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
|
@@ -49,10 +49,10 @@
|
|
| 49 |
"model_type": "bird_alpha",
|
| 50 |
"output_attentions": false
|
| 51 |
},
|
| 52 |
-
"training_percent":
|
| 53 |
-
"step":
|
| 54 |
"total_steps": 28611,
|
| 55 |
-
"tokens_seen":
|
| 56 |
"target_tokens": 30000000000,
|
| 57 |
"trained_token_target": 30000807936,
|
| 58 |
"tokens_per_step": 1048576,
|
|
@@ -68,5 +68,5 @@
|
|
| 68 |
"dataset_id": "HuggingFaceFW/fineweb-edu",
|
| 69 |
"dataset_config": "sample-100BT",
|
| 70 |
"dataset_revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9",
|
| 71 |
-
"elapsed_seconds":
|
| 72 |
}
|
|
|
|
| 49 |
"model_type": "bird_alpha",
|
| 50 |
"output_attentions": false
|
| 51 |
},
|
| 52 |
+
"training_percent": 20,
|
| 53 |
+
"step": 5723,
|
| 54 |
"total_steps": 28611,
|
| 55 |
+
"tokens_seen": 6001000448,
|
| 56 |
"target_tokens": 30000000000,
|
| 57 |
"trained_token_target": 30000807936,
|
| 58 |
"tokens_per_step": 1048576,
|
|
|
|
| 68 |
"dataset_id": "HuggingFaceFW/fineweb-edu",
|
| 69 |
"dataset_config": "sample-100BT",
|
| 70 |
"dataset_revision": "87f09149ef4734204d70ed1d046ddc9ca3f2b8f9",
|
| 71 |
+
"elapsed_seconds": 1795.5749864578247
|
| 72 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 13860292
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e63d34c2ca0bfe6feb963cbcd50446e9db7239635cf5e9e97608c4f69c4233ab
|
| 3 |
size 13860292
|
training_metrics.jsonl
CHANGED
|
@@ -428,3 +428,146 @@
|
|
| 428 |
{"step": 4270, "total_steps": 28611, "tokens": 4477419520, "loss": 2.8449864983558655, "ce_loss": 2.8426221013069153, "z_loss": 23.643829345703125, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2728963792324066, "tokens_per_second": 3990832.353878371, "eta_seconds": 6395.505035734177, "data_wait_seconds": 1.5616416931152344e-05}
|
| 429 |
{"step": 4280, "total_steps": 28611, "tokens": 4487905280, "loss": 2.8036940693855286, "ce_loss": 2.8014734983444214, "z_loss": 22.2059006690979, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27203822135925293, "tokens_per_second": 4173912.026579889, "eta_seconds": 6112.467750525475, "data_wait_seconds": 1.3053417205810547e-05}
|
| 430 |
{"step": 4290, "total_steps": 28611, "tokens": 4498391040, "loss": 2.818882703781128, "ce_loss": 2.8169109225273132, "z_loss": 19.718111515045166, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2529017925262451, "tokens_per_second": 2806021.200423336, "eta_seconds": 9088.461944675444, "data_wait_seconds": 1.4543533325195312e-05}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 428 |
{"step": 4270, "total_steps": 28611, "tokens": 4477419520, "loss": 2.8449864983558655, "ce_loss": 2.8426221013069153, "z_loss": 23.643829345703125, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2728963792324066, "tokens_per_second": 3990832.353878371, "eta_seconds": 6395.505035734177, "data_wait_seconds": 1.5616416931152344e-05}
|
| 429 |
{"step": 4280, "total_steps": 28611, "tokens": 4487905280, "loss": 2.8036940693855286, "ce_loss": 2.8014734983444214, "z_loss": 22.2059006690979, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27203822135925293, "tokens_per_second": 4173912.026579889, "eta_seconds": 6112.467750525475, "data_wait_seconds": 1.3053417205810547e-05}
|
| 430 |
{"step": 4290, "total_steps": 28611, "tokens": 4498391040, "loss": 2.818882703781128, "ce_loss": 2.8169109225273132, "z_loss": 19.718111515045166, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2529017925262451, "tokens_per_second": 2806021.200423336, "eta_seconds": 9088.461944675444, "data_wait_seconds": 1.4543533325195312e-05}
|
| 431 |
+
{"step": 4300, "total_steps": 28611, "tokens": 4508876800, "loss": 2.825824737548828, "ce_loss": 2.8233195543289185, "z_loss": 25.052409172058105, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25432994961738586, "tokens_per_second": 2428471.6298812046, "eta_seconds": 10497.108890354633, "data_wait_seconds": 0.281904935836792}
|
| 432 |
+
{"step": 4310, "total_steps": 28611, "tokens": 4519362560, "loss": 2.8534015417099, "ce_loss": 2.8514211177825928, "z_loss": 19.804739952087402, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2698717415332794, "tokens_per_second": 4570003.40003826, "eta_seconds": 5575.804467844962, "data_wait_seconds": 0.3011036515235901}
|
| 433 |
+
{"step": 4320, "total_steps": 28611, "tokens": 4529848320, "loss": 2.840970456600189, "ce_loss": 2.8387568593025208, "z_loss": 22.13575029373169, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.257672518491745, "tokens_per_second": 4640314.059954376, "eta_seconds": 5489.059422898293, "data_wait_seconds": 1.5079975128173828e-05}
|
| 434 |
+
{"step": 4330, "total_steps": 28611, "tokens": 4540334080, "loss": 2.820714294910431, "ce_loss": 2.8185348510742188, "z_loss": 21.79487657546997, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2566245198249817, "tokens_per_second": 4328274.722576073, "eta_seconds": 5882.3608684539795, "data_wait_seconds": 1.52587890625e-05}
|
| 435 |
+
{"step": 4340, "total_steps": 28611, "tokens": 4550819840, "loss": 2.8374650478363037, "ce_loss": 2.834964871406555, "z_loss": 25.001723766326904, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28247302770614624, "tokens_per_second": 4087553.495085229, "eta_seconds": 6226.215296411514, "data_wait_seconds": 1.6748905181884766e-05}
|
| 436 |
+
{"step": 4350, "total_steps": 28611, "tokens": 4561305600, "loss": 2.818229913711548, "ce_loss": 2.816084384918213, "z_loss": 21.454843521118164, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2873164117336273, "tokens_per_second": 4643969.788861052, "eta_seconds": 5477.964649343491, "data_wait_seconds": 0.562673807144165}
|
| 437 |
+
{"step": 4360, "total_steps": 28611, "tokens": 4571791360, "loss": 2.8601598143577576, "ce_loss": 2.857895255088806, "z_loss": 22.64509868621826, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2840128242969513, "tokens_per_second": 7881454.908902778, "eta_seconds": 3226.4368533372876, "data_wait_seconds": 1.3887882232666016e-05}
|
| 438 |
+
{"step": 4370, "total_steps": 28611, "tokens": 4582277120, "loss": 2.8316493034362793, "ce_loss": 2.828679919242859, "z_loss": 29.694324493408203, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2830013334751129, "tokens_per_second": 4260498.861654792, "eta_seconds": 5966.092619991303, "data_wait_seconds": 1.4722347259521484e-05}
|
| 439 |
+
{"step": 4380, "total_steps": 28611, "tokens": 4592762880, "loss": 2.876618802547455, "ce_loss": 2.87462717294693, "z_loss": 19.916411876678467, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27895647287368774, "tokens_per_second": 4422941.03471791, "eta_seconds": 5744.604066967964, "data_wait_seconds": 1.615285873413086e-05}
