
{"step": 5060, "total_steps": 28611, "tokens": 5305794560, "loss": 2.8775808811187744, "ce_loss": 2.8757822513580322, "z_loss": 17.986388683319092, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24745385348796844, "tokens_per_second": 3120816.6995164985, "eta_seconds": 7912.997062540055, "data_wait_seconds": 1.7464160919189453e-05}
|
| 508 |
+
{"step": 5070, "total_steps": 28611, "tokens": 5316280320, "loss": 2.8293395042419434, "ce_loss": 2.827562928199768, "z_loss": 17.765302658081055, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27590614557266235, "tokens_per_second": 3992078.477645414, "eta_seconds": 6183.377344465255, "data_wait_seconds": 1.609325408935547e-05}
|
| 509 |
+
{"step": 5080, "total_steps": 28611, "tokens": 5326766080, "loss": 2.841807186603546, "ce_loss": 2.8399537801742554, "z_loss": 18.534119606018066, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23798789083957672, "tokens_per_second": 2889149.8599611423, "eta_seconds": 8540.242996025085, "data_wait_seconds": 1.5497207641601562e-05}
|
| 510 |
+
{"step": 5090, "total_steps": 28611, "tokens": 5337251840, "loss": 2.8217415809631348, "ce_loss": 2.8194955587387085, "z_loss": 22.45981740951538, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2795015275478363, "tokens_per_second": 3124145.1036426662, "eta_seconds": 7894.4976234436035, "data_wait_seconds": 0.2255597710609436}
|
| 511 |
+
{"step": 5100, "total_steps": 28611, "tokens": 5347737600, "loss": 2.8594255447387695, "ce_loss": 2.857728898525238, "z_loss": 16.9662823677063, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28486064076423645, "tokens_per_second": 3954712.9114741753, "eta_seconds": 6233.845765256881, "data_wait_seconds": 1.6689300537109375e-05}
|
| 512 |
+
{"step": 5110, "total_steps": 28611, "tokens": 5358223360, "loss": 2.880132794380188, "ce_loss": 2.8778003454208374, "z_loss": 23.324766635894775, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2926405072212219, "tokens_per_second": 2931747.0188414417, "eta_seconds": 8405.42666800022, "data_wait_seconds": 1.4722347259521484e-05}
|
| 513 |
+
{"step": 5120, "total_steps": 28611, "tokens": 5368709120, "loss": 2.822890877723694, "ce_loss": 2.821044147014618, "z_loss": 18.46736717224121, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2657391428947449, "tokens_per_second": 3114951.332838025, "eta_seconds": 7907.699409723282, "data_wait_seconds": 1.800060272216797e-05}
|
| 514 |
+
{"step": 5130, "total_steps": 28611, "tokens": 5379194880, "loss": 2.8296578526496887, "ce_loss": 2.8276028633117676, "z_loss": 20.549920082092285, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2682870328426361, "tokens_per_second": 4785494.5025107805, "eta_seconds": 5145.05095410347, "data_wait_seconds": 1.1563301086425781e-05}
|
| 515 |
+
{"step": 5140, "total_steps": 28611, "tokens": 5389680640, "loss": 2.8509339690208435, "ce_loss": 2.849060833454132, "z_loss": 18.73192596435547, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2761649489402771, "tokens_per_second": 3032438.9004870676, "eta_seconds": 8115.951583409309, "data_wait_seconds": 1.5020370483398438e-05}
|
| 516 |
+
{"step": 5150, "total_steps": 28611, "tokens": 5400166400, "loss": 2.82803612947464, "ce_loss": 2.826324164867401, "z_loss": 17.11991548538208, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2985824644565582, "tokens_per_second": 3144534.22819625, "eta_seconds": 7823.302197003364, "data_wait_seconds": 1.6570091247558594e-05}
|
| 517 |
+
{"step": 5160, "total_steps": 28611, "tokens": 5410652160, "loss": 2.887777328491211, "ce_loss": 2.8854976296424866, "z_loss": 22.79687786102295, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2693580090999603, "tokens_per_second": 3875261.0121972505, "eta_seconds": 6345.419237208366, "data_wait_seconds": 1.7762184143066406e-05}
|
| 518 |
+
