{"step": 1, "total_steps": 22439, "tokens": 8912896, "source": "fineweb_hq", "phase": 1, "loss": 5.967588186264038, "ce_loss": 5.96400511264801, "logit_z_loss": 35.83174705505371, "muon_lr": 7.000000000000001e-05, "adamw_lr": 4e-06, "grad_norm": 0.2956637740135193, "tokens_per_second": 189609.30176880484, "eta_seconds": 1054734.9659662247, "data_wait_seconds": 14.140621960163116} {"step": 10, "total_steps": 22439, "tokens": 89128960, "source": "fineweb_hq", "phase": 1, "loss": 5.960334777832031, "ce_loss": 5.956752300262451, "logit_z_loss": 35.8258056640625, "muon_lr": 0.0007000000000000001, "adamw_lr": 4e-05, "grad_norm": 0.31783637404441833, "tokens_per_second": 5420500.847961092, "eta_seconds": 36879.86590006616, "data_wait_seconds": 1.4603137969970703e-05} {"step": 20, "total_steps": 22439, "tokens": 178257920, "source": "fineweb_hq", "phase": 1, "loss": 5.931681752204895, "ce_loss": 5.928101181983948, "logit_z_loss": 35.80507564544678, "muon_lr": 0.0014000000000000002, "adamw_lr": 8e-05, "grad_norm": 0.4683179557323456, "tokens_per_second": 8017463.216447492, "eta_seconds": 24922.872737860678, "data_wait_seconds": 2.5212764739990234e-05} {"step": 30, "total_steps": 22439, "tokens": 267386880, "source": "fineweb_hq", "phase": 1, "loss": 5.882287383079529, "ce_loss": 5.878711581230164, "logit_z_loss": 35.75691223144531, "muon_lr": 0.0021000000000000003, "adamw_lr": 0.00011999999999999999, "grad_norm": 0.8383325934410095, "tokens_per_second": 9117651.124056717, "eta_seconds": 21905.761006474495, "data_wait_seconds": 1.71661376953125e-05} {"step": 40, "total_steps": 22439, "tokens": 356515840, "source": "fineweb_hq", "phase": 1, "loss": 5.780414581298828, "ce_loss": 5.776850700378418, "logit_z_loss": 35.63748264312744, "muon_lr": 0.0028000000000000004, "adamw_lr": 0.00016, "grad_norm": 1.4044978618621826, "tokens_per_second": 6684341.910831861, "eta_seconds": 29866.808156609535, "data_wait_seconds": 0.3183640241622925} {"step": 50, "total_steps": 22439, "tokens": 445644800, "source": "fineweb_hq", "phase": 1, "loss": 5.59889280796051, "ce_loss": 5.595354795455933, "logit_z_loss": 35.38116645812988, "muon_lr": 0.0035000000000000005, "adamw_lr": 0.0002, "grad_norm": 1.7537622451782227, "tokens_per_second": 5099766.386212357, "eta_seconds": 39129.40582602024, "data_wait_seconds": 2.2590160369873047e-05} {"step": 60, "total_steps": 22439, "tokens": 534773760, "source": "fineweb_hq", "phase": 1, "loss": 5.355036377906799, "ce_loss": 5.351527690887451, "logit_z_loss": 35.08798122406006, "muon_lr": 0.004200000000000001, "adamw_lr": 0.00023999999999999998, "grad_norm": 1.1905395984649658, "tokens_per_second": 2275357.7469289554, "eta_seconds": 87661.68742177486, "data_wait_seconds": 0.6237474083900452} {"step": 70, "total_steps": 22439, "tokens": 623902720, "source": "fineweb_hq", "phase": 1, "loss": 5.146511554718018, "ce_loss": 5.143023490905762, "logit_z_loss": 34.881529808044434, "muon_lr": 0.004900000000000001, "adamw_lr": 0.00028000000000000003, "grad_norm": 0.7038048505783081, "tokens_per_second": 8753024.844715588, "eta_seconds": 22777.562518215178, "data_wait_seconds": 1.5974044799804688e-05} {"step": 80, "total_steps": 22439, "tokens": 713031680, "source": "fineweb_hq", "phase": 1, "loss": 4.965500593185425, "ce_loss": 4.962033152580261, "logit_z_loss": 34.67446708679199, "muon_lr": 0.005600000000000001, "adamw_lr": 0.00032, "grad_norm": 0.5216459631919861, "tokens_per_second": 8269934.859357731, "eta_seconds": 24097.341158437728, "data_wait_seconds": 2.2351741790771484e-05} {"step": 90, "total_steps": 22439, "tokens": 802160640, "source": "fineweb_hq", "phase": 1, "loss": 4.804619193077087, "ce_loss": 4.801155209541321, "logit_z_loss": 34.64008712768555, "muon_lr": 0.006300000000000001, "adamw_lr": 0.00035999999999999997, "grad_norm": 0.42248982191085815, "tokens_per_second": 5011402.028131011, "eta_seconds": 39748.22047519684, "data_wait_seconds": 1.7404556274414062e-05} {"step": 100, "total_steps": 22439, "tokens": 891289600, "source": "fineweb_hq", "phase": 1, "loss": 4.666997671127319, "ce_loss": 4.663511872291565, "logit_z_loss": 34.85922431945801, "muon_lr": 0.007000000000000001, "adamw_lr": 0.0004, "grad_norm": 0.38025227189064026, "tokens_per_second": 964689.3882402931, "eta_seconds": 206393.0485512972, "data_wait_seconds": 8.485594153404236} {"step": 110, "total_steps": 22439, "tokens": 980418560, "source": "fineweb_hq", "phase": 1, "loss": 4.543195128440857, "ce_loss": 4.539679646492004, "logit_z_loss": 35.1539421081543, "muon_lr": 0.007700000000000001, "adamw_lr": 0.00044, "grad_norm": 0.3504329323768616, "tokens_per_second": 2999739.504100792, "eta_seconds": 66344.44574668408, "data_wait_seconds": 1.913309097290039e-05} {"step": 120, "total_steps": 22439, "tokens": 1069547520, "source": "fineweb_hq", "phase": 1, "loss": 4.42356538772583, "ce_loss": 4.4200040102005005, "logit_z_loss": 35.61503314971924, "muon_lr": 0.008400000000000001, "adamw_lr": 0.00047999999999999996, "grad_norm": 0.3508388102054596, "tokens_per_second": 2185220.094304317, "eta_seconds": 91032.90160222055, "data_wait_seconds": 2.489545226097107} {"step": 130, "total_steps": 22439, "tokens": 1158676480, "source": "fineweb_hq", "phase": 1, "loss": 4.309021949768066, "ce_loss": 4.305400371551514, "logit_z_loss": 36.215521812438965, "muon_lr": 0.009100000000000002, "adamw_lr": 0.0005200000000000001, "grad_norm": 0.35900041460990906, "tokens_per_second": 2407092.5167736993, "eta_seconds": 82604.96656377315, "data_wait_seconds": 1.722574234008789e-05} {"step": 140, "total_steps": 22439, "tokens": 1247805440, "source": "fineweb_hq", "phase": 1, "loss": 4.20254111289978, "ce_loss": 4.198848009109497, "logit_z_loss": 36.930569648742676, "muon_lr": 0.009800000000000001, "adamw_lr": 0.0005600000000000001, "grad_norm": 0.5181800723075867, "tokens_per_second": 2475828.9904053914, "eta_seconds": 80275.60412056446, "data_wait_seconds": 1.6987323760986328e-05} {"step": 150, "total_steps": 22439, "tokens": 1336934400, "source": "fineweb_hq", "phase": 1, "loss": 4.0957911014556885, "ce_loss": 4.092004299163818, "logit_z_loss": 37.86782932281494, "muon_lr": 0.010500000000000002, "adamw_lr": 0.0006, "grad_norm": 0.560067355632782, "tokens_per_second": 7663503.481971913, "eta_seconds": 25922.8092492342, "data_wait_seconds": 0.0004285573959350586} {"step": 160, "total_steps": 22439, "tokens": 1426063360, "source": "fineweb_hq", "phase": 1, "loss": 3.9586216807365417, "ce_loss": 3.954736649990082, "logit_z_loss": 38.85059070587158, "muon_lr": 0.011200000000000002, "adamw_lr": 0.00064, "grad_norm": 0.6855910420417786, "tokens_per_second": 7677246.520032939, "eta_seconds": 25864.795335912706, "data_wait_seconds": 0.29149770736694336} {"step": 170, "total_steps": 22439, "tokens": 1515192320, "source": "fineweb_hq", "phase": 1, "loss": 3.8495513200759888, "ce_loss": 3.845552682876587, "logit_z_loss": 39.98680782318115, "muon_lr": 0.0119, "adamw_lr": 0.00068, "grad_norm": 0.7350673079490662, "tokens_per_second": 9416576.269628365, "eta_seconds": 21077.860502672196, "data_wait_seconds": 0.2970969080924988} {"step": 180, "total_steps": 22439, "tokens": 1604321280, "source": "fineweb_hq", "phase": 1, "loss": 3.7499501705169678, "ce_loss": 3.7458695769309998, "logit_z_loss": 40.8062801361084, "muon_lr": 0.012600000000000002, "adamw_lr": 0.0007199999999999999, "grad_norm": 0.8747629523277283, "tokens_per_second": 9286722.133615695, "eta_seconds": 21362.98999900818, "data_wait_seconds": 1.4424324035644531e-05} {"step": 190, "total_steps": 22439, "tokens": 1693450240, "source": "fineweb_hq", "phase": 1, "loss": 3.6615224480628967, "ce_loss": 3.657317876815796, "logit_z_loss": 42.04585933685303, "muon_lr": 0.013300000000000001, "adamw_lr": 0.00076, "grad_norm": 0.9143570065498352, "tokens_per_second": 9076120.159146408, "eta_seconds": 21848.875910282135, "data_wait_seconds": 1.6987323760986328e-05} {"step": 200, "total_steps": 22439, "tokens": 1782579200, "source": "fineweb_hq", "phase": 1, "loss": 3.5665494799613953, "ce_loss": 3.562268853187561, "logit_z_loss": 42.80591297149658, "muon_lr": 0.014000000000000002, "adamw_lr": 0.0008, "grad_norm": 0.852935254573822, "tokens_per_second": 10821530.650832502, "eta_seconds": 18316.622716283797, "data_wait_seconds": 2.4199485778808594e-05} {"step": 210, "total_steps": 22439, "tokens": 1871708160, "source": "fineweb_hq", "phase": 1, "loss": 3.4870752096176147, "ce_loss": 3.482684314250946, "logit_z_loss": 43.90891075134277, "muon_lr": 0.014700000000000001, "adamw_lr": 0.0008399999999999999, "grad_norm": 1.3818645477294922, "tokens_per_second": 8978432.522564368, "eta_seconds": 22066.743241214754, "data_wait_seconds": 1.4841556549072266e-05} {"step": 220, "total_steps": 22439, "tokens": 1960837120, "source": "fineweb_hq", "phase": 1, "loss": 3.3964741230010986, "ce_loss": 3.392018675804138, "logit_z_loss": 44.55475902557373, "muon_lr": 0.015400000000000002, "adamw_lr": 0.00088, "grad_norm": 1.1072789430618286, "tokens_per_second": 11189584.677343598, "eta_seconds": 17698.211500644684, "data_wait_seconds": 1.4662742614746094e-05} {"step": 230, "total_steps": 22439, "tokens": 2049966080, "source": "fineweb_hq", "phase": 1, "loss": 3.4376906752586365, "ce_loss": 3.4331058263778687, "logit_z_loss": 45.848862648010254, "muon_lr": 0.0161, "adamw_lr": 0.00092, "grad_norm": 1.1426341533660889, "tokens_per_second": 7749173.003144349, "eta_seconds": 25544.210612368584, "data_wait_seconds": 0.3090166449546814} {"step": 240, "total_steps": 22439, "tokens": 2139095040, "source": "fineweb_hq", "phase": 1, "loss": 3.430124819278717, "ce_loss": 3.425500750541687, "logit_z_loss": 46.24059581756592, "muon_lr": 0.016800000000000002, "adamw_lr": 0.0009599999999999999, "grad_norm": 0.7869250178337097, "tokens_per_second": 9606595.123747688, "eta_seconds": 20595.99428884983, "data_wait_seconds": 1.519918441772461e-05} {"step": 250, "total_steps": 22439, "tokens": 2228224000, "source": "fineweb_hq", "phase": 1, "loss": 3.3795212507247925, "ce_loss": 3.3748202323913574, "logit_z_loss": 47.00990009307861, "muon_lr": 0.0175, "adamw_lr": 0.001, "grad_norm": 0.7784124612808228, "tokens_per_second": 8801138.248823438, "eta_seconds": 22470.75818521976, "data_wait_seconds": 1.615285873413086e-05} {"step": 260, "total_steps": 22439, "tokens": 2317352960, "source": "fineweb_hq", "phase": 1, "loss": 3.32125061750412, "ce_loss": 3.316445231437683, "logit_z_loss": 48.05374717712402, "muon_lr": 0.018200000000000004, "adamw_lr": 0.0010400000000000001, "grad_norm": 0.7271197438240051, "tokens_per_second": 9157215.01433851, "eta_seconds": 21587.253337883947, "data_wait_seconds": 1.817941665649414e-05} {"step": 270, "total_steps": 22439, "tokens": 2406481920, "source": "fineweb_hq", "phase": 1, "loss": 3.29115754365921, "ce_loss": 3.286272943019867, "logit_z_loss": 48.84625053405762, "muon_lr": 0.018900000000000004, "adamw_lr": 0.00108, "grad_norm": 0.786897599697113, "tokens_per_second": 10203044.899523327, "eta_seconds": 19365.786720514297, "data_wait_seconds": 1.4066696166992188e-05} {"step": 280, "total_steps": 22439, "tokens": 2495610880, "source": "fineweb_hq", "phase": 1, "loss": 3.2658641934394836, "ce_loss": 3.260937750339508, "logit_z_loss": 49.26448059082031, "muon_lr": 0.019600000000000003, "adamw_lr": 0.0011200000000000001, "grad_norm": 0.6971092820167542, "tokens_per_second": 8094953.658517224, "eta_seconds": 24398.02261946201, "data_wait_seconds": 0.2794172763824463} {"step": 290, "total_steps": 22439, "tokens": 2584739840, "source": "fineweb_hq", "phase": 1, "loss": 3.262732744216919, "ce_loss": 3.257690668106079, "logit_z_loss": 50.42053508758545, "muon_lr": 0.020300000000000002, "adamw_lr": 0.00116, "grad_norm": 0.6038771867752075, "tokens_per_second": 10462282.390195543, "eta_seconds": 18868.897449088097, "data_wait_seconds": 1.4126300811767578e-05} {"step": 300, "total_steps": 22439, "tokens": 2673868800, "source": "fineweb_hq", "phase": 1, "loss": 3.2190935611724854, "ce_loss": 3.213988423347473, "logit_z_loss": 51.05208206176758, "muon_lr": 0.021000000000000005, "adamw_lr": 0.0012, "grad_norm": 0.5001488327980042, "tokens_per_second": 8691702.404163677, "eta_seconds": 22702.411491847037, "data_wait_seconds": 0.20256388187408447} {"step": 310, "total_steps": 22439, "tokens": 2762997760, "source": "fineweb_hq", "phase": 1, "loss": 3.212398886680603, "ce_loss": 3.2072192430496216, "logit_z_loss": 51.79640483856201, "muon_lr": 0.021700000000000004, "adamw_lr": 0.00124, "grad_norm": 0.5490106344223022, "tokens_per_second": 6087938.281466302, "eta_seconds": 32397.417067193983, "data_wait_seconds": 1.6748905181884766e-05} {"step": 320, "total_steps": 22439, "tokens": 2852126720, "source": "fineweb_hq", "phase": 1, "loss": 3.16773384809494, "ce_loss": 3.1624574065208435, "logit_z_loss": 52.76471710205078, "muon_lr": 0.022400000000000003, "adamw_lr": 0.00128, "grad_norm": 0.4295356869697571, "tokens_per_second": 8704049.034871731, "eta_seconds": 22649.728400444983, "data_wait_seconds": 1.627206802368164e-05} {"step": 330, "total_steps": 22439, "tokens": 2941255680, "source": "fineweb_hq", "phase": 1, "loss": 3.1672710180282593, "ce_loss": 3.161931037902832, "logit_z_loss": 53.40028476715088, "muon_lr": 0.023100000000000002, "adamw_lr": 0.00132, "grad_norm": 0.48047566413879395, "tokens_per_second": 3734990.4432077846, "eta_seconds": 52759.22941713333, "data_wait_seconds": 0.5583145022392273} {"step": 340, "total_steps": 22439, "tokens": 3030384640, "source": "fineweb_hq", "phase": 1, "loss": 3.1743375062942505, "ce_loss": 3.1689356565475464, "logit_z_loss": 54.01854991912842, "muon_lr": 0.0238, "adamw_lr": 0.00136, "grad_norm": 0.45766308903694153, "tokens_per_second": 7305521.797553259, "eta_seconds": 26961.262201690675, "data_wait_seconds": 0.2721228003501892} {"step": 350, "total_steps": 22439, "tokens": 3119513600, "source": "fineweb_hq", "phase": 1, "loss": 3.1624141335487366, "ce_loss": 3.1569427251815796, "logit_z_loss": 54.713884353637695, "muon_lr": 0.024500000000000004, "adamw_lr": 0.0014000000000000002, "grad_norm": 0.3848016858100891, "tokens_per_second": 7100108.619969086, "eta_seconds": 27728.72504940033, "data_wait_seconds": 1.245737075805664e-05} {"step": 360, "total_steps": 22439, "tokens": 3208642560, "source": "fineweb_hq", "phase": 1, "loss": 3.1361418962478638, "ce_loss": 3.1305649280548096, "logit_z_loss": 55.769742012023926, "muon_lr": 0.025200000000000004, "adamw_lr": 0.0014399999999999999, "grad_norm": 0.5501356720924377, "tokens_per_second": 5588996.4216903215, "eta_seconds": 35209.86880941391, "data_wait_seconds": 2.110004425048828e-05} {"step": 370, "total_steps": 22439, "tokens": 3297771520, "source": "fineweb_hq", "phase": 1, "loss": 3.0984156727790833, "ce_loss": 3.092725694179535, "logit_z_loss": 56.90030860900879, "muon_lr": 0.025900000000000003, "adamw_lr": 0.00148, "grad_norm": 0.5306575894355774, "tokens_per_second": 5312108.901753597, "eta_seconds": 