|
| 440 |
+
{"step": 4390, "total_steps": 28611, "tokens": 4603248640, "loss": 2.8350217938423157, "ce_loss": 2.832671821117401, "z_loss": 23.50015687942505, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2544385492801666, "tokens_per_second": 4411390.9687845735, "eta_seconds": 5757.267826795578, "data_wait_seconds": 1.6868114471435547e-05}
|
| 441 |
+
{"step": 4400, "total_steps": 28611, "tokens": 4613734400, "loss": 2.8577412962913513, "ce_loss": 2.8551907539367676, "z_loss": 25.50511121749878, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2791428864002228, "tokens_per_second": 9594147.6560445, "eta_seconds": 2646.099939894676, "data_wait_seconds": 1.7523765563964844e-05}
|
| 442 |
+
{"step": 4410, "total_steps": 28611, "tokens": 4624220160, "loss": 2.854028046131134, "ce_loss": 2.8519012331962585, "z_loss": 21.26815891265869, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24564264714717865, "tokens_per_second": 4202000.497111084, "eta_seconds": 6039.168199396133, "data_wait_seconds": 1.3589859008789062e-05}
|
| 443 |
+
{"step": 4420, "total_steps": 28611, "tokens": 4634705920, "loss": 2.8613314628601074, "ce_loss": 2.8590718507766724, "z_loss": 22.595773220062256, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2710101008415222, "tokens_per_second": 2859309.61412471, "eta_seconds": 8871.407940816878, "data_wait_seconds": 1.4722347259521484e-05}
|
| 444 |
+
{"step": 4430, "total_steps": 28611, "tokens": 4645191680, "loss": 2.8258755207061768, "ce_loss": 2.823387920856476, "z_loss": 24.87636375427246, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27060309052467346, "tokens_per_second": 2672096.577895834, "eta_seconds": 9489.034365653992, "data_wait_seconds": 1.728534698486328e-05}
|
| 445 |
+
{"step": 4440, "total_steps": 28611, "tokens": 4655677440, "loss": 2.822395086288452, "ce_loss": 2.8205990195274353, "z_loss": 17.960797786712646, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2622791528701782, "tokens_per_second": 4196971.295142253, "eta_seconds": 6038.9096597671505, "data_wait_seconds": 1.8656253814697266e-05}
|
| 446 |
+
{"step": 4450, "total_steps": 28611, "tokens": 4666163200, "loss": 2.8395535349845886, "ce_loss": 2.8373952507972717, "z_loss": 21.582642078399658, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3091645836830139, "tokens_per_second": 4275563.585944724, "eta_seconds": 5925.451516914368, "data_wait_seconds": 2.0444393157958984e-05}
|
| 447 |
+
{"step": 4460, "total_steps": 28611, "tokens": 4676648960, "loss": 2.8979042768478394, "ce_loss": 2.8959309458732605, "z_loss": 19.732669830322266, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27327680587768555, "tokens_per_second": 2911370.755970001, "eta_seconds": 8698.362764024734, "data_wait_seconds": 1.3768672943115234e-05}
|
| 448 |
+
{"step": 4470, "total_steps": 28611, "tokens": 4687134720, "loss": 2.8235743045806885, "ce_loss": 2.821343243122101, "z_loss": 22.31036138534546, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.33857065439224243, "tokens_per_second": 1300981.6068952598, "eta_seconds": 19457.364409947393, "data_wait_seconds": 0.5022664070129395}
|
| 449 |
+
{"step": 4480, "total_steps": 28611, "tokens": 4697620480, "loss": 2.8320061564445496, "ce_loss": 2.8301092386245728, "z_loss": 18.969400882720947, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26022258400917053, "tokens_per_second": 4595294.471467839, "eta_seconds": 5506.325571322441, "data_wait_seconds": 1.6570091247558594e-05}
|
| 450 |
+
{"step": 4490, "total_steps": 28611, "tokens": 4708106240, "loss": 2.862829566001892, "ce_loss": 2.8604259490966797, "z_loss": 24.03571844100952, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2889399826526642, "tokens_per_second": 1686231.8140514689, "eta_seconds": 14999.540090060233, "data_wait_seconds": 2.4259090423583984e-05}
|
| 451 |
+
{"step": 4500, "total_steps": 28611, "tokens": 4718592000, "loss": 2.867006778717041, "ce_loss": 2.864531099796295, "z_loss": 24.757240295410156, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3088686466217041, "tokens_per_second": 3705136.0503515755, "eta_seconds": 6823.559403061867, "data_wait_seconds": 1.5437602996826172e-05}
|
| 452 |
+
{"step": 4510, "total_steps": 28611, "tokens": 4729077760, "loss": 2.8404266834259033, "ce_loss": 2.838349461555481, "z_loss": 20.77195167541504, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2805332839488983, "tokens_per_second": 2902117.527722914, "eta_seconds": 8708.031268405914, "data_wait_seconds": 1.6510486602783203e-05}
|
| 453 |
+
{"step": 4520, "total_steps": 28611, "tokens": 4739563520, "loss": 2.8861131072044373, "ce_loss": 2.8840392231941223, "z_loss": 20.7387433052063, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2791841924190521, "tokens_per_second": 4083641.2538707363, "eta_seconds": 6185.960726118088, "data_wait_seconds": 1.4841556549072266e-05}
|
| 454 |
+
{"step": 4530, "total_steps": 28611, "tokens": 4750049280, "loss": 2.8823322653770447, "ce_loss": 2.88044136762619, "z_loss": 18.90910005569458, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29508665204048157, "tokens_per_second": 3028115.327357631, "eta_seconds": 8338.770464873314, "data_wait_seconds": 1.3709068298339844e-05}
|
| 455 |
+
{"step": 4540, "total_steps": 28611, "tokens": 4760535040, "loss": 2.842520773410797, "ce_loss": 2.8399989008903503, "z_loss": 25.218759536743164, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27656638622283936, "tokens_per_second": 2834534.1807525563, "eta_seconds": 8904.557605051994, "data_wait_seconds": 0.32135921716690063}
|
| 456 |
+
{"step": 4550, "total_steps": 28611, "tokens": 4771020800, "loss": 2.916194438934326, "ce_loss": 2.913942873477936, "z_loss": 22.515448093414307, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2785520553588867, "tokens_per_second": 4142750.349373903, "eta_seconds": 6090.105608177185, "data_wait_seconds": 1.519918441772461e-05}
|
| 457 |
+
{"step": 4560, "total_steps": 28611, "tokens": 4781506560, "loss": 2.844276547431946, "ce_loss": 2.8420385122299194, "z_loss": 22.37990379333496, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28824615478515625, "tokens_per_second": 4507136.337591805, "eta_seconds": 5595.4156890392305, "data_wait_seconds": 1.901388168334961e-05}
|
| 458 |
+
{"step": 4570, "total_steps": 28611, "tokens": 4791992320, "loss": 2.8485448360443115, "ce_loss": 2.846391439437866, "z_loss": 21.533743381500244, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2944942116737366, "tokens_per_second": 2840285.0659635994, "eta_seconds": 8875.4526501894, "data_wait_seconds": 1.436471939086914e-05}
|
| 459 |