{"step": 5170, "total_steps": 28611, "tokens": 5421137920, "loss": 2.873108446598053, "ce_loss": 2.871044635772705, "z_loss": 20.63817548751831, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30800676345825195, "tokens_per_second": 8519484.11583199, "eta_seconds": 2885.112488245964, "data_wait_seconds": 1.1801719665527344e-05}
|
| 519 |
+
{"step": 5180, "total_steps": 28611, "tokens": 5431623680, "loss": 2.834558427333832, "ce_loss": 2.83301043510437, "z_loss": 15.479610443115234, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2944486439228058, "tokens_per_second": 4173401.8863842734, "eta_seconds": 5887.088021922112, "data_wait_seconds": 1.436471939086914e-05}
|
| 520 |
+
{"step": 5190, "total_steps": 28611, "tokens": 5442109440, "loss": 2.825849711894989, "ce_loss": 2.8240734338760376, "z_loss": 17.763025283813477, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26714181900024414, "tokens_per_second": 2910757.83082137, "eta_seconds": 8437.218045401572, "data_wait_seconds": 1.4722347259521484e-05}
|
| 521 |
+
{"step": 5200, "total_steps": 28611, "tokens": 5452595200, "loss": 2.7843201756477356, "ce_loss": 2.7822386622428894, "z_loss": 20.8157901763916, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31038567423820496, "tokens_per_second": 4293586.555714066, "eta_seconds": 5717.4141984701155, "data_wait_seconds": 1.6868114471435547e-05}
|
| 522 |
+
{"step": 5210, "total_steps": 28611, "tokens": 5463080960, "loss": 2.8645113110542297, "ce_loss": 2.862677752971649, "z_loss": 18.335039615631104, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2725237309932709, "tokens_per_second": 2819357.6350057693, "eta_seconds": 8703.30413968563, "data_wait_seconds": 1.9252300262451172e-05}
|
| 523 |
+
{"step": 5220, "total_steps": 28611, "tokens": 5473566720, "loss": 2.8412880301475525, "ce_loss": 2.8389891386032104, "z_loss": 22.989408016204834, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.22703604400157928, "tokens_per_second": 4136504.4359299107, "eta_seconds": 5929.460875940323, "data_wait_seconds": 1.710653305053711e-05}
|
| 524 |
+
{"step": 5230, "total_steps": 28611, "tokens": 5484052480, "loss": 2.820448398590088, "ce_loss": 2.8184439539909363, "z_loss": 20.04449224472046, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28134676814079285, "tokens_per_second": 2858349.985918973, "eta_seconds": 8577.240567731858, "data_wait_seconds": 0.2813739776611328}
|
| 525 |
+
{"step": 5240, "total_steps": 28611, "tokens": 5494538240, "loss": 2.860379934310913, "ce_loss": 2.857899785041809, "z_loss": 24.801137924194336, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24525894224643707, "tokens_per_second": 3964088.970506877, "eta_seconds": 6182.068535375595, "data_wait_seconds": 1.5139579772949219e-05}
|
| 526 |
+
{"step": 5250, "total_steps": 28611, "tokens": 5505024000, "loss": 2.8146660923957825, "ce_loss": 2.812687635421753, "z_loss": 19.78486204147339, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28604066371917725, "tokens_per_second": 2702027.409071258, "eta_seconds": 9065.705201125144, "data_wait_seconds": 1.811981201171875e-05}
|
| 527 |
+
{"step": 5260, "total_steps": 28611, "tokens": 5515509760, "loss": 2.895419716835022, "ce_loss": 2.8935729265213013, "z_loss": 18.46878480911255, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30149635672569275, "tokens_per_second": 4178305.259216543, "eta_seconds": 5860.102758646011, "data_wait_seconds": 1.1980533599853516e-05}
|
| 528 |
+
{"step": 5270, "total_steps": 28611, "tokens": 5525995520, "loss": 2.8544018864631653, "ce_loss": 2.852412223815918, "z_loss": 19.89629602432251, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26023218035697937, "tokens_per_second": 2953010.572581889, "eta_seconds": 8288.088313412665, "data_wait_seconds": 1.9371509552001953e-05}
|
| 529 |
+