37028.36396276951, "data_wait_seconds": 0.31781405210494995} {"step": 380, "total_steps": 22439, "tokens": 3386900480, "source": "fineweb_hq", "phase": 1, "loss": 3.0493186712265015, "ce_loss": 3.043471932411194, "logit_z_loss": 58.46726131439209, "muon_lr": 0.026600000000000002, "adamw_lr": 0.00152, "grad_norm": 0.3818303048610687, "tokens_per_second": 6136950.29388512, "eta_seconds": 32037.015691637996, "data_wait_seconds": 0.43073809146881104} {"step": 390, "total_steps": 22439, "tokens": 3476029440, "source": "fineweb_hq", "phase": 1, "loss": 2.9980337619781494, "ce_loss": 2.9921072721481323, "logit_z_loss": 59.264946937561035, "muon_lr": 0.027300000000000005, "adamw_lr": 0.00156, "grad_norm": 0.4464535713195801, "tokens_per_second": 6760350.809793864, "eta_seconds": 29069.563020205496, "data_wait_seconds": 0.42292672395706177} {"step": 400, "total_steps": 22439, "tokens": 3565158400, "source": "fineweb_hq", "phase": 1, "loss": 2.925785481929779, "ce_loss": 2.9197596311569214, "logit_z_loss": 60.25872230529785, "muon_lr": 0.028000000000000004, "adamw_lr": 0.0016, "grad_norm": 0.42003414034843445, "tokens_per_second": 4391267.891676532, "eta_seconds": 44732.254963612555, "data_wait_seconds": 0.6731599569320679} {"step": 410, "total_steps": 22439, "tokens": 3654287360, "source": "fineweb_hq", "phase": 1, "loss": 2.86074960231781, "ce_loss": 2.8545563220977783, "logit_z_loss": 61.93314456939697, "muon_lr": 0.028700000000000003, "adamw_lr": 0.0016400000000000002, "grad_norm": 0.410231351852417, "tokens_per_second": 4237398.700246017, "eta_seconds": 46335.54684684277, "data_wait_seconds": 1.6510486602783203e-05} {"step": 420, "total_steps": 22439, "tokens": 3743416320, "source": "fineweb_hq", "phase": 1, "loss": 2.8084540367126465, "ce_loss": 2.8021368384361267, "logit_z_loss": 63.17254829406738, "muon_lr": 0.029400000000000003, "adamw_lr": 0.0016799999999999999, "grad_norm": 0.3880893290042877, "tokens_per_second": 6775218.231631465, "eta_seconds": 28966.307846403124, "data_wait_seconds": 0.3164432644844055} {"step": 430, "total_steps": 22439, "tokens": 3832545280, "source": "fineweb_hq", "phase": 1, "loss": 2.7710108160972595, "ce_loss": 2.7645490169525146, "logit_z_loss": 64.61753463745117, "muon_lr": 0.030100000000000002, "adamw_lr": 0.00172, "grad_norm": 0.3648725748062134, "tokens_per_second": 9626711.265961591, "eta_seconds": 20377.044937205315, "data_wait_seconds": 0.3005521297454834} {"step": 440, "total_steps": 22439, "tokens": 3921674240, "source": "fineweb_hq", "phase": 1, "loss": 2.729283392429352, "ce_loss": 2.7226916551589966, "logit_z_loss": 65.91742897033691, "muon_lr": 0.030800000000000004, "adamw_lr": 0.00176, "grad_norm": 0.34309566020965576, "tokens_per_second": 9205855.61983161, "eta_seconds": 21298.92181684971, "data_wait_seconds": 1.5854835510253906e-05} {"step": 450, "total_steps": 22439, "tokens": 4010803200, "source": "fineweb_hq", "phase": 1, "loss": 2.684748411178589, "ce_loss": 2.6779785752296448, "logit_z_loss": 67.69777297973633, "muon_lr": 0.0315, "adamw_lr": 0.0018, "grad_norm": 0.3034548759460449, "tokens_per_second": 8553461.507916095, "eta_seconds": 22913.02415549755, "data_wait_seconds": 0.7202497720718384} {"step": 460, "total_steps": 22439, "tokens": 4099932160, "source": "fineweb_hq", "phase": 1, "loss": 2.5577516555786133, "ce_loss": 2.550634264945984, "logit_z_loss": 71.17383003234863, "muon_lr": 0.0322, "adamw_lr": 0.00184, "grad_norm": 0.28681713342666626, "tokens_per_second": 6204814.153961051, "eta_seconds": 31571.701637339593, "data_wait_seconds": 1.8358230590820312e-05} {"step": 470, "total_steps": 22439, "tokens": 4189061120, "source": "fineweb_hq", "phase": 1, "loss": 2.453768730163574, "ce_loss": 2.446514129638672, "logit_z_loss": 72.54606437683105, "muon_lr": 0.032900000000000006, "adamw_lr": 0.0018800000000000002, "grad_norm": 0.354420006275177, "tokens_per_second": 5931623.626615326, "eta_seconds": 33010.761395144465, "data_wait_seconds": 1.7344951629638672e-05} {"step": 480, "total_steps": 22439, "tokens": 4278190080, "source": "fineweb_hq", "phase": 1, "loss": 2.4016764760017395, "ce_loss": 2.3941532969474792, "logit_z_loss": 75.23196601867676, "muon_lr": 0.033600000000000005, "adamw_lr": 0.0019199999999999998, "grad_norm": 0.2954200804233551, "tokens_per_second": 6421854.307163578, "eta_seconds": 30476.911169672014, "data_wait_seconds": 0.452781617641449} {"step": 490, "total_steps": 22439, "tokens": 4367319040, "source": "fineweb_hq", "phase": 1, "loss": 2.387361526489258, "ce_loss": 2.379659116268158, "logit_z_loss": 77.02351951599121, "muon_lr": 0.034300000000000004, "adamw_lr": 0.00196, "grad_norm": 0.26878464221954346, "tokens_per_second": 8874608.668837259, "eta_seconds": 22043.693598675727, "data_wait_seconds": 3.3855438232421875e-05} {"step": 500, "total_steps": 22439, "tokens": 4456448000, "source": "fineweb_hq", "phase": 1, "loss": 2.351953089237213, "ce_loss": 2.344254434108734, "logit_z_loss": 76.98688316345215, "muon_lr": 0.035, "adamw_lr": 0.002, "grad_norm": 0.32271578907966614, "tokens_per_second": 9141830.602539133, "eta_seconds": 21389.59184932709, "data_wait_seconds": 0.00019431114196777344} {"step": 510, "total_steps": 22439, "tokens": 4545576960, "source": "fineweb_hq", "phase": 1, "loss": 2.370932877063751, "ce_loss": 2.3630858063697815, "logit_z_loss": 78.47021675109863, "muon_lr": 0.0357, "adamw_lr": 0.00204, "grad_norm": 0.33357399702072144, "tokens_per_second": 8800208.620950352, "eta_seconds": 22209.802608394624, "data_wait_seconds": 1.3589859008789062e-05} {"step": 520, "total_steps": 22439, "tokens": 4634705920, "source": "fineweb_hq", "phase": 1, "loss": 2.459707796573639, "ce_loss": 2.4521210193634033, "logit_z_loss": 75.8684310913086, "muon_lr": 0.03640000000000001, "adamw_lr": 0.0020800000000000003, "grad_norm": 0.4615185558795929, "tokens_per_second": 7705173.841703852, "eta_seconds": 25354.62163963318, "data_wait_seconds": 1.436471939086914e-05} {"step": 530, "total_steps": 22439, "tokens": 4723834880, "source": "fineweb_hq", "phase": 1, "loss": 2.5353170037269592, "ce_loss": 2.52760773897171, "logit_z_loss": 77.09314155578613, "muon_lr": 0.0371, "adamw_lr": 0.00212, "grad_norm": 0.2756792902946472, "tokens_per_second": 9547387.503115516, "eta_seconds": 20452.991815853118, "data_wait_seconds": 0.23102569580078125} {"step": 540, "total_steps": 22439, "tokens": 4812963840, "source": "fineweb_hq", "phase": 1, "loss": 2.521784484386444, "ce_loss": 2.5141079425811768, "logit_z_loss": 76.76511573791504, "muon_lr": 0.03780000000000001, "adamw_lr": 0.00216, "grad_norm": 0.18886592984199524, "tokens_per_second": 7271273.446975077, "eta_seconds": 26843.09852013588, "data_wait_seconds": 0.3465467691421509} {"step": 550, "total_steps": 22439, "tokens": 4902092800, "source": "fineweb_hq", "phase": 1, "loss": 2.5104334354400635, "ce_loss": 2.502769708633423, "logit_z_loss": 76.63683700561523, "muon_lr": 0.038500000000000006, "adamw_lr": 0.0022, "grad_norm": 0.2813076376914978, "tokens_per_second": 7425982.480560611, "eta_seconds": 26271.861138200762, "data_wait_seconds": 0.1284111738204956} {"step": 560, "total_steps": 22439, "tokens": 4991221760, "source": "fineweb_hq", "phase": 1, "loss": 2.485075056552887, "ce_loss": 2.4772602319717407, "logit_z_loss": 78.14760780334473, "muon_lr": 0.039200000000000006, "adamw_lr": 0.0022400000000000002, "grad_norm": 0.22887028753757477, "tokens_per_second": 6909855.981844515, "eta_seconds": 28221.319242596626, "data_wait_seconds": 0.46238821744918823} {"step": 570, "total_steps": 22439, "tokens": 5080350720, "source": "fineweb_hq", "phase": 1, "loss": 2.4911267161369324, "ce_loss": 2.483340859413147, "logit_z_loss": 77.85906410217285, "muon_lr": 0.039900000000000005, "adamw_lr": 0.0022800000000000003, "grad_norm": 0.227179154753685, "tokens_per_second": 7787497.403233405, "eta_seconds": 25029.365986442564, "data_wait_seconds": 1.3172626495361328e-05} {"step": 580, "total_steps": 22439, "tokens": 5169479680, "source": "fineweb_hq", "phase": 1, "loss": 2.466982662677765, "ce_loss": 2.4591829776763916, "logit_z_loss": 77.99713134765625, "muon_lr": 0.040600000000000004, "adamw_lr": 0.00232, "grad_norm": 0.2317526489496231, "tokens_per_second": 7487358.288002979, "eta_seconds": 26020.79213654995, "data_wait_seconds": 1.3768672943115234e-05} {"step": 590, "total_steps": 22439, "tokens": 5258608640, "source": "fineweb_hq", "phase": 1, "loss": 2.471463978290558, "ce_loss": 2.4635881781578064, "logit_z_loss": 78.75795936584473, "muon_lr": 0.0413, "adamw_lr": 0.0023599999999999997, "grad_norm": 0.2254444658756256, "tokens_per_second": 8296458.800079717, "eta_seconds": 23472.407854557037, "data_wait_seconds": 1.5795230865478516e-05} {"step": 600, "total_steps": 22439, "tokens": 5347737600, "source": "fineweb_hq", "phase": 1, "loss": 2.4517582058906555, "ce_loss": 2.443916440010071, "logit_z_loss": 78.41762161254883, "muon_lr": 0.04200000000000001, "adamw_lr": 0.0024, "grad_norm": 0.19819648563861847, "tokens_per_second": 6818300.184785781, "eta_seconds": 28547.985636997222, "data_wait_seconds": 0.26518261432647705} {"step": 610, "total_steps": 22439, "tokens": 5436866560, "source": "fineweb_hq", "phase": 1, "loss": 2.4580911993980408, "ce_loss": 2.4501355290412903, "logit_z_loss": 79.55681991577148, "muon_lr": 0.0427, "adamw_lr": 0.00244, "grad_norm": 0.23898088932037354, "tokens_per_second": 7027915.462642427, "eta_seconds": 27683.82855744362, "data_wait_seconds": 0.28087741136550903} {"step": 620, "total_steps": 22439, "tokens": 5525995520, "source": "fineweb_hq", "phase": 1, "loss": 2.4332305788993835, "ce_loss": 2.4252651929855347, "logit_z_loss": 79.6538200378418, "muon_lr": 0.04340000000000001, "adamw_lr": 0.00248, "grad_norm": 0.2116815149784088, "tokens_per_second": 6712336.335789734, "eta_seconds": 28972.09974224567, "data_wait_seconds": 0.34881824254989624} {"step": 630, "total_steps": 22439, "tokens": 5615124480, "source": "fineweb_hq", "phase": 1, "loss": 2.3960554599761963, "ce_loss": 2.3879873156547546, "logit_z_loss": 80.68179702758789, "muon_lr": 0.0441, "adamw_lr": 0.00252, "grad_norm": 0.1983681470155716, "tokens_per_second": 9203690.473776149, "eta_seconds": 21119.935466957093, "data_wait_seconds": 1.3589859008789062e-05} {"step": 640, "total_steps": 22439, "tokens": 5704253440, "source": "fineweb_hq", "phase": 1, "loss": 2.3983024954795837, "ce_loss": 2.390074670314789, "logit_z_loss": 82.27853965759277, "muon_lr": 0.044800000000000006, "adamw_lr": 0.00256, "grad_norm": 0.1874842494726181, "tokens_per_second": 7166536.72879459, "eta_seconds": 27111.03385870457, "data_wait_seconds": 0.7625116109848022} {"step": 650, "total_steps": 22439, "tokens": 5793382400, "source": "fineweb_hq", "phase": 1, "loss": 2.396180212497711, "ce_loss": 2.3880707025527954, "logit_z_loss": 81.0950698852539, "muon_lr": 0.045500000000000006, "adamw_lr": 0.0026, "grad_norm": 0.20300427079200745, "tokens_per_second": 9557785.073881257, "eta_seconds": 20318.838459205628, "data_wait_seconds": 1.2983060479164124} {"step": 660, "total_steps": 22439, "tokens": 5882511360, "source": "fineweb_hq", "phase": 1, "loss": 2.3795944452285767, "ce_loss": 2.3716355562210083, "logit_z_loss": 79.58875274658203, "muon_lr": 0.046200000000000005, "adamw_lr": 0.00264, "grad_norm": 0.20361796021461487, "tokens_per_second": 7950054.236303745, "eta_seconds": 24416.683989095687, "data_wait_seconds": 1.5437602996826172e-05} {"step": 670, "total_steps": 22439, "tokens": 5971640320, "source": "fineweb_hq", "phase": 1, "loss": 2.3759934306144714, "ce_loss": 2.367850661277771, "logit_z_loss": 81.42828941345215, "muon_lr": 0.046900000000000004, "adamw_lr": 0.00268, "grad_norm": 0.18410010635852814, "tokens_per_second": 8104376.304865796, "eta_seconds": 23940.748272943496, "data_wait_seconds": 1.6987323760986328e-05} {"step": 680, "total_steps": 22439, "tokens": 6060769280, "source": "fineweb_hq", "phase": 1, "loss": 2.370010197162628, "ce_loss": 2.3618654012680054, "logit_z_loss": 81.44764518737793, "muon_lr": 0.0476, "adamw_lr": 0.00272, "grad_norm": 0.23240381479263306, "tokens_per_second": 6333958.580314357, "eta_seconds": 30618.404210400582, "data_wait_seconds": 0.3833252787590027} {"step": 690, "total_steps": 22439, "tokens": 6149898240, "source": "fineweb_hq", "phase": 1, "loss": 2.393221378326416, "ce_loss": 2.385291337966919, "logit_z_loss": 79.30001449584961, "muon_lr": 0.0483, "adamw_lr": 0.0027600000000000003, "grad_norm": 0.2510574460029602, "tokens_per_second": 7164714.090987016, "eta_seconds": 27055.73071615696, "data_wait_seconds": 1.8715858459472656e-05} {"step": 700, "total_steps": 22439, "tokens": 6239027200, "source": "fineweb_hq", "phase": 1, "loss": 2.328338325023651, "ce_loss": 2.320348381996155, "logit_z_loss": 79.8990478515625, "muon_lr": 0.04900000000000001, "adamw_lr": 0.0028000000000000004, "grad_norm": 0.1862829178571701, "tokens_per_second": 7604268.968707431, "eta_seconds": 25480.08847942352, "data_wait_seconds": 1.3887882232666016e-05} {"step": 710, "total_steps": 22439, "tokens": 6328156160, "source": "fineweb_hq", "phase": 1, "loss": 2.3147504925727844, "ce_loss": 2.306523859500885, "logit_z_loss": 82.26664924621582, "muon_lr": 0.0497, "adamw_lr": 0.0028399999999999996, "grad_norm": 0.2060781866312027, "tokens_per_second": 8560163.437189277, "eta_seconds": 22624.371439290047, "data_wait_seconds": 0.3879215717315674} {"step": 720, "total_steps": 22439, "tokens": 6417285120, "source": "fineweb_hq", "phase": 1, "loss": 2.332974135875702, "ce_loss": 2.3249324560165405, "logit_z_loss": 80.41722297668457, "muon_lr": 0.05040000000000001, "adamw_lr": 0.0028799999999999997, "grad_norm": 0.23572801053524017, "tokens_per_second": 10912151.829293167, "eta_seconds": 17739.781415462494, "data_wait_seconds": 1.5556812286376953e-05} {"step": 730, "total_steps": 22439, "tokens": 6506414080, "source": "fineweb_hq", "phase": 1, "loss": 2.330069839954376, "ce_loss": 2.321860134601593, "logit_z_loss": 82.09696006774902, "muon_lr": 0.0511, "adamw_lr": 0.00292, "grad_norm": 0.26685255765914917, "tokens_per_second": 9020825.559421727, "eta_seconds": 21449.262929368022, "data_wait_seconds": 1.6987323760986328e-05} {"step": 740, "total_steps": 22439, "tokens": 6595543040, "source": "fineweb_hq", "phase": 1, "loss": 2.299080550670624, "ce_loss": 2.290955424308777, "logit_z_loss": 81.25156021118164, "muon_lr": 0.051800000000000006, "adamw_lr": 0.00296, "grad_norm": 0.20033298432826996, "tokens_per_second": 9869975.372023484, "eta_seconds": 19594.87465918064, "data_wait_seconds": 1.3828277587890625e-05} {"step": 750, "total_steps": 22439, "tokens": 6684672000, "source": "fineweb_hq", "phase": 1, "loss": 2.305118501186371, "ce_loss": 2.297184705734253, "logit_z_loss": 79.33795356750488, "muon_lr": 0.052500000000000005, "adamw_lr": 0.003, "grad_norm": 0.23620666563510895, "tokens_per_second": 7993148.869520959, "eta_seconds": 24184.686723542214, "data_wait_seconds": 