+
{"step": 4580, "total_steps": 28611, "tokens": 4802478080, "loss": 2.8518555760383606, "ce_loss": 2.8492844104766846, "z_loss": 25.71137571334839, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23131848871707916, "tokens_per_second": 2577857.4533194695, "eta_seconds": 9774.912039279938, "data_wait_seconds": 2.1636486053466797e-05}
|
| 460 |
+
{"step": 4590, "total_steps": 28611, "tokens": 4812963840, "loss": 2.91481751203537, "ce_loss": 2.9129000902175903, "z_loss": 19.17478370666504, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2804790437221527, "tokens_per_second": 4548569.5955890715, "eta_seconds": 5537.530770206452, "data_wait_seconds": 1.5676021575927734e-05}
|
| 461 |
+
{"step": 4600, "total_steps": 28611, "tokens": 4823449600, "loss": 2.8867167830467224, "ce_loss": 2.8848018050193787, "z_loss": 19.149719715118408, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30533525347709656, "tokens_per_second": 4103247.84876025, "eta_seconds": 6135.958456325531, "data_wait_seconds": 1.3887882232666016e-05}
|
| 462 |
+
{"step": 4610, "total_steps": 28611, "tokens": 4833935360, "loss": 2.890459179878235, "ce_loss": 2.888142168521881, "z_loss": 23.17022132873535, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2986910343170166, "tokens_per_second": 2795470.7693997454, "eta_seconds": 9002.731436681748, "data_wait_seconds": 1.531839370727539e-05}
|
| 463 |
+
{"step": 4620, "total_steps": 28611, "tokens": 4844421120, "loss": 2.87909334897995, "ce_loss": 2.8765938878059387, "z_loss": 24.99458074569702, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3003644049167633, "tokens_per_second": 3013538.380893245, "eta_seconds": 8347.790416574479, "data_wait_seconds": 1.6510486602783203e-05}
|
| 464 |
+
{"step": 4630, "total_steps": 28611, "tokens": 4854906880, "loss": 2.8464051485061646, "ce_loss": 2.844467282295227, "z_loss": 19.37829875946045, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26850128173828125, "tokens_per_second": 2758287.922266022, "eta_seconds": 9116.488838243484, "data_wait_seconds": 1.3768672943115234e-05}
|
| 465 |
+
{"step": 4640, "total_steps": 28611, "tokens": 4865392640, "loss": 2.849781632423401, "ce_loss": 2.8474600315093994, "z_loss": 23.216312408447266, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2736847400665283, "tokens_per_second": 2873084.131809278, "eta_seconds": 8748.583105421067, "data_wait_seconds": 2.086162567138672e-05}
|
| 466 |
+
{"step": 4650, "total_steps": 28611, "tokens": 4875878400, "loss": 2.838554263114929, "ce_loss": 2.836163818836212, "z_loss": 23.90430784225464, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24400445818901062, "tokens_per_second": 4534328.473986756, "eta_seconds": 5541.047517871857, "data_wait_seconds": 1.329183578491211e-05}
|
| 467 |
+
{"step": 4660, "total_steps": 28611, "tokens": 4886364160, "loss": 2.880146563053131, "ce_loss": 2.8779205679893494, "z_loss": 22.259355545043945, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28553539514541626, "tokens_per_second": 4048846.0874815844, "eta_seconds": 6202.864528155327, "data_wait_seconds": 1.710653305053711e-05}
|
| 468 |
+
{"step": 4670, "total_steps": 28611, "tokens": 4896849920, "loss": 2.854969322681427, "ce_loss": 2.852745294570923, "z_loss": 22.24062728881836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3066392242908478, "tokens_per_second": 2991678.6984008905, "eta_seconds": 8391.261410999297, "data_wait_seconds": 1.33514404296875e-05}
|
| 469 |
+
{"step": 4680, "total_steps": 28611, "tokens": 4907335680, "loss": 2.8669012784957886, "ce_loss": 2.8644495010375977, "z_loss": 24.5181941986084, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2694089412689209, "tokens_per_second": 2855495.3557488862, "eta_seconds": 8787.782548999787, "data_wait_seconds": 1.8656253814697266e-05}
|
| 470 |
+
{"step": 4690, "total_steps": 28611, "tokens": 4917821440, "loss": 2.8598344326019287, "ce_loss": 2.8574737310409546, "z_loss": 23.606557369232178, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29362916946411133, "tokens_per_second": 4519447.921162261, "eta_seconds": 5550.011181354523, "data_wait_seconds": 1.633167266845703e-05}
|
| 471 |
+
{"step": 4700, "total_steps": 28611, "tokens": 4928307200, "loss": 2.9002373218536377, "ce_loss": 2.8982993364334106, "z_loss": 19.379749298095703, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2703843116760254, "tokens_per_second": 4271029.510291538, "eta_seconds": 5870.364668655395, "data_wait_seconds": 1.710653305053711e-05}
|
| 472 |
+
{"step": 4710, "total_steps": 28611, "tokens": 4938792960, "loss": 2.855117380619049, "ce_loss": 2.852662980556488, "z_loss": 24.544267654418945, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24344028532505035, "tokens_per_second": 3025120.0000440213, "eta_seconds": 8284.634981632233, "data_wait_seconds": 1.6987323760986328e-05}
|
| 473 |
+
{"step": 4720, "total_steps": 28611, "tokens": 4949278720, "loss": 2.8525055050849915, "ce_loss": 2.85041606426239, "z_loss": 20.89525842666626, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2640773057937622, "tokens_per_second": 3037404.0201903046, "eta_seconds": 8247.677638363839, "data_wait_seconds": 1.8715858459472656e-05}
|
| 474 |
+
{"step": 4730, "total_steps": 28611, "tokens": 4959764480, "loss": 2.853421628475189, "ce_loss": 2.8510584831237793, "z_loss": 23.63163423538208, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.282329797744751, "tokens_per_second": 4501115.299796388, "eta_seconds": 5563.297491431236, "data_wait_seconds": 1.4543533325195312e-05}
|
| 475 |
+
{"step": 4740, "total_steps": 28611, "tokens": 4970250240, "loss": 2.838623523712158, "ce_loss": 2.8365681767463684, "z_loss": 20.55377435684204, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2773599624633789, "tokens_per_second": 2991249.369418927, "eta_seconds": 8367.927445936202, "data_wait_seconds": 1.7762184143066406e-05}
|
| 476 |
+
{"step": 4750, "total_steps": 28611, "tokens": 4980736000, "loss": 2.841572940349579, "ce_loss": 2.8393316864967346, "z_loss": 22.412283897399902, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2703015208244324, "tokens_per_second": 4314128.937831097, "eta_seconds": 5799.565172147751, "data_wait_seconds": 1.2755393981933594e-05}
|
| 477 |
+
{"step": 4760, "total_steps": 28611, "tokens": 4991221760, "loss": 2.8490652441978455, "ce_loss": 2.8469600677490234, "z_loss": 21.05223512649536, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2821260988712311, "tokens_per_second": 2782465.333811961, "eta_seconds": 8988.283114290238, "data_wait_seconds": 1.4066696166992188e-05}
|
| 478 |
+