{"step": 5280, "total_steps": 28611, "tokens": 5536481280, "loss": 2.834411084651947, "ce_loss": 2.8326609134674072, "z_loss": 17.501946449279785, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27857035398483276, "tokens_per_second": 4239290.180974714, "eta_seconds": 5770.854461860657, "data_wait_seconds": 1.5079975128173828e-05}
|
| 530 |
+
{"step": 5290, "total_steps": 28611, "tokens": 5546967040, "loss": 2.858088791370392, "ce_loss": 2.85641610622406, "z_loss": 16.726853847503662, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24554449319839478, "tokens_per_second": 2976388.320976061, "eta_seconds": 8215.94437918663, "data_wait_seconds": 1.52587890625e-05}
|
| 531 |
+
{"step": 5300, "total_steps": 28611, "tokens": 5557452800, "loss": 2.8485774993896484, "ce_loss": 2.8469274640083313, "z_loss": 16.50043272972107, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2677532136440277, "tokens_per_second": 3205570.688758194, "eta_seconds": 7625.274096035958, "data_wait_seconds": 2.3245811462402344e-05}
|
| 532 |
+
{"step": 5310, "total_steps": 28611, "tokens": 5567938560, "loss": 2.836161255836487, "ce_loss": 2.834459066390991, "z_loss": 17.02223491668701, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.21873487532138824, "tokens_per_second": 3429294.482055303, "eta_seconds": 7124.751024985313, "data_wait_seconds": 1.5676021575927734e-05}
|
| 533 |
+
{"step": 5320, "total_steps": 28611, "tokens": 5578424320, "loss": 2.8455207347869873, "ce_loss": 2.843326985836029, "z_loss": 21.937496185302734, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27483776211738586, "tokens_per_second": 2264117.190817295, "eta_seconds": 10786.713565468788, "data_wait_seconds": 1.6570091247558594e-05}
|
| 534 |
+
{"step": 5330, "total_steps": 28611, "tokens": 5588910080, "loss": 2.8103166222572327, "ce_loss": 2.808302164077759, "z_loss": 20.144776821136475, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2724626958370209, "tokens_per_second": 3791993.108529782, "eta_seconds": 6437.748476147652, "data_wait_seconds": 1.704692840576172e-05}
|
| 535 |
+
{"step": 5340, "total_steps": 28611, "tokens": 5599395840, "loss": 2.845133125782013, "ce_loss": 2.8431294560432434, "z_loss": 20.036278247833252, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26320165395736694, "tokens_per_second": 2887437.4238290507, "eta_seconds": 8450.888630390167, "data_wait_seconds": 1.531839370727539e-05}
|
| 536 |
+
{"step": 5350, "total_steps": 28611, "tokens": 5609881600, "loss": 2.835105001926422, "ce_loss": 2.832891583442688, "z_loss": 22.134313106536865, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26864051818847656, "tokens_per_second": 3098086.8079984174, "eta_seconds": 7872.899582099915, "data_wait_seconds": 0.266806423664093}
|
| 537 |
+
{"step": 5360, "total_steps": 28611, "tokens": 5620367360, "loss": 2.836216986179352, "ce_loss": 2.834181308746338, "z_loss": 20.356796741485596, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24792633950710297, "tokens_per_second": 4154928.7496810383, "eta_seconds": 5867.836019539834, "data_wait_seconds": 1.4781951904296875e-05}
|
| 538 |
+
{"step": 5370, "total_steps": 28611, "tokens": 5630853120, "loss": 2.8516117930412292, "ce_loss": 2.8493948578834534, "z_loss": 22.168702602386475, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26561352610588074, "tokens_per_second": 3013814.2733666473, "eta_seconds": 8086.083814573288, "data_wait_seconds": 1.519918441772461e-05}
|
| 539 |
+
{"step": 5380, "total_steps": 28611, "tokens": 5641338880, "loss": 2.873166084289551, "ce_loss": 2.871384859085083, "z_loss": 17.812222003936768, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2953318953514099, "tokens_per_second": 2721645.286550078, "eta_seconds": 8950.273269033432, "data_wait_seconds": 1.728534698486328e-05}
|
| 540 |
+