0.653160035610199} {"step": 760, "total_steps": 22439, "tokens": 6773800960, "source": "fineweb_hq", "phase": 1, "loss": 2.3622615337371826, "ce_loss": 2.354522705078125, "logit_z_loss": 77.3880786895752, "muon_lr": 0.053200000000000004, "adamw_lr": 0.00304, "grad_norm": 0.19219592213630676, "tokens_per_second": 8174759.375875979, "eta_seconds": 23636.496623277664, "data_wait_seconds": 0.33434557914733887} {"step": 770, "total_steps": 22439, "tokens": 6862929920, "source": "fineweb_hq", "phase": 1, "loss": 2.383073151111603, "ce_loss": 2.3752957582473755, "logit_z_loss": 77.77359580993652, "muon_lr": 0.0539, "adamw_lr": 0.0030800000000000003, "grad_norm": 0.22470791637897491, "tokens_per_second": 7493282.985046385, "eta_seconds": 25774.22256832123, "data_wait_seconds": 1.4543533325195312e-05} {"step": 780, "total_steps": 22439, "tokens": 6952058880, "source": "fineweb_hq", "phase": 1, "loss": 2.3486892580986023, "ce_loss": 2.340909242630005, "logit_z_loss": 77.80061531066895, "muon_lr": 0.05460000000000001, "adamw_lr": 0.00312, "grad_norm": 0.19442570209503174, "tokens_per_second": 7974212.17532066, "eta_seconds": 24208.587659788132, "data_wait_seconds": 1.6629695892333984e-05} {"step": 790, "total_steps": 22439, "tokens": 7041187840, "source": "fineweb_hq", "phase": 1, "loss": 2.3511235117912292, "ce_loss": 2.3434258103370667, "logit_z_loss": 76.97773361206055, "muon_lr": 0.0553, "adamw_lr": 0.00316, "grad_norm": 0.18331126868724823, "tokens_per_second": 8197510.245438312, "eta_seconds": 23538.279273438453, "data_wait_seconds": 1.627206802368164e-05} {"step": 800, "total_steps": 22439, "tokens": 7130316800, "source": "fineweb_hq", "phase": 1, "loss": 2.343844771385193, "ce_loss": 2.3361929059028625, "logit_z_loss": 76.51930809020996, "muon_lr": 0.05600000000000001, "adamw_lr": 0.0032, "grad_norm": 0.1974499672651291, "tokens_per_second": 7005134.072868889, "eta_seconds": 27532.114951372147, "data_wait_seconds": 0.3746710419654846} {"step": 810, "total_steps": 22439, "tokens": 7219445760, "source": "fineweb_hq", "phase": 1, "loss": 2.2092705368995667, "ce_loss": 2.201336443424225, "logit_z_loss": 79.34107208251953, "muon_lr": 0.0567, "adamw_lr": 0.0032400000000000003, "grad_norm": 0.1958804875612259, "tokens_per_second": 7538323.863033231, "eta_seconds": 25572.92988290787, "data_wait_seconds": 0.8902894258499146} {"step": 820, "total_steps": 22439, "tokens": 7308574720, "source": "fineweb_hq", "phase": 1, "loss": 2.1729026436805725, "ce_loss": 2.16474711894989, "logit_z_loss": 81.55514907836914, "muon_lr": 0.05740000000000001, "adamw_lr": 0.0032800000000000004, "grad_norm": 0.23285837471485138, "tokens_per_second": 9451195.882156769, "eta_seconds": 20387.673795628547, "data_wait_seconds": 0.31566721200942993} {"step": 830, "total_steps": 22439, "tokens": 7397703680, "source": "fineweb_hq", "phase": 1, "loss": 2.153770089149475, "ce_loss": 2.145902693271637, "logit_z_loss": 78.67469024658203, "muon_lr": 0.058100000000000006, "adamw_lr": 0.0033200000000000005, "grad_norm": 0.1934303492307663, "tokens_per_second": 9319240.540504752, "eta_seconds": 20666.788117218017, "data_wait_seconds": 1.6450881958007812e-05} {"step": 840, "total_steps": 22439, "tokens": 7486832640, "source": "fineweb_hq", "phase": 1, "loss": 2.1568243503570557, "ce_loss": 2.148854672908783, "logit_z_loss": 79.69684410095215, "muon_lr": 0.058800000000000005, "adamw_lr": 0.0033599999999999997, "grad_norm": 0.19662460684776306, "tokens_per_second": 9581271.945798812, "eta_seconds": 20092.284384894374, "data_wait_seconds": 1.3232231140136719e-05} {"step": 850, "total_steps": 22439, "tokens": 7575961600, "source": "fineweb_hq", "phase": 1, "loss": 2.152070641517639, "ce_loss": 2.1442551612854004, "logit_z_loss": 78.15550422668457, "muon_lr": 0.059500000000000004, "adamw_lr": 0.0034, "grad_norm": 0.18207232654094696, "tokens_per_second": 9762642.39925466, "eta_seconds": 19709.8801609993, "data_wait_seconds": 1.4126300811767578e-05} {"step": 860, "total_steps": 22439, "tokens": 7665090560, "source": "fineweb_hq", "phase": 1, "loss": 2.145963132381439, "ce_loss": 2.137876272201538, "logit_z_loss": 80.86890602111816, "muon_lr": 0.060200000000000004, "adamw_lr": 0.00344, "grad_norm": 0.1876753568649292, "tokens_per_second": 9893073.30349838, "eta_seconds": 19441.014625453947, "data_wait_seconds": 1.537799835205078e-05} {"step": 870, "total_steps": 22439, "tokens": 7754219520, "source": "fineweb_hq", "phase": 1, "loss": 2.145168960094452, "ce_loss": 2.137241542339325, "logit_z_loss": 79.27460289001465, "muon_lr": 0.0609, "adamw_lr": 0.00348, "grad_norm": 0.221941277384758, "tokens_per_second": 8483347.529066838, "eta_seconds": 22661.131489109994, "data_wait_seconds": 1.5079975128173828e-05} {"step": 880, "total_steps": 22439, "tokens": 7843348480, "source": "fineweb_hq", "phase": 1, "loss": 2.1310052275657654, "ce_loss": 2.123206377029419, "logit_z_loss": 77.9881420135498, "muon_lr": 0.06160000000000001, "adamw_lr": 0.00352, "grad_norm": 0.17409531772136688, "tokens_per_second": 8918937.64257767, "eta_seconds": 21544.396044063567, "data_wait_seconds": 1.329183578491211e-05} {"step": 890, "total_steps": 22439, "tokens": 7932477440, "source": "fineweb_hq", "phase": 1, "loss": 2.1497772932052612, "ce_loss": 2.1419413089752197, "logit_z_loss": 78.36023139953613, "muon_lr": 0.0623, "adamw_lr": 0.0035600000000000002, "grad_norm": 0.22990204393863678, "tokens_per_second": 9922804.604194226, "eta_seconds": 19355.817590403556, "data_wait_seconds": 1.5676021575927734e-05} {"step": 900, "total_steps": 22439, "tokens": 8021606400, "source": "fineweb_hq", "phase": 1, "loss": 2.128612518310547, "ce_loss": 2.120979964733124, "logit_z_loss": 76.3257942199707, "muon_lr": 0.063, "adamw_lr": 0.0036, "grad_norm": 0.18078908324241638, "tokens_per_second": 9650671.570589593, "eta_seconds": 19892.384228372575, "data_wait_seconds": 0.051418960094451904} {"step": 910, "total_steps": 22439, "tokens": 8110735360, "source": "fineweb_hq", "phase": 1, "loss": 2.3088300824165344, "ce_loss": 2.301823318004608, "logit_z_loss": 70.06817817687988, "muon_lr": 0.0637, "adamw_lr": 0.00364, "grad_norm": 0.2104783058166504, "tokens_per_second": 7219887.872922974, "eta_seconds": 26577.384768486023, "data_wait_seconds": 0.29506224393844604} {"step": 920, "total_steps": 22439, "tokens": 8199864320, "source": "fineweb_hq", "phase": 1, "loss": 2.3767300248146057, "ce_loss": 2.3701910972595215, "logit_z_loss": 65.3893928527832, "muon_lr": 0.0644, "adamw_lr": 0.00368, "grad_norm": 0.23128600418567657, "tokens_per_second": 9192341.784089683, "eta_seconds": 20864.82569174767, "data_wait_seconds": 1.3172626495361328e-05} {"step": 930, "total_steps": 22439, "tokens": 8288993280, "source": "fineweb_hq", "phase": 1, "loss": 2.3693774342536926, "ce_loss": 2.362643301486969, "logit_z_loss": 67.34131240844727, "muon_lr": 0.0651, "adamw_lr": 0.00372, "grad_norm": 0.2287091165781021, "tokens_per_second": 10073121.40196061, "eta_seconds": 19031.586378645898, "data_wait_seconds": 1.4781951904296875e-05} {"step": 940, "total_steps": 22439, "tokens": 8378122240, "source": "fineweb_hq", "phase": 1, "loss": 2.3465049266815186, "ce_loss": 2.340116858482361, "logit_z_loss": 63.88089084625244, "muon_lr": 0.06580000000000001, "adamw_lr": 0.0037600000000000003, "grad_norm": 0.22197671234607697, "tokens_per_second": 8754935.55516695, "eta_seconds": 21886.894528985023, "data_wait_seconds": 1.341104507446289e-05} {"step": 950, "total_steps": 22439, "tokens": 8467251200, "source": "fineweb_hq", "phase": 1, "loss": 2.33204847574234, "ce_loss": 2.3254379630088806, "logit_z_loss": 66.10550880432129, "muon_lr": 0.0665, "adamw_lr": 0.0038000000000000004, "grad_norm": 0.18201303482055664, "tokens_per_second": 8971161.761053331, "eta_seconds": 21349.433578991888, "data_wait_seconds": 0.00030362606048583984} {"step": 960, "total_steps": 22439, "tokens": 8556380160, "source": "fineweb_hq", "phase": 1, "loss": 2.350585162639618, "ce_loss": 2.3441357016563416, "logit_z_loss": 64.49478530883789, "muon_lr": 0.06720000000000001, "adamw_lr": 0.0038399999999999997, "grad_norm": 0.2307051122188568, "tokens_per_second": 8768643.45441727, "eta_seconds": 21832.350029873847, "data_wait_seconds": 1.8477439880371094e-05} {"step": 970, "total_steps": 22439, "tokens": 8645509120, "source": "fineweb_hq", "phase": 1, "loss": 2.3355281949043274, "ce_loss": 2.328825294971466, "logit_z_loss": 67.02908897399902, "muon_lr": 0.0679, "adamw_lr": 0.0038799999999999998, "grad_norm": 0.21734148263931274, "tokens_per_second": 7220713.442206703, "eta_seconds": 26500.285014152527, "data_wait_seconds": 0.25003528594970703} {"step": 980, "total_steps": 22439, "tokens": 8734638080, "source": "fineweb_hq", "phase": 1, "loss": 2.3283920288085938, "ce_loss": 2.3219318985939026, "logit_z_loss": 64.60088920593262, "muon_lr": 0.06860000000000001, "adamw_lr": 0.00392, "grad_norm": 0.20072227716445923, "tokens_per_second": 9270987.236583356, "eta_seconds": 20630.14761893749, "data_wait_seconds": 1.245737075805664e-05} {"step": 990, "total_steps": 22439, "tokens": 8823767040, "source": "fineweb_hq", "phase": 1, "loss": 2.323706567287445, "ce_loss": 2.317197024822235, "logit_z_loss": 65.09517860412598, "muon_lr": 0.06930000000000001, "adamw_lr": 0.00396, "grad_norm": 0.18527741730213165, "tokens_per_second": 9336268.191085013, "eta_seconds": 20476.351192069054, "data_wait_seconds": 1.3947486877441406e-05} {"step": 1000, "total_steps": 22439, "tokens": 8912896000, "source": "fineweb_hq", "phase": 1, "loss": 2.3358243703842163, "ce_loss": 2.329273998737335, "logit_z_loss": 65.50436592102051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23283950984477997, "tokens_per_second": 9433630.894132858, "eta_seconds": 20255.570679879187, "data_wait_seconds": 1.5676021575927734e-05} {"step": 1010, "total_steps": 22439, "tokens": 9002024960, "source": "fineweb_hq", "phase": 1, "loss": 2.315945625305176, "ce_loss": 2.309797704219818, "logit_z_loss": 61.47883129119873, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20814353227615356, "tokens_per_second": 9852860.27603847, "eta_seconds": 19384.67034273148, "data_wait_seconds": 0.22886061668395996} {"step": 1020, "total_steps": 22439, "tokens": 9091153920, "source": "fineweb_hq", "phase": 1, "loss": 2.3088624477386475, "ce_loss": 2.30258309841156, "logit_z_loss": 62.792927742004395, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21581503748893738, "tokens_per_second": 8651330.612411598, "eta_seconds": 22066.5846650362, "data_wait_seconds": 1.806020736694336e-05} {"step": 1030, "total_steps": 22439, "tokens": 9180282880, "source": "fineweb_hq", "phase": 1, "loss": 2.2938343286514282, "ce_loss": 2.2875046133995056, "logit_z_loss": 63.2970085144043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2105294018983841, "tokens_per_second": 9340256.124235211, "eta_seconds": 20429.438756918906, "data_wait_seconds": 0.26373594999313354} {"step": 1040, "total_steps": 22439, "tokens": 9269411840, "source": "fineweb_hq", "phase": 1, "loss": 2.291613817214966, "ce_loss": 2.2854092717170715, "logit_z_loss": 62.04541778564453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21177281439304352, "tokens_per_second": 9291618.76773903, "eta_seconds": 20526.78508143425, "data_wait_seconds": 1.3887882232666016e-05} {"step": 1050, "total_steps": 22439, "tokens": 9358540800, "source": "fineweb_hq", "phase": 1, "loss": 2.2960025668144226, "ce_loss": 2.289924383163452, "logit_z_loss": 60.78238868713379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1940109133720398, "tokens_per_second": 9229805.947100338, "eta_seconds": 20654.59811794758, "data_wait_seconds": 1.6927719116210938e-05} {"step": 1060, "total_steps": 22439, "tokens": 9447669760, "source": "fineweb_hq", "phase": 1, "loss": 2.2542683482170105, "ce_loss": 2.2478742003440857, "logit_z_loss": 63.94139099121094, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21360020339488983, "tokens_per_second": 7268330.627052976, "eta_seconds": 26216.309268426896, "data_wait_seconds": 1.4007091522216797e-05} {"step": 1070, "total_steps": 22439, "tokens": 9536798720, "source": "fineweb_hq", "phase": 1, "loss": 2.226654887199402, "ce_loss": 2.220464825630188, "logit_z_loss": 61.90073108673096, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18968330323696136, "tokens_per_second": 9982306.738514233, "eta_seconds": 19079.72572002411, "data_wait_seconds": 1.424551010131836e-05} {"step": 1080, "total_steps": 22439, "tokens": 9625927680, "source": "fineweb_hq", "phase": 1, "loss": 2.2515273690223694, "ce_loss": 2.2451473474502563, "logit_z_loss": 63.80070877075195, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2117748260498047, "tokens_per_second": 9098439.298023513, "eta_seconds": 20923.428670382502, "data_wait_seconds": 0.24623018503189087} {"step": 1090, "total_steps": 22439, "tokens": 9715056640, "source": "fineweb_hq", "phase": 1, "loss": 2.213638424873352, "ce_loss": 2.207147002220154, "logit_z_loss": 64.91473197937012, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20987659692764282, "tokens_per_second": 9320515.442111455, "eta_seconds": 20415.331950879096, "data_wait_seconds": 0.277202308177948} {"step": 1100, "total_steps": 22439, "tokens": 9804185600, "source": "fineweb_hq", "phase": 1, "loss": 2.1991316080093384, "ce_loss": 2.1925421953201294, "logit_z_loss": 65.89375495910645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19404654204845428, "tokens_per_second": 9263205.526926557, "eta_seconds": 20532.01639444828, "data_wait_seconds": 1.4960765838623047e-05} {"step": 1110, "total_steps": 22439, "tokens": 9893314560, "source": "fineweb_hq", "phase": 1, "loss": 2.1957609057426453, "ce_loss": 2.1894816160202026, "logit_z_loss": 62.79327964782715, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18220849335193634, "tokens_per_second": 8321119.599639584, "eta_seconds": 22845.863048553467, "data_wait_seconds": 1.722574234008789e-05} {"step": 1120, "total_steps": 22439, "tokens": 9982443520, "source": "fineweb_hq", "phase": 1, "loss": 2.1929144859313965, "ce_loss": 2.1866838335990906, "logit_z_loss": 62.306596755981445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16241706907749176, "tokens_per_second": 10415627.523396535, "eta_seconds": 18243.16676044464, "data_wait_seconds": 1.4126300811767578e-05} {"step": 1130, "total_steps": 22439, "tokens": 10071572480, "source": "fineweb_hq", "phase": 1, "loss": 2.1921173334121704, "ce_loss": 2.18603253364563, "logit_z_loss": 60.84793949127197, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20235379040241241, "tokens_per_second": 10827755.012398869, "eta_seconds": 17540.561330258846, "data_wait_seconds": 0.553187906742096} {"step": 1140, "total_steps": 22439, "tokens": 10160701440, "source": "fineweb_hq", "phase": 1, "loss": 2.201793372631073, "ce_loss": 2.195651352405548, "logit_z_loss": 61.42008590698242, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24805955588817596, "tokens_per_second": 