{"step": 4770, "total_steps": 28611, "tokens": 5001707520, "loss": 2.850490629673004, "ce_loss": 2.848209798336029, "z_loss": 22.808415412902832, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2689613997936249, "tokens_per_second": 3058535.5021101795, "eta_seconds": 8173.5524726629255, "data_wait_seconds": 1.5556812286376953e-05}
|
| 479 |
+
{"step": 4780, "total_steps": 28611, "tokens": 5012193280, "loss": 2.8585265278816223, "ce_loss": 2.8559535145759583, "z_loss": 25.730438232421875, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2581586539745331, "tokens_per_second": 2312520.124498289, "eta_seconds": 10805.793381547926, "data_wait_seconds": 0.29825901985168457}
|
| 480 |
+
{"step": 4790, "total_steps": 28611, "tokens": 5022679040, "loss": 2.846479654312134, "ce_loss": 2.8445053696632385, "z_loss": 19.74295473098755, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26421186327934265, "tokens_per_second": 3956178.1987597807, "eta_seconds": 6313.701668906212, "data_wait_seconds": 1.3589859008789062e-05}
|
| 481 |
+
{"step": 4800, "total_steps": 28611, "tokens": 5033164800, "loss": 2.8357269167900085, "ce_loss": 2.833476483821869, "z_loss": 22.5046443939209, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26946189999580383, "tokens_per_second": 2750591.365325829, "eta_seconds": 9077.190981817246, "data_wait_seconds": 1.71661376953125e-05}
|
| 482 |
+
{"step": 4810, "total_steps": 28611, "tokens": 5043650560, "loss": 2.8729401230812073, "ce_loss": 2.8711584210395813, "z_loss": 17.8175368309021, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30905681848526, "tokens_per_second": 4260164.16773323, "eta_seconds": 5858.2618869543085, "data_wait_seconds": 1.5020370483398438e-05}
|
| 483 |
+
{"step": 4820, "total_steps": 28611, "tokens": 5054136320, "loss": 2.8481613397598267, "ce_loss": 2.8459677696228027, "z_loss": 21.935787677764893, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28971073031425476, "tokens_per_second": 2992663.568363131, "eta_seconds": 8335.942562913895, "data_wait_seconds": 1.8477439880371094e-05}
|
| 484 |
+
{"step": 4830, "total_steps": 28611, "tokens": 5064622080, "loss": 2.8564024567604065, "ce_loss": 2.854471802711487, "z_loss": 19.30617094039917, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2981952428817749, "tokens_per_second": 4577948.439921828, "eta_seconds": 5447.0219975709915, "data_wait_seconds": 1.329183578491211e-05}
|
| 485 |
+
{"step": 4840, "total_steps": 28611, "tokens": 5075107840, "loss": 2.8818039298057556, "ce_loss": 2.8793272972106934, "z_loss": 24.766355514526367, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3280891180038452, "tokens_per_second": 2970405.07650502, "eta_seconds": 8391.347124052047, "data_wait_seconds": 1.4126300811767578e-05}
|
| 486 |
+
{"step": 4850, "total_steps": 28611, "tokens": 5085593600, "loss": 2.8162323236465454, "ce_loss": 2.8143922686576843, "z_loss": 18.40050983428955, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24066857993602753, "tokens_per_second": 2954059.4285614495, "eta_seconds": 8434.22921526432, "data_wait_seconds": 0.29496824741363525}
|
| 487 |
+
{"step": 4860, "total_steps": 28611, "tokens": 5096079360, "loss": 2.872758209705353, "ce_loss": 2.8705215454101562, "z_loss": 22.36639928817749, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27830323576927185, "tokens_per_second": 4490765.551132002, "eta_seconds": 5545.764590120316, "data_wait_seconds": 1.7523765563964844e-05}
|
| 488 |
+
{"step": 4870, "total_steps": 28611, "tokens": 5106565120, "loss": 2.8078288435935974, "ce_loss": 2.8055561184883118, "z_loss": 22.727385997772217, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25972411036491394, "tokens_per_second": 4640530.470019146, "eta_seconds": 5364.525236248969, "data_wait_seconds": 1.1682510375976562e-05}
|
| 489 |
+
{"step": 4880, "total_steps": 28611, "tokens": 5117050880, "loss": 2.891089916229248, "ce_loss": 2.889294981956482, "z_loss": 17.94898557662964, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30362385511398315, "tokens_per_second": 2894367.9480003803, "eta_seconds": 8597.302590084075, "data_wait_seconds": 1.4662742614746094e-05}
|
| 490 |
+
{"step": 4890, "total_steps": 28611, "tokens": 5127536640, "loss": 2.853326976299286, "ce_loss": 2.8510684967041016, "z_loss": 22.584437370300293, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3077157437801361, "tokens_per_second": 3992053.47507303, "eta_seconds": 6230.695919108391, "data_wait_seconds": 1.3589859008789062e-05}
|
| 491 |
+
{"step": 4900, "total_steps": 28611, "tokens": 5138022400, "loss": 2.8302329182624817, "ce_loss": 2.8282254934310913, "z_loss": 20.074665069580078, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24874533712863922, "tokens_per_second": 2960316.4362421017, "eta_seconds": 8398.691853213311, "data_wait_seconds": 1.6510486602783203e-05}
|
| 492 |
+
{"step": 4910, "total_steps": 28611, "tokens": 5148508160, "loss": 2.841311991214752, "ce_loss": 2.838577926158905, "z_loss": 27.340368270874023, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24776367843151093, "tokens_per_second": 4571996.341510169, "eta_seconds": 5435.765455532074, "data_wait_seconds": 1.4901161193847656e-05}
|
| 493 |
+
{"step": 4920, "total_steps": 28611, "tokens": 5158993920, "loss": 2.860412836074829, "ce_loss": 2.858314037322998, "z_loss": 20.98746967315674, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2840048372745514, "tokens_per_second": 2983624.437907857, "eta_seconds": 8326.052602458, "data_wait_seconds": 1.3887882232666016e-05}
|
| 494 |
+
{"step": 4930, "total_steps": 28611, "tokens": 5169479680, "loss": 2.8444469571113586, "ce_loss": 2.841994285583496, "z_loss": 24.526278018951416, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26817306876182556, "tokens_per_second": 3035306.9206709047, "eta_seconds": 8180.829453158379, "data_wait_seconds": 0.27299004793167114}
|
| 495 |
+
{"step": 4940, "total_steps": 28611, "tokens": 5179965440, "loss": 2.8317294120788574, "ce_loss": 2.8298068046569824, "z_loss": 19.22528076171875, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2836485803127289, "tokens_per_second": 4501614.249826918, "eta_seconds": 5513.76486711502, "data_wait_seconds": 1.3828277587890625e-05}
|
| 496 |
+
{"step": 4950, "total_steps": 28611, "tokens": 5190451200, "loss": 2.8478071093559265, "ce_loss": 2.845799148082733, "z_loss": 20.07975196838379, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28038331866264343, "tokens_per_second": 3122272.3080404974, "eta_seconds": 7946.250130748749, "data_wait_seconds": 1.621246337890625e-05}
|
| 497 |
+