{"step": 5390, "total_steps": 28611, "tokens": 5651824640, "loss": 2.8411785364151, "ce_loss": 2.8389676809310913, "z_loss": 22.109129905700684, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31024160981178284, "tokens_per_second": 4536442.951742887, "eta_seconds": 5367.4175019979475, "data_wait_seconds": 1.4960765838623047e-05}
|
| 541 |
+
{"step": 5400, "total_steps": 28611, "tokens": 5662310400, "loss": 2.862811803817749, "ce_loss": 2.8611578941345215, "z_loss": 16.539058208465576, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24690109491348267, "tokens_per_second": 2307288.1367948237, "eta_seconds": 10548.529742717743, "data_wait_seconds": 0.2503778338432312}
|
| 542 |
+
{"step": 5410, "total_steps": 28611, "tokens": 5672796160, "loss": 2.8532257676124573, "ce_loss": 2.8511399626731873, "z_loss": 20.85810422897339, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.251174658536911, "tokens_per_second": 2548932.117754782, "eta_seconds": 9544.393750834464, "data_wait_seconds": 1.6868114471435547e-05}
|
| 543 |
+
{"step": 5420, "total_steps": 28611, "tokens": 5683281920, "loss": 2.8625964522361755, "ce_loss": 2.8604761958122253, "z_loss": 21.201916694641113, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33656707406044006, "tokens_per_second": 3895902.127526286, "eta_seconds": 6241.821590995788, "data_wait_seconds": 1.4185905456542969e-05}
|
| 544 |
+
{"step": 5430, "total_steps": 28611, "tokens": 5693767680, "loss": 2.849523901939392, "ce_loss": 2.847778081893921, "z_loss": 17.458433628082275, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2557050883769989, "tokens_per_second": 2863578.4997038785, "eta_seconds": 8488.344307136536, "data_wait_seconds": 0.2509610056877136}
|
| 545 |
+
{"step": 5440, "total_steps": 28611, "tokens": 5704253440, "loss": 2.811217248439789, "ce_loss": 2.8094311952590942, "z_loss": 17.860483169555664, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2956523001194, "tokens_per_second": 3485332.6825841716, "eta_seconds": 6971.086179924011, "data_wait_seconds": 1.2755393981933594e-05}
|
| 546 |
+
{"step": 5450, "total_steps": 28611, "tokens": 5714739200, "loss": 2.863163471221924, "ce_loss": 2.861423969268799, "z_loss": 17.39546036720276, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2693449556827545, "tokens_per_second": 2927436.103694308, "eta_seconds": 8296.020092582703, "data_wait_seconds": 1.6391277313232422e-05}
|
| 547 |
+
{"step": 5460, "total_steps": 28611, "tokens": 5725224960, "loss": 2.8235044479370117, "ce_loss": 2.8216691613197327, "z_loss": 18.352829933166504, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2726002335548401, "tokens_per_second": 2358361.593658595, "eta_seconds": 10293.41006963253, "data_wait_seconds": 0.2851561903953552}
|
| 548 |
+
{"step": 5470, "total_steps": 28611, "tokens": 5735710720, "loss": 2.8072230219841003, "ce_loss": 2.805505931377411, "z_loss": 17.17177152633667, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28299620747566223, "tokens_per_second": 4041479.319344155, "eta_seconds": 6004.0137035608295, "data_wait_seconds": 1.4007091522216797e-05}
|
| 549 |
+
{"step": 5480, "total_steps": 28611, "tokens": 5746196480, "loss": 2.866787612438202, "ce_loss": 2.8650404810905457, "z_loss": 17.471713066101074, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2598026990890503, "tokens_per_second": 2785167.6327072745, "eta_seconds": 8708.492505502702, "data_wait_seconds": 1.5079975128173828e-05}
|
| 550 |
+
{"step": 5490, "total_steps": 28611, "tokens": 5756682240, "loss": 2.8789955377578735, "ce_loss": 2.877134084701538, "z_loss": 18.613967418670654, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2597297132015228, "tokens_per_second": 3854281.4068065993, "eta_seconds": 6290.180486869812, "data_wait_seconds": 1.3113021850585938e-05}
|
| 551 |
+
{"step": 5500, "total_steps": 28611, "tokens": 5767168000, "loss": 2.9045660495758057, "ce_loss": 2.902557611465454, "z_loss": 20.084296226501465, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27388226985931396, "tokens_per_second": 3107541.8643598463, "eta_seconds": 7798.330961823463, "data_wait_seconds": 0.2812444567680359}