9187007.316986762, "eta_seconds": 20663.50502986908, "data_wait_seconds": 1.33514404296875e-05} {"step": 1150, "total_steps": 22439, "tokens": 10249830400, "source": "fineweb_hq", "phase": 1, "loss": 2.1848737597465515, "ce_loss": 2.178762972354889, "logit_z_loss": 61.10784149169922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1915677934885025, "tokens_per_second": 8017549.878793077, "eta_seconds": 23666.412534070016, "data_wait_seconds": 0.734839141368866} {"step": 1160, "total_steps": 22439, "tokens": 10338959360, "source": "fineweb_hq", "phase": 1, "loss": 2.2128114104270935, "ce_loss": 2.207035720348358, "logit_z_loss": 57.75673198699951, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1836061328649521, "tokens_per_second": 8607512.94512555, "eta_seconds": 22033.95047943592, "data_wait_seconds": 0.26971113681793213} {"step": 1170, "total_steps": 22439, "tokens": 10428088320, "source": "fineweb_hq", "phase": 1, "loss": 2.2115935683250427, "ce_loss": 2.2059048414230347, "logit_z_loss": 56.88769340515137, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21005618572235107, "tokens_per_second": 8601990.621824866, "eta_seconds": 22037.734445214275, "data_wait_seconds": 1.4543533325195312e-05} {"step": 1180, "total_steps": 22439, "tokens": 10517217280, "source": "fineweb_hq", "phase": 1, "loss": 2.2108685970306396, "ce_loss": 2.205065965652466, "logit_z_loss": 58.0264949798584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2048349231481552, "tokens_per_second": 6527352.306947386, "eta_seconds": 29028.501474070552, "data_wait_seconds": 0.40934544801712036} {"step": 1190, "total_steps": 22439, "tokens": 10606346240, "source": "fineweb_hq", "phase": 1, "loss": 2.1958491802215576, "ce_loss": 2.1902396082878113, "logit_z_loss": 56.09574317932129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21773114800453186, "tokens_per_second": 6065309.458343724, "eta_seconds": 31225.13837170601, "data_wait_seconds": 1.7881393432617188e-05} {"step": 1200, "total_steps": 22439, "tokens": 10695475200, "source": "fineweb_hq", "phase": 1, "loss": 2.194515645503998, "ce_loss": 2.188836455345154, "logit_z_loss": 56.79174995422363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21552665531635284, "tokens_per_second": 5643336.389543482, "eta_seconds": 33544.16343047619, "data_wait_seconds": 0.420016348361969} {"step": 1210, "total_steps": 22439, "tokens": 10784604160, "source": "fineweb_hq", "phase": 1, "loss": 2.1866493225097656, "ce_loss": 2.180506944656372, "logit_z_loss": 61.42391777038574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1618250459432602, "tokens_per_second": 6509909.2427951405, "eta_seconds": 29065.208457922934, "data_wait_seconds": 1.6391277313232422e-05} {"step": 1220, "total_steps": 22439, "tokens": 10873733120, "source": "fineweb_hq", "phase": 1, "loss": 2.1837894320487976, "ce_loss": 2.1780731678009033, "logit_z_loss": 57.16245174407959, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17903585731983185, "tokens_per_second": 5785274.650759153, "eta_seconds": 32690.365045881274, "data_wait_seconds": 0.4803680181503296} {"step": 1230, "total_steps": 22439, "tokens": 10962862080, "source": "fineweb_hq", "phase": 1, "loss": 2.186292052268982, "ce_loss": 2.1805285215377808, "logit_z_loss": 57.635008811950684, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1786961406469345, "tokens_per_second": 3934933.9499942474, "eta_seconds": 48039.84353137016, "data_wait_seconds": 2.0444393157958984e-05} {"step": 1240, "total_steps": 22439, "tokens": 11051991040, "source": "fineweb_hq", "phase": 1, "loss": 2.1740596890449524, "ce_loss": 2.168077290058136, "logit_z_loss": 59.823829650878906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18215879797935486, "tokens_per_second": 5501526.033626959, "eta_seconds": 34344.01312456131, "data_wait_seconds": 0.4658889174461365} {"step": 1250, "total_steps": 22439, "tokens": 11141120000, "source": "fineweb_hq", "phase": 1, "loss": 2.177476644515991, "ce_loss": 2.1721092462539673, "logit_z_loss": 53.67388725280762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17663264274597168, "tokens_per_second": 7093314.637192832, "eta_seconds": 26624.415101194383, "data_wait_seconds": 0.838799238204956} {"step": 1260, "total_steps": 22439, "tokens": 11230248960, "source": "fineweb_hq", "phase": 1, "loss": 2.1736501455307007, "ce_loss": 2.1680175065994263, "logit_z_loss": 56.326937675476074, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18713848292827606, "tokens_per_second": 9275076.2939427, "eta_seconds": 20351.9861618042, "data_wait_seconds": 1.7344951629638672e-05} {"step": 1270, "total_steps": 22439, "tokens": 11319377920, "source": "fineweb_hq", "phase": 1, "loss": 2.171439290046692, "ce_loss": 2.1658676862716675, "logit_z_loss": 55.71616077423096, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17681118845939636, "tokens_per_second": 10163876.216749635, "eta_seconds": 18563.497960853576, "data_wait_seconds": 1.5556812286376953e-05} {"step": 1280, "total_steps": 22439, "tokens": 11408506880, "source": "fineweb_hq", "phase": 1, "loss": 2.172498881816864, "ce_loss": 2.1671526432037354, "logit_z_loss": 53.46236991882324, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21558675169944763, "tokens_per_second": 7872081.107580812, "eta_seconds": 23956.557851314545, "data_wait_seconds": 1.52587890625e-05} {"step": 1290, "total_steps": 22439, "tokens": 11497635840, "source": "fineweb_hq", "phase": 1, "loss": 2.182535409927368, "ce_loss": 2.1769255995750427, "logit_z_loss": 56.098440170288086, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19773919880390167, "tokens_per_second": 9128997.265697043, "eta_seconds": 20648.361700391768, "data_wait_seconds": 1.3768672943115234e-05} {"step": 1300, "total_steps": 22439, "tokens": 11586764800, "source": "fineweb_hq", "phase": 1, "loss": 2.1767271161079407, "ce_loss": 2.1712238788604736, "logit_z_loss": 55.032203674316406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21685725450515747, "tokens_per_second": 9063967.381502723, "eta_seconds": 20786.67106950283, "data_wait_seconds": 1.7762184143066406e-05} {"step": 1310, "total_steps": 22439, "tokens": 11675893760, "source": "fineweb_hq", "phase": 1, "loss": 2.1603753566741943, "ce_loss": 2.155220150947571, "logit_z_loss": 51.55232048034668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1842598021030426, "tokens_per_second": 9861225.835400911, "eta_seconds": 19097.07603571415, "data_wait_seconds": 1.33514404296875e-05} {"step": 1320, "total_steps": 22439, "tokens": 11765022720, "source": "fineweb_hq", "phase": 1, "loss": 2.1079850792884827, "ce_loss": 2.102415084838867, "logit_z_loss": 55.700544357299805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17595218122005463, "tokens_per_second": 6900867.509486216, "eta_seconds": 27276.491015839576, "data_wait_seconds": 0.3082209825515747} {"step": 1330, "total_steps": 22439, "tokens": 11854151680, "source": "fineweb_hq", "phase": 1, "loss": 2.098674774169922, "ce_loss": 2.092881441116333, "logit_z_loss": 57.933040618896484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18926651775836945, "tokens_per_second": 10164078.776251659, "eta_seconds": 18510.513919234276, "data_wait_seconds": 0.20438069105148315} {"step": 1340, "total_steps": 22439, "tokens": 11943280640, "source": "fineweb_hq", "phase": 1, "loss": 2.0978167057037354, "ce_loss": 2.0922529101371765, "logit_z_loss": 55.63784980773926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1748604029417038, "tokens_per_second": 9311522.142505705, "eta_seconds": 20195.75208284855, "data_wait_seconds": 1.4066696166992188e-05} {"step": 1350, "total_steps": 22439, "tokens": 12032409600, "source": "fineweb_hq", "phase": 1, "loss": 2.088294208049774, "ce_loss": 2.082521080970764, "logit_z_loss": 57.730990409851074, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19150473177433014, "tokens_per_second": 9295863.583229437, "eta_seconds": 20220.18310198784, "data_wait_seconds": 1.4185905456542969e-05} {"step": 1360, "total_steps": 22439, "tokens": 12121538560, "source": "fineweb_hq", "phase": 1, "loss": 2.0781739950180054, "ce_loss": 2.0726250410079956, "logit_z_loss": 55.48923397064209, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17205914855003357, "tokens_per_second": 8457849.682816232, "eta_seconds": 22213.085101962086, "data_wait_seconds": 0.056102633476257324} {"step": 1370, "total_steps": 22439, "tokens": 12210667520, "source": "fineweb_hq", "phase": 1, "loss": 2.065874397754669, "ce_loss": 2.0603575110435486, "logit_z_loss": 55.16893196105957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1729859560728073, "tokens_per_second": 9531101.034462433, "eta_seconds": 19702.425264930724, "data_wait_seconds": 0.35638147592544556} {"step": 1380, "total_steps": 22439, "tokens": 12299796480, "source": "fineweb_hq", "phase": 1, "loss": 2.0683966279029846, "ce_loss": 2.0629679560661316, "logit_z_loss": 54.28699493408203, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17686040699481964, "tokens_per_second": 9088862.167204509, "eta_seconds": 20651.284331417086, "data_wait_seconds": 0.3025711178779602} {"step": 1390, "total_steps": 22439, "tokens": 12388925440, "source": "fineweb_hq", "phase": 1, "loss": 2.060248374938965, "ce_loss": 2.055089592933655, "logit_z_loss": 51.58818531036377, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19178014993667603, "tokens_per_second": 9378649.0197791, "eta_seconds": 20003.68576629162, "data_wait_seconds": 1.5735626220703125e-05} {"step": 1400, "total_steps": 22439, "tokens": 12478054400, "source": "fineweb_hq", "phase": 1, "loss": 2.0516480207443237, "ce_loss": 2.0463549494743347, "logit_z_loss": 52.930710792541504, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19199952483177185, "tokens_per_second": 9534900.891662834, "eta_seconds": 19666.53047311306, "data_wait_seconds": 0.03774505853652954} {"step": 1410, "total_steps": 22439, "tokens": 12567183360, "source": "fineweb_hq", "phase": 1, "loss": 2.082814395427704, "ce_loss": 2.077356278896332, "logit_z_loss": 54.580986976623535, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19560787081718445, "tokens_per_second": 7411146.157204641, "eta_seconds": 25290.189399623872, "data_wait_seconds": 0.21239382028579712} {"step": 1420, "total_steps": 22439, "tokens": 12656312320, "source": "fineweb_hq", "phase": 1, "loss": 2.140061616897583, "ce_loss": 2.1349568963050842, "logit_z_loss": 51.04781723022461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17775961756706238, "tokens_per_second": 8078483.430020843, "eta_seconds": 23190.016127014158, "data_wait_seconds": 1.4603137969970703e-05} {"step": 1430, "total_steps": 22439, "tokens": 12745441280, "source": "fineweb_hq", "phase": 1, "loss": 2.134713590145111, "ce_loss": 2.1295687556266785, "logit_z_loss": 51.44787120819092, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16385625302791595, "tokens_per_second": 7835420.998543558, "eta_seconds": 23898.018000411987, "data_wait_seconds": 1.8298625946044922e-05} {"step": 1440, "total_steps": 22439, "tokens": 12834570240, "source": "fineweb_hq", "phase": 1, "loss": 2.142542004585266, "ce_loss": 2.137802541255951, "logit_z_loss": 47.3944206237793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17602215707302094, "tokens_per_second": 9120821.746139593, "eta_seconds": 20520.28954334259, "data_wait_seconds": 0.22306346893310547} {"step": 1450, "total_steps": 22439, "tokens": 12923699200, "source": "fineweb_hq", "phase": 1, "loss": 2.1314090490341187, "ce_loss": 2.1264910101890564, "logit_z_loss": 49.18070030212402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1731693297624588, "tokens_per_second": 7504608.369476812, "eta_seconds": 24927.719733500482, "data_wait_seconds": 0.25221914052963257} {"step": 1460, "total_steps": 22439, "tokens": 13012828160, "source": "fineweb_hq", "phase": 1, "loss": 2.1087422966957092, "ce_loss": 2.1036584973335266, "logit_z_loss": 50.837815284729004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1698717176914215, "tokens_per_second": 6035893.438792461, "eta_seconds": 30978.619334506988, "data_wait_seconds": 1.6629695892333984e-05} {"step": 1470, "total_steps": 22439, "tokens": 13101957120, "source": "fineweb_hq", "phase": 1, "loss": 2.081827223300934, "ce_loss": 2.076612651348114, "logit_z_loss": 52.14511775970459, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18203063309192657, "tokens_per_second": 9702547.217923736, "eta_seconds": 19262.41759264469, "data_wait_seconds": 0.7113362550735474} {"step": 1480, "total_steps": 22439, "tokens": 13191086080, "source": "fineweb_hq", "phase": 1, "loss": 2.0914183259010315, "ce_loss": 2.0867974162101746, "logit_z_loss": 46.20897102355957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19632883369922638, "tokens_per_second": 8598304.899568362, "eta_seconds": 21725.838923597334, "data_wait_seconds": 1.806020736694336e-05} {"step": 1490, "total_steps": 22439, "tokens": 13280215040, "source": "fineweb_hq", "phase": 1, "loss": 2.0886389017105103, "ce_loss": 2.083609700202942, "logit_z_loss": 50.292640686035156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19562934339046478, "tokens_per_second": 10506689.338326996, "eta_seconds": 17771.179130887984, "data_wait_seconds": 1.6629695892333984e-05} {"step": 1500, "total_steps": 22439, "tokens": 13369344000, "source": "fineweb_hq", "phase": 1, "loss": 2.0707769989967346, "ce_loss": 2.0659416913986206, "logit_z_loss": 48.353233337402344, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15800239145755768, "tokens_per_second": 8567470.96660805, "eta_seconds": 21783.222852039336, "data_wait_seconds": 1.3768672943115234e-05} {"step": 1510, "total_steps": 22439, "tokens": 13458472960, "source": "fineweb_hq", "phase": 1, "loss": 2.0773581862449646, "ce_loss": 2.0723947286605835, "logit_z_loss": 49.634596824645996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17286138236522675, "tokens_per_second": 9092079.133495083, "eta_seconds": 20516.539467501643, "data_wait_seconds": 1.633167266845703e-05} {"step": 1520, "total_steps": 22439, "tokens": 13547601920, "source": "fineweb_hq", "phase": 1, "loss": 2.057716429233551, "ce_loss": 2.0529782474040985, "logit_z_loss": 47.38206386566162, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20234528183937073, "tokens_per_second": 6287389.958911484, "eta_seconds": 29654.415050196647, "data_wait_seconds": 0.3744494915008545} {"step": 1530, "total_steps": 22439, "tokens": 13636730880, "source": "fineweb_hq", "phase": 1, "loss": 1.9040162861347198, "ce_loss": 1.8983643352985382, "logit_z_loss": 56.51964092254639, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17348912358283997, "tokens_per_second": 9308517.723903116, "eta_seconds": 20020.345665287972, "data_wait_seconds": 1.5556812286376953e-05} {"step": 1540, "total_steps": 22439, "tokens": 13725859840, "source": "fineweb_hq", "phase": 