{"step": 4960, "total_steps": 28611, "tokens": 5200936960, "loss": 2.8581709265708923, "ce_loss": 2.8562917709350586, "z_loss": 18.791743278503418, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2796802818775177, "tokens_per_second": 4672990.307211332, "eta_seconds": 5307.066641616821, "data_wait_seconds": 1.8537044525146484e-05}
|
| 498 |
+
{"step": 4970, "total_steps": 28611, "tokens": 5211422720, "loss": 2.8664321899414062, "ce_loss": 2.8642722368240356, "z_loss": 21.59907341003418, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2679775357246399, "tokens_per_second": 2978172.0251328517, "eta_seconds": 8323.69151506424, "data_wait_seconds": 1.4424324035644531e-05}
|
| 499 |
+
{"step": 4980, "total_steps": 28611, "tokens": 5221908480, "loss": 2.8875719904899597, "ce_loss": 2.885858654975891, "z_loss": 17.133514642715454, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2828197479248047, "tokens_per_second": 2909364.536216277, "eta_seconds": 8516.945589852334, "data_wait_seconds": 0.2682461738586426}
|
| 500 |
+
{"step": 4990, "total_steps": 28611, "tokens": 5232394240, "loss": 2.8775826692581177, "ce_loss": 2.875543773174286, "z_loss": 20.389357089996338, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2667386531829834, "tokens_per_second": 4110899.7523148335, "eta_seconds": 6025.059035325051, "data_wait_seconds": 1.2636184692382812e-05}
|
| 501 |
+
{"step": 5000, "total_steps": 28611, "tokens": 5242880000, "loss": 2.8702152371406555, "ce_loss": 2.8680903911590576, "z_loss": 21.24892807006836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.31298840045928955, "tokens_per_second": 3086126.660865914, "eta_seconds": 8022.330466842651, "data_wait_seconds": 0.04120147228240967}
|
| 502 |
+
{"step": 5010, "total_steps": 28611, "tokens": 5253365760, "loss": 2.8509527444839478, "ce_loss": 2.848973035812378, "z_loss": 19.797194004058838, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2576618492603302, "tokens_per_second": 2973802.8261808995, "eta_seconds": 8321.816751980781, "data_wait_seconds": 0.26097142696380615}
|
| 503 |
+
{"step": 5020, "total_steps": 28611, "tokens": 5263851520, "loss": 2.832056164741516, "ce_loss": 2.8299161195755005, "z_loss": 21.40045928955078, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2953527867794037, "tokens_per_second": 3153192.570921706, "eta_seconds": 7845.050963306428, "data_wait_seconds": 1.5139579772949219e-05}
|
| 504 |
+
{"step": 5030, "total_steps": 28611, "tokens": 5274337280, "loss": 2.872215449810028, "ce_loss": 2.8701802492141724, "z_loss": 20.351999282836914, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2614591717720032, "tokens_per_second": 3096986.6322598234, "eta_seconds": 7984.041777396203, "data_wait_seconds": 1.3947486877441406e-05}
|
| 505 |
+
{"step": 5040, "total_steps": 28611, "tokens": 5284823040, "loss": 2.8360384106636047, "ce_loss": 2.833931267261505, "z_loss": 21.07228183746338, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2633492052555084, "tokens_per_second": 2985648.88237849, "eta_seconds": 8278.262404489516, "data_wait_seconds": 0.3046404719352722}
|
| 506 |
+
{"step": 5050, "total_steps": 28611, "tokens": 5295308800, "loss": 2.8249053955078125, "ce_loss": 2.8225702047348022, "z_loss": 23.35150146484375, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28290316462516785, "tokens_per_second": 4736147.787682398, "eta_seconds": 5216.369979047776, "data_wait_seconds": 1.424551010131836e-05}
|
| 507 |
+
{"step": 5060, "total_steps": 28611, "tokens": 5305794560, "loss": 2.8951034545898438, "ce_loss": 2.8933791518211365, "z_loss": 17.242838382720947, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27075475454330444, "tokens_per_second": 3161720.7451575072, "eta_seconds": 7810.624456262588, "data_wait_seconds": 1.7642974853515625e-05}
|
| 508 |
+
{"step": 5070, "total_steps": 28611, "tokens": 5316280320, "loss": 2.842601239681244, "ce_loss": 2.8404244780540466, "z_loss": 21.767410278320312, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24469220638275146, "tokens_per_second": 4189523.0558541915, "eta_seconds": 5891.966051244736, "data_wait_seconds": 1.7344951629638672e-05}
|
| 509 |
+
{"step": 5080, "total_steps": 28611, "tokens": 5326766080, "loss": 2.861898720264435, "ce_loss": 2.860158324241638, "z_loss": 17.404105186462402, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2877402603626251, "tokens_per_second": 2961649.676039491, "eta_seconds": 8331.181792235375, "data_wait_seconds": 1.5437602996826172e-05}
|
| 510 |
+
{"step": 5090, "total_steps": 28611, "tokens": 5337251840, "loss": 2.8390270471572876, "ce_loss": 2.8369157314300537, "z_loss": 21.11320734024048, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3135501444339752, "tokens_per_second": 3155817.381498624, "eta_seconds": 7815.267207980156, "data_wait_seconds": 0.2520154118537903}
|
| 511 |
+
{"step": 5100, "total_steps": 28611, "tokens": 5347737600, "loss": 2.8718366026878357, "ce_loss": 2.869609534740448, "z_loss": 22.269948482513428, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2902224659919739, "tokens_per_second": 4106018.662398743, "eta_seconds": 6004.130122876167, "data_wait_seconds": 1.4722347259521484e-05}
|
| 512 |
+
{"step": 5110, "total_steps": 28611, "tokens": 5358223360, "loss": 2.8888670802116394, "ce_loss": 2.88707172870636, "z_loss": 17.953436851501465, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25678661465644836, "tokens_per_second": 2910372.211430019, "eta_seconds": 8467.159107422827, "data_wait_seconds": 1.3828277587890625e-05}
|
| 513 |
+
{"step": 5120, "total_steps": 28611, "tokens": 5368709120, "loss": 2.8413995504379272, "ce_loss": 2.8395485877990723, "z_loss": 18.509550094604492, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3140503764152527, "tokens_per_second": 3051207.5113468613, "eta_seconds": 8072.901867341996, "data_wait_seconds": 1.7821788787841797e-05}
|
| 514 |
+
{"step": 5130, "total_steps": 28611, "tokens": 5379194880, "loss": 2.840455174446106, "ce_loss": 2.8387102484703064, "z_loss": 17.449350833892822, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.251611590385437, "tokens_per_second": 4967382.0062770415, "eta_seconds": 4956.657858181, "data_wait_seconds": 1.1980533599853516e-05}
|
| 515 |
+
{"step": 5140, "total_steps": 28611, "tokens": 5389680640, "loss": 2.8643383383750916, "ce_loss": 2.8625248670578003, "z_loss": 18.134280681610107, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30625471472740173, "tokens_per_second": 3023466.479099151, "eta_seconds": 8140.036433720589, "data_wait_seconds": 1.3470649719238281e-05}
|
| 516 |
+