|
| 552 |
+
{"step": 5510, "total_steps": 28611, "tokens": 5777653760, "loss": 2.8149659633636475, "ce_loss": 2.8128172755241394, "z_loss": 21.48620367050171, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30149173736572266, "tokens_per_second": 3986541.721694652, "eta_seconds": 6076.232450842857, "data_wait_seconds": 1.4126300811767578e-05}
|
| 553 |
+
{"step": 5520, "total_steps": 28611, "tokens": 5788139520, "loss": 2.818528890609741, "ce_loss": 2.8167242407798767, "z_loss": 18.046669483184814, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26664644479751587, "tokens_per_second": 2870954.3250906873, "eta_seconds": 8433.66549038887, "data_wait_seconds": 1.4483928680419922e-05}
|
| 554 |
+
{"step": 5530, "total_steps": 28611, "tokens": 5798625280, "loss": 2.7990846037864685, "ce_loss": 2.7973568439483643, "z_loss": 17.277742385864258, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2283342331647873, "tokens_per_second": 3903054.503746245, "eta_seconds": 6200.831331658363, "data_wait_seconds": 1.6868114471435547e-05}
|
| 555 |
+
{"step": 5540, "total_steps": 28611, "tokens": 5809111040, "loss": 2.8401681184768677, "ce_loss": 2.838568687438965, "z_loss": 15.993680477142334, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2573334574699402, "tokens_per_second": 2971701.438586939, "eta_seconds": 8140.688893532753, "data_wait_seconds": 2.3066997528076172e-05}
|
| 556 |
+
{"step": 5550, "total_steps": 28611, "tokens": 5819596800, "loss": 2.798658788204193, "ce_loss": 2.7965216636657715, "z_loss": 21.37174415588379, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31356024742126465, "tokens_per_second": 4513058.188593761, "eta_seconds": 5358.054367017746, "data_wait_seconds": 1.9788742065429688e-05}
|
| 557 |
+
{"step": 5560, "total_steps": 28611, "tokens": 5830082560, "loss": 2.797594428062439, "ce_loss": 2.7956092953681946, "z_loss": 19.850999355316162, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2616618871688843, "tokens_per_second": 2891526.694238224, "eta_seconds": 8359.156920170784, "data_wait_seconds": 1.5497207641601562e-05}
|
| 558 |
+
{"step": 5570, "total_steps": 28611, "tokens": 5840568320, "loss": 2.8503554463386536, "ce_loss": 2.8482561707496643, "z_loss": 20.992470741271973, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3111128807067871, "tokens_per_second": 2859325.0433097347, "eta_seconds": 8449.63033235073, "data_wait_seconds": 2.396106719970703e-05}
|
| 559 |
+
{"step": 5580, "total_steps": 28611, "tokens": 5851054080, "loss": 2.846054196357727, "ce_loss": 2.8441205620765686, "z_loss": 19.33634376525879, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2914489805698395, "tokens_per_second": 4021309.7088951836, "eta_seconds": 6005.44489338398, "data_wait_seconds": 1.5437602996826172e-05}
|
| 560 |
+
{"step": 5590, "total_steps": 28611, "tokens": 5861539840, "loss": 2.8159618973731995, "ce_loss": 2.8141000866889954, "z_loss": 18.618014812469482, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2459363490343094, "tokens_per_second": 4724577.157076457, "eta_seconds": 5109.297042560577, "data_wait_seconds": 1.6987323760986328e-05}
|
| 561 |
+
{"step": 5600, "total_steps": 28611, "tokens": 5872025600, "loss": 2.7805323004722595, "ce_loss": 2.7782976031303406, "z_loss": 22.3466477394104, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2726951241493225, "tokens_per_second": 4143318.207998969, "eta_seconds": 5823.540728640556, "data_wait_seconds": 1.4126300811767578e-05}
|
| 562 |
+
{"step": 5610, "total_steps": 28611, "tokens": 5882511360, "loss": 2.7670704126358032, "ce_loss": 2.765090525150299, "z_loss": 19.7980375289917, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29404303431510925, "tokens_per_second": 3035637.937331374, "eta_seconds": 7945.050455260277, "data_wait_seconds": 1.4603137969970703e-05}