1, "loss": 1.8817239701747894, "ce_loss": 1.8762353956699371, "logit_z_loss": 54.885868072509766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16048908233642578, "tokens_per_second": 9112112.889356993, "eta_seconds": 20442.08799493313, "data_wait_seconds": 1.1861324310302734e-05} {"step": 1550, "total_steps": 22439, "tokens": 13814988800, "source": "fineweb_hq", "phase": 1, "loss": 1.8594870567321777, "ce_loss": 1.8541532158851624, "logit_z_loss": 53.338401794433594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18961311876773834, "tokens_per_second": 9242667.851403465, "eta_seconds": 20143.695255231854, "data_wait_seconds": 1.8715858459472656e-05} {"step": 1560, "total_steps": 22439, "tokens": 13904117760, "source": "fineweb_hq", "phase": 1, "loss": 1.844145506620407, "ce_loss": 1.83866947889328, "logit_z_loss": 54.76022434234619, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18260520696640015, "tokens_per_second": 9402739.405664518, "eta_seconds": 19791.291405129432, "data_wait_seconds": 1.5556812286376953e-05} {"step": 1570, "total_steps": 22439, "tokens": 13993246720, "source": "fineweb_hq", "phase": 1, "loss": 1.8625465631484985, "ce_loss": 1.8571626842021942, "logit_z_loss": 53.83877086639404, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21269944310188293, "tokens_per_second": 8617195.38264099, "eta_seconds": 21585.123507666587, "data_wait_seconds": 0.00039327144622802734} {"step": 1580, "total_steps": 22439, "tokens": 14082375680, "source": "fineweb_hq", "phase": 1, "loss": 1.8576784133911133, "ce_loss": 1.852257788181305, "logit_z_loss": 54.20642948150635, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18018083274364471, "tokens_per_second": 8709399.860919463, "eta_seconds": 21346.37295713425, "data_wait_seconds": 1.4483928680419922e-05} {"step": 1590, "total_steps": 22439, "tokens": 14171504640, "source": "fineweb_hq", "phase": 1, "loss": 1.8398555219173431, "ce_loss": 1.8350794315338135, "logit_z_loss": 47.76077461242676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19809888303279877, "tokens_per_second": 9664614.896297604, "eta_seconds": 19227.35367088318, "data_wait_seconds": 0.33451390266418457} {"step": 1600, "total_steps": 22439, "tokens": 14260633600, "source": "fineweb_hq", "phase": 1, "loss": 1.8575379550457, "ce_loss": 1.8519391119480133, "logit_z_loss": 55.98841190338135, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18590709567070007, "tokens_per_second": 9800288.456847217, "eta_seconds": 18952.078866028787, "data_wait_seconds": 0.3293381333351135} {"step": 1610, "total_steps": 22439, "tokens": 14349762560, "source": "fineweb_hq", "phase": 1, "loss": 1.8441789746284485, "ce_loss": 1.8391726315021515, "logit_z_loss": 50.06344223022461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18135440349578857, "tokens_per_second": 9559483.699845973, "eta_seconds": 19420.16081757545, "data_wait_seconds": 1.33514404296875e-05} {"step": 1620, "total_steps": 22439, "tokens": 14438891520, "source": "fineweb_hq", "phase": 1, "loss": 1.8581799566745758, "ce_loss": 1.8534447252750397, "logit_z_loss": 47.35223865509033, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1726432591676712, "tokens_per_second": 9121133.744320609, "eta_seconds": 20343.69706940651, "data_wait_seconds": 1.5020370483398438e-05} {"step": 1630, "total_steps": 22439, "tokens": 14528020480, "source": "fineweb_hq", "phase": 1, "loss": 2.040734648704529, "ce_loss": 2.0364299714565277, "logit_z_loss": 43.04685306549072, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1729593127965927, "tokens_per_second": 6881823.976535148, "eta_seconds": 26950.479043984415, "data_wait_seconds": 0.3507254719734192} {"step": 1640, "total_steps": 22439, "tokens": 14617149440, "source": "fineweb_hq", "phase": 1, "loss": 2.070746898651123, "ce_loss": 2.066723108291626, "logit_z_loss": 40.23808002471924, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17318405210971832, "tokens_per_second": 8850613.425659243, "eta_seconds": 20945.364461016656, "data_wait_seconds": 1.5020370483398438e-05} {"step": 1650, "total_steps": 22439, "tokens": 14706278400, "source": "fineweb_hq", "phase": 1, "loss": 2.088268756866455, "ce_loss": 2.0842718482017517, "logit_z_loss": 39.969401359558105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1824924200773239, "tokens_per_second": 7266274.781739803, "eta_seconds": 25500.02587428093, "data_wait_seconds": 1.811981201171875e-05} {"step": 1660, "total_steps": 22439, "tokens": 14795407360, "source": "fineweb_hq", "phase": 1, "loss": 2.065667152404785, "ce_loss": 2.061748206615448, "logit_z_loss": 39.18961811065674, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19156883656978607, "tokens_per_second": 7733618.489485933, "eta_seconds": 23947.530672192574, "data_wait_seconds": 0.2956838011741638} {"step": 1670, "total_steps": 22439, "tokens": 14884536320, "source": "fineweb_hq", "phase": 1, "loss": 2.0814231038093567, "ce_loss": 2.077380955219269, "logit_z_loss": 40.42177200317383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19338126480579376, "tokens_per_second": 7917534.85191414, "eta_seconds": 23379.99648706913, "data_wait_seconds": 1.9431114196777344e-05} {"step": 1680, "total_steps": 22439, "tokens": 14973665280, "source": "fineweb_hq", "phase": 1, "loss": 2.074860095977783, "ce_loss": 2.07120943069458, "logit_z_loss": 36.50687122344971, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2033320814371109, "tokens_per_second": 8129803.057072863, "eta_seconds": 22758.58428120613, "data_wait_seconds": 0.35082554817199707} {"step": 1690, "total_steps": 22439, "tokens": 15062794240, "source": "fineweb_hq", "phase": 1, "loss": 2.0777726769447327, "ce_loss": 2.0735161900520325, "logit_z_loss": 42.56516456604004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18531139194965363, "tokens_per_second": 6870875.741202654, "eta_seconds": 26915.590685915948, "data_wait_seconds": 1.5974044799804688e-05} {"step": 1700, "total_steps": 22439, "tokens": 15151923200, "source": "fineweb_hq", "phase": 1, "loss": 2.0900848507881165, "ce_loss": 2.0861698389053345, "logit_z_loss": 39.150065422058105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15263396501541138, "tokens_per_second": 5019988.2725010915, "eta_seconds": 36821.70955588817, "data_wait_seconds": 1.5984386205673218} {"step": 1710, "total_steps": 22439, "tokens": 15241052160, "source": "fineweb_hq", "phase": 1, "loss": 2.109273135662079, "ce_loss": 2.1052210927009583, "logit_z_loss": 40.52022457122803, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1937076896429062, "tokens_per_second": 3276723.3358929423, "eta_seconds": 56384.1991663456, "data_wait_seconds": 0.20483702421188354} {"step": 1720, "total_steps": 22439, "tokens": 15330181120, "source": "fineweb_hq", "phase": 1, "loss": 2.0865384340286255, "ce_loss": 2.0828535556793213, "logit_z_loss": 36.84969520568848, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19902455806732178, "tokens_per_second": 5927261.404666345, "eta_seconds": 31155.415564870833, "data_wait_seconds": 0.2533225417137146} {"step": 1730, "total_steps": 22439, "tokens": 15419310080, "source": "fineweb_hq", "phase": 1, "loss": 2.086715519428253, "ce_loss": 2.0825002193450928, "logit_z_loss": 42.15324878692627, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18051756918430328, "tokens_per_second": 1247194.225314065, "eta_seconds": 147993.92068827152, "data_wait_seconds": 7.639620542526245} {"step": 1740, "total_steps": 22439, "tokens": 15508439040, "source": "fineweb_hq", "phase": 1, "loss": 2.0996888875961304, "ce_loss": 2.095764935016632, "logit_z_loss": 39.23931884765625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19026674330234528, "tokens_per_second": 3509288.518486953, "eta_seconds": 52571.34981410504, "data_wait_seconds": 0.8919594883918762} {"step": 1750, "total_steps": 22439, "tokens": 15597568000, "source": "fineweb_hq", "phase": 1, "loss": 2.0865880250930786, "ce_loss": 2.0825039744377136, "logit_z_loss": 40.84074306488037, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19831131398677826, "tokens_per_second": 6079510.6208143635, "eta_seconds": 30331.20868523121, "data_wait_seconds": 2.1636486053466797e-05} {"step": 1760, "total_steps": 22439, "tokens": 15686696960, "source": "fineweb_hq", "phase": 1, "loss": 2.096293330192566, "ce_loss": 2.092851996421814, "logit_z_loss": 34.41297721862793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21348203718662262, "tokens_per_second": 5105524.996197016, "eta_seconds": 36100.06346483231, "data_wait_seconds": 1.8894672393798828e-05} {"step": 1770, "total_steps": 22439, "tokens": 15775825920, "source": "fineweb_hq", "phase": 1, "loss": 2.0741121768951416, "ce_loss": 2.07038414478302, "logit_z_loss": 37.28074932098389, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17991657555103302, "tokens_per_second": 2964905.41354485, "eta_seconds": 62133.735053539276, "data_wait_seconds": 1.8537044525146484e-05} {"step": 1780, "total_steps": 22439, "tokens": 15864954880, "source": "fineweb_hq", "phase": 1, "loss": 2.090374171733856, "ce_loss": 2.0867990851402283, "logit_z_loss": 35.75125694274902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19784201681613922, "tokens_per_second": 7555764.500325254, "eta_seconds": 24369.674101948738, "data_wait_seconds": 0.5108202695846558} {"step": 1790, "total_steps": 22439, "tokens": 15954083840, "source": "fineweb_hq", "phase": 1, "loss": 2.0731102228164673, "ce_loss": 2.0692981481552124, "logit_z_loss": 38.120967864990234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2058764398097992, "tokens_per_second": 6994334.905783939, "eta_seconds": 26313.065070962908, "data_wait_seconds": 0.4086616039276123} {"step": 1800, "total_steps": 22439, "tokens": 16043212800, "source": "fineweb_hq", "phase": 1, "loss": 2.085924506187439, "ce_loss": 2.082058846950531, "logit_z_loss": 38.656654357910156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16061393916606903, "tokens_per_second": 9008859.170746934, "eta_seconds": 20419.151532673837, "data_wait_seconds": 0.3464326858520508} {"step": 1810, "total_steps": 22439, "tokens": 16132341760, "source": "fineweb_hq", "phase": 1, "loss": 2.076956868171692, "ce_loss": 2.073280394077301, "logit_z_loss": 36.764954566955566, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16147595643997192, "tokens_per_second": 9412981.514282247, "eta_seconds": 19533.038634467124, "data_wait_seconds": 0.46132928133010864} {"step": 1820, "total_steps": 22439, "tokens": 16221470720, "source": "fineweb_hq", "phase": 1, "loss": 2.0617546439170837, "ce_loss": 2.0579012036323547, "logit_z_loss": 38.53470993041992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17057357728481293, "tokens_per_second": 9361937.559841026, "eta_seconds": 19630.01797964573, "data_wait_seconds": 1.4722347259521484e-05} {"step": 1830, "total_steps": 22439, "tokens": 16310599680, "source": "fineweb_hq", "phase": 1, "loss": 2.077634572982788, "ce_loss": 2.0740774869918823, "logit_z_loss": 35.571064949035645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19916455447673798, "tokens_per_second": 9223275.653139817, "eta_seconds": 19915.4704436779, "data_wait_seconds": 1.4662742614746094e-05} {"step": 1840, "total_steps": 22439, "tokens": 16399728640, "source": "fineweb_hq", "phase": 1, "loss": 2.069937288761139, "ce_loss": 2.0659188628196716, "logit_z_loss": 40.18417453765869, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16897347569465637, "tokens_per_second": 8666948.555177018, "eta_seconds": 21183.550765895845, "data_wait_seconds": 1.531839370727539e-05} {"step": 1850, "total_steps": 22439, "tokens": 16488857600, "source": "fineweb_hq", "phase": 1, "loss": 2.06863534450531, "ce_loss": 2.0647894740104675, "logit_z_loss": 38.459123611450195, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17927035689353943, "tokens_per_second": 9764518.941272276, "eta_seconds": 18793.308390069007, "data_wait_seconds": 1.6450881958007812e-05} {"step": 1860, "total_steps": 22439, "tokens": 16577986560, "source": "fineweb_hq", "phase": 1, "loss": 2.065973460674286, "ce_loss": 2.0624547600746155, "logit_z_loss": 35.18690490722656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16765494644641876, "tokens_per_second": 9569821.659962384, "eta_seconds": 19166.34325082302, "data_wait_seconds": 0.23574674129486084} {"step": 1870, "total_steps": 22439, "tokens": 16667115520, "source": "fineweb_hq", "phase": 1, "loss": 2.0627678632736206, "ce_loss": 2.058988571166992, "logit_z_loss": 37.79322814941406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1835007220506668, "tokens_per_second": 7101459.13075587, "eta_seconds": 25815.730886912344, "data_wait_seconds": 0.19693702459335327} {"step": 1880, "total_steps": 22439, "tokens": 16756244480, "source": "fineweb_hq", "phase": 1, "loss": 2.0630168318748474, "ce_loss": 2.0591832995414734, "logit_z_loss": 38.33492946624756, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20454849302768707, "tokens_per_second": 7078566.608806944, "eta_seconds": 25886.629170942306, "data_wait_seconds": 1.4662742614746094e-05} {"step": 1890, "total_steps": 22439, "tokens": 16845373440, "source": "fineweb_hq", "phase": 1, "loss": 2.0526363849639893, "ce_loss": 2.049336850643158, "logit_z_loss": 32.99487113952637, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17431329190731049, "tokens_per_second": 8145120.254432363, "eta_seconds": 22485.990897965432, "data_wait_seconds": 1.6748905181884766e-05} {"step": 1900, "total_steps": 22439, "tokens": 16934502400, "source": "fineweb_hq", "phase": 1, "loss": 2.0603498816490173, "ce_loss": 2.05675607919693, "logit_z_loss": 35.938087463378906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15636110305786133, "tokens_per_second": 7592324.752115036, "eta_seconds": 24111.45162000656, "data_wait_seconds": 1.4841556549072266e-05} {"step": 1910, "total_steps": 22439, "tokens": 17023631360, "source": "fineweb_hq", "phase": 1, "loss": 2.067397117614746, "ce_loss": 2.063813805580139, "logit_z_loss": 35.833237648010254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17567378282546997, "tokens_per_second": 8462457.547105325, "eta_seconds": 21621.71461014748, "data_wait_seconds": 1.4185905456542969e-05} {"step": 1920, "total_steps": 22439, "tokens": 17112760320, "source": "fineweb_hq", "phase": 1, "loss": 2.0542134642601013, "ce_loss": 2.050836205482483, "logit_z_loss": 33.77270984649658, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16789911687374115, "tokens_per_second": 6533045.916672609, "eta_seconds": 27993.636560440063, "data_wait_seconds": 0.24484151601791382} {"step": 1930, "total_steps": 22439, "tokens": 17201889280, "source": "fineweb_hq", "phase": 1, "loss": 2.0394577383995056, "ce_loss": 2.035736620426178, "logit_z_loss": 37.21140956878662, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18145474791526794, "tokens_per_second": 