{"step": 5150, "total_steps": 28611, "tokens": 5400166400, "loss": 2.8467459678649902, "ce_loss": 2.8444237112998962, "z_loss": 23.222238540649414, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2681812345981598, "tokens_per_second": 3159583.585299198, "eta_seconds": 7786.039163661003, "data_wait_seconds": 1.7344951629638672e-05}
|
| 517 |
+
{"step": 5160, "total_steps": 28611, "tokens": 5410652160, "loss": 2.901316821575165, "ce_loss": 2.8994216918945312, "z_loss": 18.951197624206543, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2915832996368408, "tokens_per_second": 3979931.611692369, "eta_seconds": 6178.537265253067, "data_wait_seconds": 1.806020736694336e-05}
|
| 518 |
+
{"step": 5170, "total_steps": 28611, "tokens": 5421137920, "loss": 2.8808563947677612, "ce_loss": 2.8790379762649536, "z_loss": 18.183846950531006, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26225903630256653, "tokens_per_second": 9768500.342502479, "eta_seconds": 2516.2173470020293, "data_wait_seconds": 1.2218952178955078e-05}
|
| 519 |
+
{"step": 5180, "total_steps": 28611, "tokens": 5431623680, "loss": 2.846882700920105, "ce_loss": 2.8448838591575623, "z_loss": 19.98788833618164, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.26489630341529846, "tokens_per_second": 4356624.595772316, "eta_seconds": 5639.4999651432045, "data_wait_seconds": 1.4662742614746094e-05}
|
| 520 |
+
{"step": 5190, "total_steps": 28611, "tokens": 5442109440, "loss": 2.8406771421432495, "ce_loss": 2.8391152024269104, "z_loss": 15.619572639465332, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2802983224391937, "tokens_per_second": 2950812.337770106, "eta_seconds": 8322.690732192994, "data_wait_seconds": 1.4483928680419922e-05}
|
| 521 |
+
{"step": 5200, "total_steps": 28611, "tokens": 5452595200, "loss": 2.7970157861709595, "ce_loss": 2.7950050830841064, "z_loss": 20.106762409210205, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27595052123069763, "tokens_per_second": 4626486.693998907, "eta_seconds": 5306.016067838668, "data_wait_seconds": 1.817941665649414e-05}
|
| 522 |
+
{"step": 5210, "total_steps": 28611, "tokens": 5463080960, "loss": 2.882532060146332, "ce_loss": 2.880864381790161, "z_loss": 16.677371978759766, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28218430280685425, "tokens_per_second": 2880400.0289111035, "eta_seconds": 8518.860828256607, "data_wait_seconds": 1.8835067749023438e-05}
|
| 523 |
+
{"step": 5220, "total_steps": 28611, "tokens": 5473566720, "loss": 2.859506905078888, "ce_loss": 2.857811391353607, "z_loss": 16.955758094787598, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2721351981163025, "tokens_per_second": 4329617.341975806, "eta_seconds": 5664.990524268151, "data_wait_seconds": 1.5914440155029297e-05}
|
| 524 |
+
{"step": 5230, "total_steps": 28611, "tokens": 5484052480, "loss": 2.8355135321617126, "ce_loss": 2.8337318301200867, "z_loss": 17.81676483154297, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2919056713581085, "tokens_per_second": 2827714.362402161, "eta_seconds": 8670.166895914077, "data_wait_seconds": 0.30075323581695557}
|
| 525 |
+
{"step": 5240, "total_steps": 28611, "tokens": 5494538240, "loss": 2.874295234680176, "ce_loss": 2.8722482919692993, "z_loss": 20.469712257385254, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27379509806632996, "tokens_per_second": 4234411.490041681, "eta_seconds": 5787.408652567863, "data_wait_seconds": 1.3649463653564453e-05}
|
| 526 |
+
{"step": 5250, "total_steps": 28611, "tokens": 5505024000, "loss": 2.8303322792053223, "ce_loss": 2.828245460987091, "z_loss": 20.867538452148438, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2904130518436432, "tokens_per_second": 2735522.72630831, "eta_seconds": 8954.699480438232, "data_wait_seconds": 1.9609928131103516e-05}
|
| 527 |
+
{"step": 5260, "total_steps": 28611, "tokens": 5515509760, "loss": 2.9127069115638733, "ce_loss": 2.910534679889679, "z_loss": 21.722198963165283, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3019965887069702, "tokens_per_second": 4306090.803219411, "eta_seconds": 5686.201080036163, "data_wait_seconds": 1.1861324310302734e-05}
|
| 528 |
+
{"step": 5270, "total_steps": 28611, "tokens": 5525995520, "loss": 2.865713894367218, "ce_loss": 2.8637643456459045, "z_loss": 19.495180130004883, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25614386796951294, "tokens_per_second": 3015478.9597516665, "eta_seconds": 8116.393031644821, "data_wait_seconds": 1.8477439880371094e-05}
|
| 529 |
+
{"step": 5280, "total_steps": 28611, "tokens": 5536481280, "loss": 2.851631820201874, "ce_loss": 2.8499905467033386, "z_loss": 16.41267156600952, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30811139941215515, "tokens_per_second": 4659349.345488054, "eta_seconds": 5250.588621282577, "data_wait_seconds": 1.3530254364013672e-05}
|
| 530 |
+
{"step": 5290, "total_steps": 28611, "tokens": 5546967040, "loss": 2.8721131682395935, "ce_loss": 2.870331645011902, "z_loss": 17.81544542312622, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2702823877334595, "tokens_per_second": 3042003.2791480212, "eta_seconds": 8038.729301714897, "data_wait_seconds": 1.436471939086914e-05}
|
| 531 |
+
{"step": 5300, "total_steps": 28611, "tokens": 5557452800, "loss": 2.867655634880066, "ce_loss": 2.866017460823059, "z_loss": 16.382282257080078, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2713162302970886, "tokens_per_second": 3294484.4793848204, "eta_seconds": 7419.478006029129, "data_wait_seconds": 1.806020736694336e-05}
|
| 532 |
+
{"step": 5310, "total_steps": 28611, "tokens": 5567938560, "loss": 2.8594855070114136, "ce_loss": 2.8573344945907593, "z_loss": 21.510239124298096, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30282530188560486, "tokens_per_second": 3343876.4265241865, "eta_seconds": 7306.75008866787, "data_wait_seconds": 1.6689300537109375e-05}
|
| 533 |
+
{"step": 5320, "total_steps": 28611, "tokens": 5578424320, "loss": 2.863983988761902, "ce_loss": 2.8621283173561096, "z_loss": 18.556779861450195, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2491503804922104, "tokens_per_second": 2287710.588791075, "eta_seconds": 10675.46906311512, "data_wait_seconds": 1.901388168334961e-05}
|
| 534 |
+
{"step": 5330, "total_steps": 28611, "tokens": 5588910080, "loss": 2.828756034374237, "ce_loss": 2.826768696308136, "z_loss": 19.873632431030273, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2866571545600891, "tokens_per_second": 4118118.246894964, "eta_seconds": 5927.925424289703, "data_wait_seconds": 1.3649463653564453e-05}
|
| 535 |
+
{"step": 5340, "total_steps": 28611, "tokens": 5599395840, "loss": 2.8658642172813416, "ce_loss": 2.8634076714515686, "z_loss": 24.565459728240967, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.30240121483802795, "tokens_per_second": 2816057.318840844, "eta_seconds": 8665.097806334496, "data_wait_seconds": 1.615285873413086e-05}