|
| 563 |
+
{"step": 5620, "total_steps": 28611, "tokens": 5892997120, "loss": 2.7991095781326294, "ce_loss": 2.7972933650016785, "z_loss": 18.162179946899414, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2735256552696228, "tokens_per_second": 3111389.7670628, "eta_seconds": 7748.245196151733, "data_wait_seconds": 0.1967756152153015}
|
| 564 |
+
{"step": 5630, "total_steps": 28611, "tokens": 5903482880, "loss": 2.8336843252182007, "ce_loss": 2.8318965435028076, "z_loss": 17.877618312835693, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24542900919914246, "tokens_per_second": 4563719.571741266, "eta_seconds": 5280.1940779209135, "data_wait_seconds": 1.2755393981933594e-05}
|
| 565 |
+
{"step": 5640, "total_steps": 28611, "tokens": 5913968640, "loss": 2.8391897082328796, "ce_loss": 2.8371741771698, "z_loss": 20.15577459335327, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30171477794647217, "tokens_per_second": 3045387.855334943, "eta_seconds": 7909.284610104561, "data_wait_seconds": 0.25138795375823975}
|
| 566 |
+
{"step": 5650, "total_steps": 28611, "tokens": 5924454400, "loss": 2.8355531096458435, "ce_loss": 2.8338438272476196, "z_loss": 17.093022346496582, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2579728960990906, "tokens_per_second": 4453169.175104192, "eta_seconds": 5406.56610815525, "data_wait_seconds": 1.627206802368164e-05}
|
| 567 |
+
{"step": 5660, "total_steps": 28611, "tokens": 5934940160, "loss": 2.814241588115692, "ce_loss": 2.8124532103538513, "z_loss": 17.883944034576416, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2708532512187958, "tokens_per_second": 2782314.4797591926, "eta_seconds": 8649.585785889625, "data_wait_seconds": 1.531839370727539e-05}
|
| 568 |
+
{"step": 5670, "total_steps": 28611, "tokens": 5945425920, "loss": 2.808601975440979, "ce_loss": 2.8065733313560486, "z_loss": 20.28624153137207, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3203968107700348, "tokens_per_second": 3301113.7959532435, "eta_seconds": 7287.050220894814, "data_wait_seconds": 0.23148125410079956}
|
| 569 |
+
{"step": 5680, "total_steps": 28611, "tokens": 5955911680, "loss": 2.80528062582016, "ce_loss": 2.8036506175994873, "z_loss": 16.299731969833374, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27649813890457153, "tokens_per_second": 4066493.502975268, "eta_seconds": 5912.931187129021, "data_wait_seconds": 1.4185905456542969e-05}
|
| 570 |
+
{"step": 5690, "total_steps": 28611, "tokens": 5966397440, "loss": 2.8319506645202637, "ce_loss": 2.829925537109375, "z_loss": 20.251323223114014, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3184238374233246, "tokens_per_second": 2970719.479374421, "eta_seconds": 8090.434207224846, "data_wait_seconds": 1.633167266845703e-05}
|
| 571 |
+
{"step": 5700, "total_steps": 28611, "tokens": 5976883200, "loss": 2.797289729118347, "ce_loss": 2.7953194975852966, "z_loss": 19.702202796936035, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28573471307754517, "tokens_per_second": 2943460.2673902586, "eta_seconds": 8161.796849155426, "data_wait_seconds": 1.6868114471435547e-05}
|
| 572 |
+
{"step": 5710, "total_steps": 28611, "tokens": 5987368960, "loss": 2.801128387451172, "ce_loss": 2.7995027899742126, "z_loss": 16.256030559539795, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31723037362098694, "tokens_per_second": 4233681.4494555, "eta_seconds": 5671.999479103088, "data_wait_seconds": 1.4662742614746094e-05}
|
| 573 |
+
{"step": 5720, "total_steps": 28611, "tokens": 5997854720, "loss": 2.792540192604065, "ce_loss": 2.7903518676757812, "z_loss": 21.88259220123291, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24733977019786835, "tokens_per_second": 2899584.655111964, "eta_seconds": 8278.06602358818, "data_wait_seconds": 1.710653305053711e-05}
|