8515193.61488275, "eta_seconds": 21466.873488879206, "data_wait_seconds": 0.25879907608032227} {"step": 1940, "total_steps": 22439, "tokens": 17291018240, "source": "fineweb_hq", "phase": 1, "loss": 2.0570812821388245, "ce_loss": 2.0537479519844055, "logit_z_loss": 33.33323001861572, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18107885122299194, "tokens_per_second": 8248411.683858491, "eta_seconds": 22150.3802315712, "data_wait_seconds": 1.7821788787841797e-05} {"step": 1950, "total_steps": 22439, "tokens": 17380147200, "source": "fineweb_hq", "phase": 1, "loss": 2.056769907474518, "ce_loss": 2.0533993244171143, "logit_z_loss": 33.70588207244873, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19859902560710907, "tokens_per_second": 9788980.568801235, "eta_seconds": 18655.29560105801, "data_wait_seconds": 1.4781951904296875e-05} {"step": 1960, "total_steps": 22439, "tokens": 17469276160, "source": "fineweb_hq", "phase": 1, "loss": 2.0523224472999573, "ce_loss": 2.049231708049774, "logit_z_loss": 30.90770959854126, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18709014356136322, "tokens_per_second": 9703613.547283856, "eta_seconds": 18810.229436135294, "data_wait_seconds": 1.436471939086914e-05} {"step": 1970, "total_steps": 22439, "tokens": 17558405120, "source": "fineweb_hq", "phase": 1, "loss": 2.0357059836387634, "ce_loss": 2.0323468446731567, "logit_z_loss": 33.59111404418945, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16176199913024902, "tokens_per_second": 9202603.185496282, "eta_seconds": 19824.615334010123, "data_wait_seconds": 2.1696090698242188e-05} {"step": 1980, "total_steps": 22439, "tokens": 17647534080, "source": "fineweb_hq", "phase": 1, "loss": 2.0358684062957764, "ce_loss": 2.0321549773216248, "logit_z_loss": 37.134392738342285, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17926311492919922, "tokens_per_second": 8536655.426703805, "eta_seconds": 21360.70043234825, "data_wait_seconds": 1.722574234008789e-05} {"step": 1990, "total_steps": 22439, "tokens": 17736663040, "source": "fineweb_hq", "phase": 1, "loss": 2.033815383911133, "ce_loss": 2.030185043811798, "logit_z_loss": 36.30331325531006, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1813754141330719, "tokens_per_second": 6394368.948053533, "eta_seconds": 28503.173930788038, "data_wait_seconds": 0.6035826802253723} {"step": 2000, "total_steps": 22439, "tokens": 17825792000, "source": "fineweb_hq", "phase": 1, "loss": 2.0539544820785522, "ce_loss": 2.0504390001296997, "logit_z_loss": 35.15492057800293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16201187670230865, "tokens_per_second": 8755013.058933334, "eta_seconds": 20807.585336279866, "data_wait_seconds": 1.9729137420654297e-05} {"step": 2010, "total_steps": 22439, "tokens": 17914920960, "source": "fineweb_hq", "phase": 1, "loss": 2.0579468607902527, "ce_loss": 2.0548595786094666, "logit_z_loss": 30.872943878173828, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19797830283641815, "tokens_per_second": 9025640.10961994, "eta_seconds": 20173.810408186913, "data_wait_seconds": 1.6987323760986328e-05} {"step": 2020, "total_steps": 22439, "tokens": 18004049920, "source": "fineweb_hq", "phase": 1, "loss": 2.058414340019226, "ce_loss": 2.0551266074180603, "logit_z_loss": 32.877206802368164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17406673729419708, "tokens_per_second": 8986068.878712814, "eta_seconds": 20252.729628539084, "data_wait_seconds": 0.6265622973442078} {"step": 2030, "total_steps": 22439, "tokens": 18093178880, "source": "fineweb_hq", "phase": 1, "loss": 2.055076479911804, "ce_loss": 2.0518360137939453, "logit_z_loss": 32.40447425842285, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17415285110473633, "tokens_per_second": 9521053.598226178, "eta_seconds": 19105.37448270321, "data_wait_seconds": 1.3113021850585938e-05} {"step": 2040, "total_steps": 22439, "tokens": 18182307840, "source": "fineweb_hq", "phase": 1, "loss": 2.051347494125366, "ce_loss": 2.04822039604187, "logit_z_loss": 31.27086305618286, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1755242645740509, "tokens_per_second": 6112505.995554627, "eta_seconds": 29744.619577670095, "data_wait_seconds": 0.22991424798965454} {"step": 2050, "total_steps": 22439, "tokens": 18271436800, "source": "fineweb_hq", "phase": 1, "loss": 2.023362398147583, "ce_loss": 2.020069181919098, "logit_z_loss": 32.93211078643799, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15420261025428772, "tokens_per_second": 8311362.620492473, "eta_seconds": 21864.65021944046, "data_wait_seconds": 1.2814998626708984e-05} {"step": 2060, "total_steps": 22439, "tokens": 18360565760, "source": "fineweb_hq", "phase": 1, "loss": 2.0401476621627808, "ce_loss": 2.0369198322296143, "logit_z_loss": 32.27815818786621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20179200172424316, "tokens_per_second": 9102785.573016398, "eta_seconds": 19953.881822991374, "data_wait_seconds": 1.4126300811767578e-05} {"step": 2070, "total_steps": 22439, "tokens": 18449694720, "source": "fineweb_hq", "phase": 1, "loss": 2.021561861038208, "ce_loss": 2.018371343612671, "logit_z_loss": 31.905070304870605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19769331812858582, "tokens_per_second": 8823987.82777565, "eta_seconds": 20574.232667517663, "data_wait_seconds": 1.4066696166992188e-05} {"step": 2080, "total_steps": 22439, "tokens": 18538823680, "source": "fineweb_hq", "phase": 1, "loss": 2.023696720600128, "ce_loss": 2.0203598737716675, "logit_z_loss": 33.368385314941406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18662874400615692, "tokens_per_second": 10197244.29483104, "eta_seconds": 17794.77321691513, "data_wait_seconds": 0.2470015287399292} {"step": 2090, "total_steps": 22439, "tokens": 18627952640, "source": "fineweb_hq", "phase": 1, "loss": 2.0196818113327026, "ce_loss": 2.0164642333984375, "logit_z_loss": 32.1757869720459, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19313523173332214, "tokens_per_second": 9372249.055848967, "eta_seconds": 19351.653975820544, "data_wait_seconds": 0.2907504439353943} {"step": 2100, "total_steps": 22439, "tokens": 18717081600, "source": "fineweb_hq", "phase": 1, "loss": 2.017025589942932, "ce_loss": 2.014066994190216, "logit_z_loss": 29.585394859313965, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19103077054023743, "tokens_per_second": 9048078.605022399, "eta_seconds": 20035.125650143626, "data_wait_seconds": 1.3470649719238281e-05} {"step": 2110, "total_steps": 22439, "tokens": 18806210560, "source": "fineweb_hq", "phase": 1, "loss": 2.01532518863678, "ce_loss": 2.0119999647140503, "logit_z_loss": 33.25211048126221, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1808129847049713, "tokens_per_second": 9445669.251899688, "eta_seconds": 19182.363679265978, "data_wait_seconds": 1.2576580047607422e-05} {"step": 2120, "total_steps": 22439, "tokens": 18895339520, "source": "fineweb_hq", "phase": 1, "loss": 2.0197638869285583, "ce_loss": 2.0165956020355225, "logit_z_loss": 31.68268871307373, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19909454882144928, "tokens_per_second": 9395176.330383413, "eta_seconds": 19275.969652462005, "data_wait_seconds": 1.3887882232666016e-05} {"step": 2130, "total_steps": 22439, "tokens": 18984468480, "source": "fineweb_hq", "phase": 1, "loss": 2.0107338428497314, "ce_loss": 2.0076237618923187, "logit_z_loss": 31.10090208053589, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1823236048221588, "tokens_per_second": 9627546.76266418, "eta_seconds": 18801.467219662667, "data_wait_seconds": 1.9311904907226562e-05} {"step": 2140, "total_steps": 22439, "tokens": 19073597440, "source": "fineweb_hq", "phase": 1, "loss": 2.031189978122711, "ce_loss": 2.0279616117477417, "logit_z_loss": 32.28326892852783, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16408708691596985, "tokens_per_second": 8344190.512125164, "eta_seconds": 21682.49582042694, "data_wait_seconds": 1.4543533325195312e-05} {"step": 2150, "total_steps": 22439, "tokens": 19162726400, "source": "fineweb_hq", "phase": 1, "loss": 2.0433151721954346, "ce_loss": 2.0402119755744934, "logit_z_loss": 31.032260417938232, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17117755115032196, "tokens_per_second": 8402817.629268855, "eta_seconds": 21520.60831525326, "data_wait_seconds": 1.6450881958007812e-05} {"step": 2160, "total_steps": 22439, "tokens": 19251855360, "source": "fineweb_hq", "phase": 1, "loss": 2.025361120700836, "ce_loss": 2.02221018075943, "logit_z_loss": 31.50890588760376, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17410482466220856, "tokens_per_second": 8389083.132792465, "eta_seconds": 21545.21717367172, "data_wait_seconds": 1.5854835510253906e-05} {"step": 2170, "total_steps": 22439, "tokens": 19340984320, "source": "fineweb_hq", "phase": 1, "loss": 2.0582395792007446, "ce_loss": 2.0553871989250183, "logit_z_loss": 28.523427486419678, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19384868443012238, "tokens_per_second": 9948567.369923385, "eta_seconds": 18158.945133161546, "data_wait_seconds": 1.7523765563964844e-05} {"step": 2180, "total_steps": 22439, "tokens": 19430113280, "source": "fineweb_hq", "phase": 1, "loss": 2.04480642080307, "ce_loss": 2.0418859720230103, "logit_z_loss": 29.2048978805542, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21167334914207458, "tokens_per_second": 9123024.215374405, "eta_seconds": 19792.379785609242, "data_wait_seconds": 1.4781951904296875e-05} {"step": 2190, "total_steps": 22439, "tokens": 19519242240, "source": "fineweb_hq", "phase": 1, "loss": 2.035609245300293, "ce_loss": 2.032755970954895, "logit_z_loss": 28.53266668319702, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1592211127281189, "tokens_per_second": 9510310.637958212, "eta_seconds": 18977.00695323944, "data_wait_seconds": 1.4662742614746094e-05} {"step": 2200, "total_steps": 22439, "tokens": 19608371200, "source": "fineweb_hq", "phase": 1, "loss": 2.0395575165748596, "ce_loss": 2.0368998050689697, "logit_z_loss": 26.57715892791748, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21143221855163574, "tokens_per_second": 9278747.025326917, "eta_seconds": 19440.997976517676, "data_wait_seconds": 0.35680097341537476} {"step": 2210, "total_steps": 22439, "tokens": 19697500160, "source": "fineweb_hq", "phase": 1, "loss": 2.04223769903183, "ce_loss": 2.0393736362457275, "logit_z_loss": 28.64102077484131, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19915087521076202, "tokens_per_second": 9214055.364833716, "eta_seconds": 19567.819602227213, "data_wait_seconds": 0.22983777523040771} {"step": 2220, "total_steps": 22439, "tokens": 19786629120, "source": "fineweb_hq", "phase": 1, "loss": 2.032498598098755, "ce_loss": 2.029607892036438, "logit_z_loss": 28.90727186203003, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18063539266586304, "tokens_per_second": 9579657.869271174, "eta_seconds": 18811.720280957223, "data_wait_seconds": 1.7404556274414062e-05} {"step": 2230, "total_steps": 22439, "tokens": 19875758080, "source": "fineweb_hq", "phase": 1, "loss": 2.0459529757499695, "ce_loss": 2.0427300333976746, "logit_z_loss": 32.229825019836426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1797666847705841, "tokens_per_second": 7281984.29575339, "eta_seconds": 24735.11448919773, "data_wait_seconds": 1.3947486877441406e-05} {"step": 2240, "total_steps": 22439, "tokens": 19964887040, "source": "fineweb_hq", "phase": 1, "loss": 2.0370681285858154, "ce_loss": 2.034290611743927, "logit_z_loss": 27.775355339050293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20008210837841034, "tokens_per_second": 7804978.473512011, "eta_seconds": 23066.250203633306, "data_wait_seconds": 0.3049730658531189} {"step": 2250, "total_steps": 22439, "tokens": 20054016000, "source": "fineweb_hq", "phase": 1, "loss": 2.0312031507492065, "ce_loss": 2.0282183289527893, "logit_z_loss": 29.84849977493286, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.180914044380188, "tokens_per_second": 10134962.04868786, "eta_seconds": 17754.625669002533, "data_wait_seconds": 1.4126300811767578e-05} {"step": 2260, "total_steps": 22439, "tokens": 20143144960, "source": "fineweb_hq", "phase": 1, "loss": 2.0502676963806152, "ce_loss": 2.0475288033485413, "logit_z_loss": 27.389009475708008, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1776323914527893, "tokens_per_second": 10322435.91790427, "eta_seconds": 17423.53547306061, "data_wait_seconds": 1.3530254364013672e-05} {"step": 2270, "total_steps": 22439, "tokens": 20232273920, "source": "fineweb_hq", "phase": 1, "loss": 2.0364686846733093, "ce_loss": 2.0335270166397095, "logit_z_loss": 29.416617393493652, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1887456327676773, "tokens_per_second": 8408172.204505512, "eta_seconds": 21379.700017046925, "data_wait_seconds": 0.3190762996673584} {"step": 2280, "total_steps": 22439, "tokens": 20321402880, "source": "fineweb_hq", "phase": 1, "loss": 2.0495488047599792, "ce_loss": 2.046824812889099, "logit_z_loss": 27.240195274353027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1733546108007431, "tokens_per_second": 8799248.12202286, "eta_seconds": 20419.366288161276, "data_wait_seconds": 1.621246337890625e-05} {"step": 2290, "total_steps": 22439, "tokens": 20410531840, "source": "fineweb_hq", "phase": 1, "loss": 2.0428406596183777, "ce_loss": 2.03978031873703, "logit_z_loss": 30.603853702545166, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16898378729820251, "tokens_per_second": 8275810.900326003, "eta_seconds": 21700.10210080147, "data_wait_seconds": 1.329183578491211e-05} {"step": 2300, "total_steps": 22439, "tokens": 20499660800, "source": "fineweb_hq", "phase": 1, "loss": 1.9401326775550842, "ce_loss": 1.937130481004715, "logit_z_loss": 30.022052764892578, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17700089514255524, "tokens_per_second": 7071836.378770762, "eta_seconds": 25381.923863911627, "data_wait_seconds": 1.4424324035644531e-05} {"step": 2310, "total_steps": 22439, "tokens": 20588789760, "source": "fineweb_hq", "phase": 1, "loss": 1.9017107784748077, "ce_loss": 1.8984443247318268, "logit_z_loss": 32.66446876525879, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17911341786384583, "tokens_per_second": 8775481.3780292, "eta_seconds": 20444.198540854457, "data_wait_seconds": 1.4603137969970703e-05} {"step": 2320, "total_steps": 22439, "tokens": 20677918720, "source": "fineweb_hq", "phase": 1, "loss": 1.9005666971206665, "ce_loss": 1.8975791037082672, "logit_z_loss": 29.875754833221436, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1751108169555664, "tokens_per_second": 9484708.28503684, "eta_seconds": 18906.069563245772, "data_wait_seconds": 1.4126300811767578e-05} {"step": 2330, "total_steps": 22439, "tokens": 20767047680, "source": "fineweb_hq", "phase": 