|
| 536 |
+
{"step": 5350, "total_steps": 28611, "tokens": 5609881600, "loss": 2.848562002182007, "ce_loss": 2.846404492855072, "z_loss": 21.574832916259766, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.23635368049144745, "tokens_per_second": 3242063.4867928224, "eta_seconds": 7523.272272539139, "data_wait_seconds": 0.27497631311416626}
|
| 537 |
+
{"step": 5360, "total_steps": 28611, "tokens": 5620367360, "loss": 2.8498326539993286, "ce_loss": 2.847572445869446, "z_loss": 22.601855754852295, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2696838676929474, "tokens_per_second": 4339208.15034773, "eta_seconds": 5618.638178038596, "data_wait_seconds": 1.3589859008789062e-05}
|
| 538 |
+
{"step": 5370, "total_steps": 28611, "tokens": 5630853120, "loss": 2.868575632572174, "ce_loss": 2.866249740123749, "z_loss": 23.258906364440918, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3031178116798401, "tokens_per_second": 3039142.5473411586, "eta_seconds": 8018.694232463837, "data_wait_seconds": 1.4960765838623047e-05}
|
| 539 |
+
{"step": 5380, "total_steps": 28611, "tokens": 5641338880, "loss": 2.888072907924652, "ce_loss": 2.886109232902527, "z_loss": 19.636864185333252, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29231971502304077, "tokens_per_second": 3058194.794868434, "eta_seconds": 7965.309828162193, "data_wait_seconds": 1.6868114471435547e-05}
|
| 540 |
+
{"step": 5390, "total_steps": 28611, "tokens": 5651824640, "loss": 2.852774202823639, "ce_loss": 2.8506722450256348, "z_loss": 21.01936626434326, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28133222460746765, "tokens_per_second": 4328771.024021079, "eta_seconds": 5624.91828763485, "data_wait_seconds": 1.245737075805664e-05}
|
| 541 |
+
{"step": 5400, "total_steps": 28611, "tokens": 5662310400, "loss": 2.8811079263687134, "ce_loss": 2.878801465034485, "z_loss": 23.063867568969727, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2867341935634613, "tokens_per_second": 2346147.2147019403, "eta_seconds": 10373.815156817436, "data_wait_seconds": 0.2611260414123535}
|
| 542 |
+
{"step": 5410, "total_steps": 28611, "tokens": 5672796160, "loss": 2.864288330078125, "ce_loss": 2.862634539604187, "z_loss": 16.53721332550049, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2603471577167511, "tokens_per_second": 2716691.2107901536, "eta_seconds": 8955.015453863143, "data_wait_seconds": 1.800060272216797e-05}
|
| 543 |
+
{"step": 5420, "total_steps": 28611, "tokens": 5683281920, "loss": 2.87518447637558, "ce_loss": 2.873203933238983, "z_loss": 19.805065155029297, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28538185358047485, "tokens_per_second": 4144157.2063512164, "eta_seconds": 5867.906260585785, "data_wait_seconds": 1.430511474609375e-05}
|
| 544 |
+
{"step": 5430, "total_steps": 28611, "tokens": 5693767680, "loss": 2.86641126871109, "ce_loss": 2.86479115486145, "z_loss": 16.20119047164917, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2870481014251709, "tokens_per_second": 2977308.1229516417, "eta_seconds": 8164.099667286872, "data_wait_seconds": 0.2642616033554077}
|
| 545 |
+
{"step": 5440, "total_steps": 28611, "tokens": 5704253440, "loss": 2.820334792137146, "ce_loss": 2.818217933177948, "z_loss": 21.168777465820312, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24116264283657074, "tokens_per_second": 3571855.305090311, "eta_seconds": 6802.222492432595, "data_wait_seconds": 1.3113021850585938e-05}
|
| 546 |
+
{"step": 5450, "total_steps": 28611, "tokens": 5714739200, "loss": 2.8842380046844482, "ce_loss": 2.8822269439697266, "z_loss": 20.1106014251709, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2831636965274811, "tokens_per_second": 2930424.9391743364, "eta_seconds": 8287.558712506294, "data_wait_seconds": 1.71661376953125e-05}
|
| 547 |
+
{"step": 5460, "total_steps": 28611, "tokens": 5725224960, "loss": 2.838895618915558, "ce_loss": 2.8369300365448, "z_loss": 19.65572166442871, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2742737829685211, "tokens_per_second": 2274289.1492288676, "eta_seconds": 10673.921116948128, "data_wait_seconds": 0.29230791330337524}
|
| 548 |
+
{"step": 5470, "total_steps": 28611, "tokens": 5735710720, "loss": 2.8159228563308716, "ce_loss": 2.8141197562217712, "z_loss": 18.031214237213135, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.24135997891426086, "tokens_per_second": 4096663.193299353, "eta_seconds": 5923.1369705200195, "data_wait_seconds": 1.4185905456542969e-05}
|
| 549 |
+
{"step": 5480, "total_steps": 28611, "tokens": 5746196480, "loss": 2.88388854265213, "ce_loss": 2.8822324872016907, "z_loss": 16.56078267097473, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3113740384578705, "tokens_per_second": 2791749.8577346173, "eta_seconds": 8687.960129666328, "data_wait_seconds": 1.6510486602783203e-05}
|
| 550 |
+
{"step": 5490, "total_steps": 28611, "tokens": 5756682240, "loss": 2.900524318218231, "ce_loss": 2.898568332195282, "z_loss": 19.559576511383057, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27984267473220825, "tokens_per_second": 3983599.943465724, "eta_seconds": 6085.984044599533, "data_wait_seconds": 1.633167266845703e-05}
|
| 551 |
+
{"step": 5500, "total_steps": 28611, "tokens": 5767168000, "loss": 2.917384684085846, "ce_loss": 2.915222942829132, "z_loss": 21.61765766143799, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3300296664237976, "tokens_per_second": 3126507.4850228867, "eta_seconds": 7751.025721859932, "data_wait_seconds": 0.28453850746154785}
|
| 552 |
+
{"step": 5510, "total_steps": 28611, "tokens": 5777653760, "loss": 2.8312202095985413, "ce_loss": 2.8295140266418457, "z_loss": 17.061892986297607, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2986941337585449, "tokens_per_second": 4112708.4443204263, "eta_seconds": 5889.83014574051, "data_wait_seconds": 1.4543533325195312e-05}
|
| 553 |
+
{"step": 5520, "total_steps": 28611, "tokens": 5788139520, "loss": 2.8378873467445374, "ce_loss": 2.835945188999176, "z_loss": 19.421292781829834, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29639849066734314, "tokens_per_second": 2940350.041764162, "eta_seconds": 8234.621073031425, "data_wait_seconds": 1.8298625946044922e-05}
|
| 554 |
+
{"step": 5530, "total_steps": 28611, "tokens": 5798625280, "loss": 2.821432590484619, "ce_loss": 2.8192997574806213, "z_loss": 21.327750205993652, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28678369522094727, "tokens_per_second": 4152765.101490504, "eta_seconds": 5827.9681283473965, "data_wait_seconds": 2.0265579223632812e-05}