1, "loss": 1.8686105906963348, "ce_loss": 1.865123450756073, "logit_z_loss": 34.87128257751465, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17796088755130768, "tokens_per_second": 9165022.259538634, "eta_seconds": 19555.809095549583, "data_wait_seconds": 1.8298625946044922e-05} {"step": 2340, "total_steps": 22439, "tokens": 20856176640, "source": "fineweb_hq", "phase": 1, "loss": 1.873387098312378, "ce_loss": 1.8701667189598083, "logit_z_loss": 32.203744888305664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19001726806163788, "tokens_per_second": 8629001.643489469, "eta_seconds": 20760.25757153034, "data_wait_seconds": 1.6450881958007812e-05} {"step": 2350, "total_steps": 22439, "tokens": 20945305600, "source": "fineweb_hq", "phase": 1, "loss": 1.895044356584549, "ce_loss": 1.8916590511798859, "logit_z_loss": 33.85303211212158, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2089897245168686, "tokens_per_second": 9314424.06504595, "eta_seconds": 19222.999349570277, "data_wait_seconds": 1.6510486602783203e-05} {"step": 2360, "total_steps": 22439, "tokens": 21034434560, "source": "fineweb_hq", "phase": 1, "loss": 1.8755459785461426, "ce_loss": 1.8725358843803406, "logit_z_loss": 30.10120916366577, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16605927050113678, "tokens_per_second": 8927379.911409175, "eta_seconds": 20046.42353746891, "data_wait_seconds": 1.6748905181884766e-05} {"step": 2370, "total_steps": 22439, "tokens": 21123563520, "source": "fineweb_hq", "phase": 1, "loss": 1.8748614192008972, "ce_loss": 1.8717356026172638, "logit_z_loss": 31.258115768432617, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20171324908733368, "tokens_per_second": 9691002.61617337, "eta_seconds": 18457.62682237625, "data_wait_seconds": 1.6391277313232422e-05} {"step": 2380, "total_steps": 22439, "tokens": 21212692480, "source": "fineweb_hq", "phase": 1, "loss": 1.8649995028972626, "ce_loss": 1.8621598184108734, "logit_z_loss": 28.396848678588867, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18578790128231049, "tokens_per_second": 9663180.683950953, "eta_seconds": 18501.545889639856, "data_wait_seconds": 1.3649463653564453e-05} {"step": 2390, "total_steps": 22439, "tokens": 21301821440, "source": "fineweb_hq", "phase": 1, "loss": 1.9864574670791626, "ce_loss": 1.9836850464344025, "logit_z_loss": 27.724369049072266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17627465724945068, "tokens_per_second": 6821217.128229169, "eta_seconds": 26196.88664717674, "data_wait_seconds": 0.5083907246589661} {"step": 2400, "total_steps": 22439, "tokens": 21390950400, "source": "fineweb_hq", "phase": 1, "loss": 1.9788068234920502, "ce_loss": 1.9762361347675323, "logit_z_loss": 25.70701265335083, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1984950602054596, "tokens_per_second": 8775916.055489646, "eta_seconds": 20351.781149077415, "data_wait_seconds": 0.5659934282302856} {"step": 2410, "total_steps": 22439, "tokens": 21480079360, "source": "fineweb_hq", "phase": 1, "loss": 1.9926580488681793, "ce_loss": 1.9902203381061554, "logit_z_loss": 24.376806259155273, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18437065184116364, "tokens_per_second": 7404583.01354052, "eta_seconds": 24108.9057489872, "data_wait_seconds": 1.621246337890625e-05} {"step": 2420, "total_steps": 22439, "tokens": 21569208320, "source": "fineweb_hq", "phase": 1, "loss": 2.0003251135349274, "ce_loss": 1.9975771307945251, "logit_z_loss": 27.479761600494385, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17090129852294922, "tokens_per_second": 6319803.517671299, "eta_seconds": 28233.039923644068, "data_wait_seconds": 0.40043574571609497} {"step": 2430, "total_steps": 22439, "tokens": 21658337280, "source": "fineweb_hq", "phase": 1, "loss": 1.9818964004516602, "ce_loss": 1.9790487885475159, "logit_z_loss": 28.476386547088623, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17446281015872955, "tokens_per_second": 7589800.799504974, "eta_seconds": 23497.07729821205, "data_wait_seconds": 0.25648975372314453} {"step": 2440, "total_steps": 22439, "tokens": 21747466240, "source": "fineweb_hq", "phase": 1, "loss": 1.9831117987632751, "ce_loss": 1.9807832539081573, "logit_z_loss": 23.28531551361084, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18964725732803345, "tokens_per_second": 8018075.051413864, "eta_seconds": 22230.89781038761, "data_wait_seconds": 0.3421950340270996} {"step": 2450, "total_steps": 22439, "tokens": 21836595200, "source": "fineweb_hq", "phase": 1, "loss": 1.982147991657257, "ce_loss": 1.979582041501999, "logit_z_loss": 25.659483432769775, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1743936538696289, "tokens_per_second": 10159598.9296984, "eta_seconds": 17536.113322663306, "data_wait_seconds": 1.4007091522216797e-05} {"step": 2460, "total_steps": 22439, "tokens": 21925724160, "source": "fineweb_hq", "phase": 1, "loss": 1.974508672952652, "ce_loss": 1.9717817902565002, "logit_z_loss": 27.26885175704956, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19994820654392242, "tokens_per_second": 8940969.761335818, "eta_seconds": 19916.267914700507, "data_wait_seconds": 1.52587890625e-05} {"step": 2470, "total_steps": 22439, "tokens": 22014853120, "source": "fineweb_hq", "phase": 1, "loss": 1.9687584936618805, "ce_loss": 1.9663656949996948, "logit_z_loss": 23.928418159484863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1657525599002838, "tokens_per_second": 6969173.01780997, "eta_seconds": 25538.413204717635, "data_wait_seconds": 0.27575284242630005} {"step": 2480, "total_steps": 22439, "tokens": 22103982080, "source": "fineweb_hq", "phase": 1, "loss": 1.999930053949356, "ce_loss": 1.9974282681941986, "logit_z_loss": 25.018331050872803, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18792824447155, "tokens_per_second": 7249753.94079564, "eta_seconds": 24537.728137636186, "data_wait_seconds": 1.4603137969970703e-05} {"step": 2490, "total_steps": 22439, "tokens": 22193111040, "source": "fineweb_hq", "phase": 1, "loss": 2.0429925322532654, "ce_loss": 2.0408782958984375, "logit_z_loss": 21.141847133636475, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20084185898303986, "tokens_per_second": 8020126.876062213, "eta_seconds": 22169.644576907158, "data_wait_seconds": 0.5099901556968689} {"step": 2500, "total_steps": 22439, "tokens": 22282240000, "source": "fineweb_hq", "phase": 1, "loss": 2.0321720838546753, "ce_loss": 2.0297150015830994, "logit_z_loss": 24.570388793945312, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17361007630825043, "tokens_per_second": 8272056.6747684, "eta_seconds": 21483.681789326667, "data_wait_seconds": 0.31056344509124756} {"step": 2510, "total_steps": 22439, "tokens": 22371368960, "source": "fineweb_hq", "phase": 1, "loss": 2.0315598845481873, "ce_loss": 2.029115915298462, "logit_z_loss": 24.439398288726807, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18751464784145355, "tokens_per_second": 9125137.314834632, "eta_seconds": 19465.47194366455, "data_wait_seconds": 1.4007091522216797e-05} {"step": 2520, "total_steps": 22439, "tokens": 22460497920, "source": "fineweb_hq", "phase": 1, "loss": 2.0464203357696533, "ce_loss": 2.0440592765808105, "logit_z_loss": 23.610262393951416, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1805707812309265, "tokens_per_second": 4949999.265695508, "eta_seconds": 35865.858941507344, "data_wait_seconds": 0.6782848834991455} {"step": 2530, "total_steps": 22439, "tokens": 22549626880, "source": "fineweb_hq", "phase": 1, "loss": 2.0386396646499634, "ce_loss": 2.036255955696106, "logit_z_loss": 23.83685302734375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17036259174346924, "tokens_per_second": 5241914.736570314, "eta_seconds": 33851.53238492012, "data_wait_seconds": 0.3079301118850708} {"step": 2540, "total_steps": 22439, "tokens": 22638755840, "source": "fineweb_hq", "phase": 1, "loss": 2.036342442035675, "ce_loss": 2.0340967774391174, "logit_z_loss": 22.457284927368164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2245582640171051, "tokens_per_second": 8748815.452773618, "eta_seconds": 20272.197814822197, "data_wait_seconds": 0.39283931255340576} {"step": 2550, "total_steps": 22439, "tokens": 22727884800, "source": "fineweb_hq", "phase": 1, "loss": 2.044211447238922, "ce_loss": 2.0418595671653748, "logit_z_loss": 23.518996715545654, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18874821066856384, "tokens_per_second": 8151503.396987275, "eta_seconds": 21746.7355297327, "data_wait_seconds": 0.2972421646118164} {"step": 2560, "total_steps": 22439, "tokens": 22817013760, "source": "fineweb_hq", "phase": 1, "loss": 2.0354344248771667, "ce_loss": 2.033164083957672, "logit_z_loss": 22.70346689224243, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17443670332431793, "tokens_per_second": 8984935.867344784, "eta_seconds": 19719.61316139698, "data_wait_seconds": 1.33514404296875e-05} {"step": 2570, "total_steps": 22439, "tokens": 22906142720, "source": "fineweb_hq", "phase": 1, "loss": 2.0364562273025513, "ce_loss": 2.0341145396232605, "logit_z_loss": 23.41673469543457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18492279946804047, "tokens_per_second": 7627493.220938208, "eta_seconds": 23217.369782495498, "data_wait_seconds": 1.2934207916259766e-05} {"step": 2580, "total_steps": 22439, "tokens": 22995271680, "source": "fineweb_hq", "phase": 1, "loss": 2.043550670146942, "ce_loss": 2.041157364845276, "logit_z_loss": 23.93217658996582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17250965535640717, "tokens_per_second": 7341542.272451861, "eta_seconds": 24109.539262366292, "data_wait_seconds": 0.2229267954826355} {"step": 2590, "total_steps": 22439, "tokens": 23084400640, "source": "fineweb_hq", "phase": 1, "loss": 2.0466388463974, "ce_loss": 2.044396758079529, "logit_z_loss": 22.42099952697754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19460804760456085, "tokens_per_second": 9161156.036900764, "eta_seconds": 19311.107898545266, "data_wait_seconds": 0.16409051418304443} {"step": 2600, "total_steps": 22439, "tokens": 23173529600, "source": "fineweb_hq", "phase": 1, "loss": 2.049946129322052, "ce_loss": 2.047722041606903, "logit_z_loss": 22.240821361541748, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19772844016551971, "tokens_per_second": 9043088.49408612, "eta_seconds": 19553.37978386879, "data_wait_seconds": 0.2356126308441162} {"step": 2610, "total_steps": 22439, "tokens": 23262658560, "source": "fineweb_hq", "phase": 1, "loss": 2.057569205760956, "ce_loss": 2.0548635125160217, "logit_z_loss": 27.056442260742188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19993296265602112, "tokens_per_second": 8635678.287871933, "eta_seconds": 20465.539462280274, "data_wait_seconds": 1.430511474609375e-05} {"step": 2620, "total_steps": 22439, "tokens": 23351787520, "source": "fineweb_hq", "phase": 1, "loss": 2.049093782901764, "ce_loss": 2.0469396114349365, "logit_z_loss": 21.541772842407227, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18193447589874268, "tokens_per_second": 9663963.564733563, "eta_seconds": 18278.69948399067, "data_wait_seconds": 1.5079975128173828e-05} {"step": 2630, "total_steps": 22439, "tokens": 23440916480, "source": "fineweb_hq", "phase": 1, "loss": 2.0323676466941833, "ce_loss": 2.0302462577819824, "logit_z_loss": 21.213253021240234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16667558252811432, "tokens_per_second": 9055837.452836405, "eta_seconds": 19496.325743865964, "data_wait_seconds": 1.704692840576172e-05} {"step": 2640, "total_steps": 22439, "tokens": 23530045440, "source": "fineweb_hq", "phase": 1, "loss": 2.046623647212982, "ce_loss": 2.0443366169929504, "logit_z_loss": 22.87041139602661, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17947569489479065, "tokens_per_second": 9072132.615733445, "eta_seconds": 19451.482399845125, "data_wait_seconds": 1.6450881958007812e-05} {"step": 2650, "total_steps": 22439, "tokens": 23619174400, "source": "fineweb_hq", "phase": 1, "loss": 2.066701591014862, "ce_loss": 2.0646812319755554, "logit_z_loss": 20.203235626220703, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2239726185798645, "tokens_per_second": 7794773.485728374, "eta_seconds": 22627.63623175621, "data_wait_seconds": 1.3470649719238281e-05} {"step": 2660, "total_steps": 22439, "tokens": 23708303360, "source": "fineweb_hq", "phase": 1, "loss": 2.0189367532730103, "ce_loss": 2.01670241355896, "logit_z_loss": 22.34329605102539, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17575415968894958, "tokens_per_second": 7087545.599300122, "eta_seconds": 24872.950376701356, "data_wait_seconds": 0.25083112716674805} {"step": 2670, "total_steps": 22439, "tokens": 23797432320, "source": "fineweb_hq", "phase": 1, "loss": 2.018219143152237, "ce_loss": 2.0159740447998047, "logit_z_loss": 22.45146131515503, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19600842893123627, "tokens_per_second": 7731864.941424136, "eta_seconds": 22788.685829210284, "data_wait_seconds": 0.3047335743904114} {"step": 2680, "total_steps": 22439, "tokens": 23886561280, "source": "fineweb_hq", "phase": 1, "loss": 2.010403484106064, "ce_loss": 2.0084343254566193, "logit_z_loss": 19.69104290008545, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18596908450126648, "tokens_per_second": 7948545.5906628845, "eta_seconds": 22156.243561196326, "data_wait_seconds": 0.3490881323814392} {"step": 2690, "total_steps": 22439, "tokens": 23975690240, "source": "fineweb_hq", "phase": 1, "loss": 2.021104633808136, "ce_loss": 2.01892751455307, "logit_z_loss": 21.7708740234375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21858298778533936, "tokens_per_second": 7215131.559947135, "eta_seconds": 24396.060091423988, "data_wait_seconds": 1.6689300537109375e-05} {"step": 2700, "total_steps": 22439, "tokens": 24064819200, "source": "fineweb_hq", "phase": 1, "loss": 1.9965222775936127, "ce_loss": 1.9941023588180542, "logit_z_loss": 24.199517250061035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19311967492103577, "tokens_per_second": 6570226.218527248, "eta_seconds": 26777.107559537886, "data_wait_seconds": 1.7404556274414062e-05} {"step": 2710, "total_steps": 22439, "tokens": 24153948160, "source": "fineweb_hq", "phase": 1, "loss": 2.0004174411296844, "ce_loss": 1.9981793761253357, "logit_z_loss": 22.381272792816162, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20052550733089447, "tokens_per_second": 7320321.25270534, "eta_seconds": 24021.148678278925, "data_wait_seconds": 1.800060272216797e-05} {"step": 2720, "total_steps": 22439, "tokens": 24243077120, "source": "fineweb_hq", "phase": 1, "loss": 1.992913007736206, "ce_loss": 1.9906989932060242, "logit_z_loss": 22.14000415802002, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20012864470481873, "tokens_per_second": 