|
| 555 |
+
{"step": 5540, "total_steps": 28611, "tokens": 5809111040, "loss": 2.8544209599494934, "ce_loss": 2.8522366881370544, "z_loss": 21.84286880493164, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2961283028125763, "tokens_per_second": 2913519.668834758, "eta_seconds": 8303.255047416687, "data_wait_seconds": 1.9073486328125e-05}
|
| 556 |
+
{"step": 5550, "total_steps": 28611, "tokens": 5819596800, "loss": 2.8146973848342896, "ce_loss": 2.812445282936096, "z_loss": 22.521353244781494, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.28307634592056274, "tokens_per_second": 4480409.886039056, "eta_seconds": 5397.097977876663, "data_wait_seconds": 1.919269561767578e-05}
|
| 557 |
+
{"step": 5560, "total_steps": 28611, "tokens": 5830082560, "loss": 2.812990427017212, "ce_loss": 2.810965657234192, "z_loss": 20.247817516326904, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2567515969276428, "tokens_per_second": 2870018.3300115517, "eta_seconds": 8421.801743650436, "data_wait_seconds": 1.71661376953125e-05}
|
| 558 |
+
{"step": 5570, "total_steps": 28611, "tokens": 5840568320, "loss": 2.8621554374694824, "ce_loss": 2.860354483127594, "z_loss": 18.009080410003662, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2731661796569824, "tokens_per_second": 2845577.432664114, "eta_seconds": 8490.45235552788, "data_wait_seconds": 1.4722347259521484e-05}
|
| 559 |
+
{"step": 5580, "total_steps": 28611, "tokens": 5851054080, "loss": 2.862524688243866, "ce_loss": 2.8608453273773193, "z_loss": 16.793652534484863, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2731526494026184, "tokens_per_second": 4428823.735891833, "eta_seconds": 5452.859561848641, "data_wait_seconds": 1.5079975128173828e-05}
|
| 560 |
+
{"step": 5590, "total_steps": 28611, "tokens": 5861539840, "loss": 2.833803653717041, "ce_loss": 2.831888437271118, "z_loss": 19.15241003036499, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2954215705394745, "tokens_per_second": 4779689.935407489, "eta_seconds": 5050.383690619468, "data_wait_seconds": 1.627206802368164e-05}
|
| 561 |
+
{"step": 5600, "total_steps": 28611, "tokens": 5872025600, "loss": 2.7937440276145935, "ce_loss": 2.791705548763275, "z_loss": 20.384576320648193, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2282181978225708, "tokens_per_second": 4108980.167236901, "eta_seconds": 5872.207057213783, "data_wait_seconds": 1.8298625946044922e-05}
|
| 562 |
+
{"step": 5610, "total_steps": 28611, "tokens": 5882511360, "loss": 2.7813501358032227, "ce_loss": 2.7797058820724487, "z_loss": 16.442617416381836, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2770359218120575, "tokens_per_second": 2995926.1224583774, "eta_seconds": 8050.364258050919, "data_wait_seconds": 1.5735626220703125e-05}
|
| 563 |
+
{"step": 5620, "total_steps": 28611, "tokens": 5892997120, "loss": 2.821694076061249, "ce_loss": 2.819494366645813, "z_loss": 21.997390747070312, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3083125054836273, "tokens_per_second": 3078285.265629132, "eta_seconds": 7831.571389818191, "data_wait_seconds": 0.21795302629470825}
|
| 564 |
+
{"step": 5630, "total_steps": 28611, "tokens": 5903482880, "loss": 2.8470510840415955, "ce_loss": 2.844879984855652, "z_loss": 21.711091995239258, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29306116700172424, "tokens_per_second": 4735238.589335877, "eta_seconds": 5088.935774064064, "data_wait_seconds": 1.2755393981933594e-05}
|
| 565 |
+
{"step": 5640, "total_steps": 28611, "tokens": 5913968640, "loss": 2.8535556197166443, "ce_loss": 2.851509988307953, "z_loss": 20.45615816116333, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2659810483455658, "tokens_per_second": 3117700.9042824903, "eta_seconds": 7725.833887052537, "data_wait_seconds": 0.26430535316467285}
|
| 566 |
+
{"step": 5650, "total_steps": 28611, "tokens": 5924454400, "loss": 2.850207567214966, "ce_loss": 2.847760021686554, "z_loss": 24.475388050079346, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.25985246896743774, "tokens_per_second": 4512840.538448625, "eta_seconds": 5335.077393245697, "data_wait_seconds": 1.3589859008789062e-05}
|
| 567 |
+
{"step": 5660, "total_steps": 28611, "tokens": 5934940160, "loss": 2.831961989402771, "ce_loss": 2.8302029967308044, "z_loss": 17.589582920074463, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.3041720390319824, "tokens_per_second": 2841516.9476822694, "eta_seconds": 8469.373302745818, "data_wait_seconds": 1.436471939086914e-05}
|
| 568 |
+
{"step": 5670, "total_steps": 28611, "tokens": 5945425920, "loss": 2.8206741213798523, "ce_loss": 2.818877935409546, "z_loss": 17.961820125579834, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.303232342004776, "tokens_per_second": 3299995.956537757, "eta_seconds": 7289.51863360405, "data_wait_seconds": 0.25112783908843994}
|
| 569 |
+
{"step": 5680, "total_steps": 28611, "tokens": 5955911680, "loss": 2.824622690677643, "ce_loss": 2.8231261372566223, "z_loss": 14.96519136428833, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2889309525489807, "tokens_per_second": 4167445.893521083, "eta_seconds": 5769.696084928512, "data_wait_seconds": 1.3232231140136719e-05}
|
| 570 |
+
{"step": 5690, "total_steps": 28611, "tokens": 5966397440, "loss": 2.8421149849891663, "ce_loss": 2.840066075325012, "z_loss": 20.48895502090454, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.27557840943336487, "tokens_per_second": 3001540.6866234937, "eta_seconds": 8007.3578889369965, "data_wait_seconds": 1.817941665649414e-05}
|
| 571 |
+
{"step": 5700, "total_steps": 28611, "tokens": 5976883200, "loss": 2.8146555423736572, "ce_loss": 2.8128944039344788, "z_loss": 17.6112961769104, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29659146070480347, "tokens_per_second": 2857028.4860553085, "eta_seconds": 8408.710257267952, "data_wait_seconds": 2.0623207092285156e-05}
|
| 572 |
+
{"step": 5710, "total_steps": 28611, "tokens": 5987368960, "loss": 2.815598785877228, "ce_loss": 2.813680648803711, "z_loss": 19.181795597076416, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.29509371519088745, "tokens_per_second": 4464471.598225356, "eta_seconds": 5378.786368703842, "data_wait_seconds": 1.5020370483398438e-05}
|
| 573 |
+
{"step": 5720, "total_steps": 28611, "tokens": 5997854720, "loss": 2.8120274543762207, "ce_loss": 2.810309886932373, "z_loss": 17.176077365875244, "muon_lr": 0.03, "adamw_lr": 0.003, "grad_norm": 0.2933826446533203, "tokens_per_second": 3011024.430394211, "eta_seconds": 7971.689958310127, "data_wait_seconds": 1.8417835235595703e-05}
|