6823522.240067311, "eta_seconds": 25756.990310955047, "data_wait_seconds": 1.7523765563964844e-05} {"step": 2730, "total_steps": 22439, "tokens": 24332206080, "source": "fineweb_hq", "phase": 1, "loss": 1.9965522587299347, "ce_loss": 1.9943932592868805, "logit_z_loss": 21.5897479057312, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20192262530326843, "tokens_per_second": 7888564.031572155, "eta_seconds": 22268.218469285963, "data_wait_seconds": 1.71661376953125e-05} {"step": 2740, "total_steps": 22439, "tokens": 24421335040, "source": "fineweb_hq", "phase": 1, "loss": 2.0045469999313354, "ce_loss": 2.0023904144763947, "logit_z_loss": 21.565941333770752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20243780314922333, "tokens_per_second": 9681871.749793015, "eta_seconds": 18134.420992279054, "data_wait_seconds": 1.5079975128173828e-05} {"step": 2750, "total_steps": 22439, "tokens": 24510464000, "source": "fineweb_hq", "phase": 1, "loss": 1.9818840622901917, "ce_loss": 1.9795295298099518, "logit_z_loss": 23.545257568359375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1542973816394806, "tokens_per_second": 9039170.568789288, "eta_seconds": 19413.95042924881, "data_wait_seconds": 1.424551010131836e-05} {"step": 2760, "total_steps": 22439, "tokens": 24599592960, "source": "fineweb_hq", "phase": 1, "loss": 1.996865600347519, "ce_loss": 1.9948537945747375, "logit_z_loss": 20.117997646331787, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15348832309246063, "tokens_per_second": 7100589.3930939725, "eta_seconds": 24701.735401654245, "data_wait_seconds": 1.919269561767578e-05} {"step": 2770, "total_steps": 22439, "tokens": 24688721920, "source": "fineweb_hq", "phase": 1, "loss": 2.0015414655208588, "ce_loss": 1.999369502067566, "logit_z_loss": 21.71975803375244, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1986944079399109, "tokens_per_second": 5991378.574558683, "eta_seconds": 29260.002392172813, "data_wait_seconds": 0.3649511933326721} {"step": 2780, "total_steps": 22439, "tokens": 24777850880, "source": "fineweb_hq", "phase": 1, "loss": 2.009061276912689, "ce_loss": 2.0069447457790375, "logit_z_loss": 21.165384769439697, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20025430619716644, "tokens_per_second": 7452770.878010976, "eta_seconds": 23510.5339117527, "data_wait_seconds": 2.187490463256836e-05} {"step": 2790, "total_steps": 22439, "tokens": 24866979840, "source": "fineweb_hq", "phase": 1, "loss": 2.0088039338588715, "ce_loss": 2.0067827701568604, "logit_z_loss": 20.211430549621582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19638516008853912, "tokens_per_second": 4552223.187576828, "eta_seconds": 38471.2010566473, "data_wait_seconds": 0.40549737215042114} {"step": 2800, "total_steps": 22439, "tokens": 24956108800, "source": "fineweb_hq", "phase": 1, "loss": 2.036081314086914, "ce_loss": 2.034053385257721, "logit_z_loss": 20.278470516204834, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20813503861427307, "tokens_per_second": 5026191.615089892, "eta_seconds": 34825.64493134021, "data_wait_seconds": 1.7344951629638672e-05} {"step": 2810, "total_steps": 22439, "tokens": 25045237760, "source": "fineweb_hq", "phase": 1, "loss": 2.045987844467163, "ce_loss": 2.043971061706543, "logit_z_loss": 20.168405055999756, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16371722519397736, "tokens_per_second": 5612501.593762744, "eta_seconds": 31171.703501772878, "data_wait_seconds": 0.37957578897476196} {"step": 2820, "total_steps": 22439, "tokens": 25134366720, "source": "fineweb_hq", "phase": 1, "loss": 2.0393665432929993, "ce_loss": 2.0372620224952698, "logit_z_loss": 21.045576095581055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21430955827236176, "tokens_per_second": 5923994.345426148, "eta_seconds": 29517.601879382135, "data_wait_seconds": 0.30988454818725586} {"step": 2830, "total_steps": 22439, "tokens": 25223495680, "source": "fineweb_hq", "phase": 1, "loss": 2.0364155769348145, "ce_loss": 2.0344332456588745, "logit_z_loss": 19.823069095611572, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1926155835390091, "tokens_per_second": 6963803.311545451, "eta_seconds": 25097.345494270325, "data_wait_seconds": 1.6808509826660156e-05} {"step": 2840, "total_steps": 22439, "tokens": 25312624640, "source": "fineweb_hq", "phase": 1, "loss": 2.046131134033203, "ce_loss": 2.044194757938385, "logit_z_loss": 19.36377477645874, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20294208824634552, "tokens_per_second": 6046367.633991261, "eta_seconds": 28890.70914609432, "data_wait_seconds": 0.2543771266937256} {"step": 2850, "total_steps": 22439, "tokens": 25401753600, "source": "fineweb_hq", "phase": 1, "loss": 2.052057981491089, "ce_loss": 2.050046384334564, "logit_z_loss": 20.115856647491455, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1994180828332901, "tokens_per_second": 4863801.3218455175, "eta_seconds": 35896.76226284504, "data_wait_seconds": 0.44462305307388306} {"step": 2860, "total_steps": 22439, "tokens": 25490882560, "source": "fineweb_hq", "phase": 1, "loss": 2.03972065448761, "ce_loss": 2.037589371204376, "logit_z_loss": 21.31310796737671, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1825914829969406, "tokens_per_second": 5928231.987595295, "eta_seconds": 29436.363345623016, "data_wait_seconds": 1.8358230590820312e-05} {"step": 2870, "total_steps": 22439, "tokens": 25580011520, "source": "fineweb_hq", "phase": 1, "loss": 2.02578467130661, "ce_loss": 2.0235286355018616, "logit_z_loss": 22.56062126159668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2081959992647171, "tokens_per_second": 3475797.660710917, "eta_seconds": 50180.26906328201, "data_wait_seconds": 2.002716064453125e-05} {"step": 2880, "total_steps": 22439, "tokens": 25669140480, "source": "fineweb_hq", "phase": 1, "loss": 2.031068801879883, "ce_loss": 2.0291643142700195, "logit_z_loss": 19.044764518737793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17492066323757172, "tokens_per_second": 2995575.5524823647, "eta_seconds": 58194.93777065277, "data_wait_seconds": 0.3082745671272278} {"step": 2890, "total_steps": 22439, "tokens": 25758269440, "source": "fineweb_hq", "phase": 1, "loss": 2.0326411724090576, "ce_loss": 2.0306041836738586, "logit_z_loss": 20.36912250518799, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19325879216194153, "tokens_per_second": 8886887.740461785, "eta_seconds": 19606.211869955063, "data_wait_seconds": 1.621246337890625e-05} {"step": 2900, "total_steps": 22439, "tokens": 25847398400, "source": "fineweb_hq", "phase": 1, "loss": 2.02907794713974, "ce_loss": 2.0269455909729004, "logit_z_loss": 21.32329750061035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20417892932891846, "tokens_per_second": 8705785.147505874, "eta_seconds": 20003.833312368395, "data_wait_seconds": 1.4066696166992188e-05} {"step": 2910, "total_steps": 22439, "tokens": 25936527360, "source": "fineweb_hq", "phase": 1, "loss": 2.0174092948436737, "ce_loss": 2.015255242586136, "logit_z_loss": 21.540610313415527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1901286393404007, "tokens_per_second": 8603417.166774614, "eta_seconds": 20231.489722037317, "data_wait_seconds": 1.710653305053711e-05} {"step": 2920, "total_steps": 22439, "tokens": 26025656320, "source": "fineweb_hq", "phase": 1, "loss": 2.028744876384735, "ce_loss": 2.02659273147583, "logit_z_loss": 21.521047115325928, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18201610445976257, "tokens_per_second": 10808031.790532192, "eta_seconds": 16096.438315105437, "data_wait_seconds": 1.6868114471435547e-05} {"step": 2930, "total_steps": 22439, "tokens": 26114785280, "source": "fineweb_hq", "phase": 1, "loss": 2.017153024673462, "ce_loss": 2.0150014758110046, "logit_z_loss": 21.515522480010986, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16262181103229523, "tokens_per_second": 7933577.274913043, "eta_seconds": 21917.18590979576, "data_wait_seconds": 0.29410362243652344} {"step": 2940, "total_steps": 22439, "tokens": 26203914240, "source": "fineweb_hq", "phase": 1, "loss": 2.008989691734314, "ce_loss": 2.006857305765152, "logit_z_loss": 21.32365369796753, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16997307538986206, "tokens_per_second": 7429290.7435259605, "eta_seconds": 23392.887033724783, "data_wait_seconds": 0.3371458649635315} {"step": 2950, "total_steps": 22439, "tokens": 26293043200, "source": "fineweb_hq", "phase": 1, "loss": 2.045538365840912, "ce_loss": 2.0436489582061768, "logit_z_loss": 18.894349575042725, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18968424201011658, "tokens_per_second": 9473516.550345507, "eta_seconds": 18335.68656589985, "data_wait_seconds": 1.5735626220703125e-05} {"step": 2960, "total_steps": 22439, "tokens": 26382172160, "source": "fineweb_hq", "phase": 1, "loss": 2.032977879047394, "ce_loss": 2.031268894672394, "logit_z_loss": 17.090324878692627, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18169793486595154, "tokens_per_second": 9272735.173797641, "eta_seconds": 18723.09495849609, "data_wait_seconds": 1.5795230865478516e-05} {"step": 2970, "total_steps": 22439, "tokens": 26471301120, "source": "fineweb_hq", "phase": 1, "loss": 2.030811607837677, "ce_loss": 2.028698205947876, "logit_z_loss": 21.1332688331604, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17696693539619446, "tokens_per_second": 9613583.779603638, "eta_seconds": 18049.99843993187, "data_wait_seconds": 1.728534698486328e-05} {"step": 2980, "total_steps": 22439, "tokens": 26560430080, "source": "fineweb_hq", "phase": 1, "loss": 2.0206340551376343, "ce_loss": 2.018738567829132, "logit_z_loss": 18.954172611236572, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17399431765079498, "tokens_per_second": 8228654.676487621, "eta_seconds": 21077.08368897438, "data_wait_seconds": 0.47944337129592896} {"step": 2990, "total_steps": 22439, "tokens": 26649559040, "source": "fineweb_hq", "phase": 1, "loss": 2.0190563201904297, "ce_loss": 2.0171340107917786, "logit_z_loss": 19.22331142425537, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17740830779075623, "tokens_per_second": 9010614.33609036, "eta_seconds": 19238.079429244994, "data_wait_seconds": 1.609325408935547e-05} {"step": 3000, "total_steps": 22439, "tokens": 26738688000, "source": "fineweb_hq", "phase": 1, "loss": 2.0277265310287476, "ce_loss": 2.0258068442344666, "logit_z_loss": 19.19658660888672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1734822541475296, "tokens_per_second": 6214823.535554323, "eta_seconds": 27878.15041775703, "data_wait_seconds": 1.2814998626708984e-05} {"step": 3010, "total_steps": 22439, "tokens": 26827816960, "source": "fineweb_hq", "phase": 1, "loss": 2.0212342143058777, "ce_loss": 2.0191848278045654, "logit_z_loss": 20.4937744140625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1838039755821228, "tokens_per_second": 8231843.172039608, "eta_seconds": 21036.437741208076, "data_wait_seconds": 0.4989001154899597} {"step": 3020, "total_steps": 22439, "tokens": 26916945920, "source": "fineweb_hq", "phase": 1, "loss": 2.026560127735138, "ce_loss": 2.024289548397064, "logit_z_loss": 22.70566987991333, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1977616250514984, "tokens_per_second": 9058881.585238805, "eta_seconds": 19106.05915260315, "data_wait_seconds": 1.424551010131836e-05} {"step": 3030, "total_steps": 22439, "tokens": 27006074880, "source": "fineweb_hq", "phase": 1, "loss": 2.0278123021125793, "ce_loss": 2.025873363018036, "logit_z_loss": 19.389294147491455, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20423085987567902, "tokens_per_second": 9247201.996992582, "eta_seconds": 18707.323417425156, "data_wait_seconds": 1.6689300537109375e-05} {"step": 3040, "total_steps": 22439, "tokens": 27095203840, "source": "fineweb_hq", "phase": 1, "loss": 2.02807480096817, "ce_loss": 2.026272177696228, "logit_z_loss": 18.026451110839844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21557274460792542, "tokens_per_second": 7737830.059605479, "eta_seconds": 22344.929802298546, "data_wait_seconds": 0.2599955201148987} {"step": 3050, "total_steps": 22439, "tokens": 27184332800, "source": "fineweb_hq", "phase": 1, "loss": 2.0250712037086487, "ce_loss": 2.023128628730774, "logit_z_loss": 19.425785064697266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1814272701740265, "tokens_per_second": 8197072.021924584, "eta_seconds": 21082.179110026358, "data_wait_seconds": 1.6748905181884766e-05} {"step": 3060, "total_steps": 22439, "tokens": 27273461760, "source": "fineweb_hq", "phase": 1, "loss": 2.0234243869781494, "ce_loss": 2.021772265434265, "logit_z_loss": 16.520527362823486, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17811869084835052, "tokens_per_second": 8557799.778534735, "eta_seconds": 20183.10968401432, "data_wait_seconds": 0.21652740240097046} {"step": 3070, "total_steps": 22439, "tokens": 27362590720, "source": "fineweb_hq", "phase": 1, "loss": 2.013308584690094, "ce_loss": 2.0115171670913696, "logit_z_loss": 17.914490222930908, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19540226459503174, "tokens_per_second": 8227929.51501047, "eta_seconds": 20981.448894166948, "data_wait_seconds": 1.4841556549072266e-05} {"step": 3080, "total_steps": 22439, "tokens": 27451719680, "source": "fineweb_hq", "phase": 1, "loss": 2.018525004386902, "ce_loss": 2.016875982284546, "logit_z_loss": 16.490397453308105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1966647505760193, "tokens_per_second": 6950098.593826779, "eta_seconds": 24826.231072068214, "data_wait_seconds": 1.8656253814697266e-05} {"step": 3090, "total_steps": 22439, "tokens": 27540848640, "source": "fineweb_hq", "phase": 1, "loss": 2.023775339126587, "ce_loss": 2.0218202471733093, "logit_z_loss": 19.55098533630371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20028211176395416, "tokens_per_second": 6472125.012575003, "eta_seconds": 26645.9044547081, "data_wait_seconds": 0.5513713359832764} {"step": 3100, "total_steps": 22439, "tokens": 27629977600, "source": "fineweb_hq", "phase": 1, "loss": 2.001436859369278, "ce_loss": 1.999504268169403, "logit_z_loss": 19.325819492340088, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1843174695968628, "tokens_per_second": 7665745.953878834, "eta_seconds": 22485.28672630787, "data_wait_seconds": 0.35889387130737305} {"step": 3110, "total_steps": 22439, "tokens": 27719106560, "source": "fineweb_hq", "phase": 1, "loss": 2.003302723169327, "ce_loss": 2.0013208091259003, "logit_z_loss": 19.8188157081604, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2056308090686798, "tokens_per_second": 9129567.108894512, "eta_seconds": 18870.266763925552, "data_wait_seconds": 1.4007091522216797e-05} {"step": 3120, "total_steps": 22439, "tokens": 27808235520, "source": "fineweb_hq", "phase": 1, "loss": 1.9902152121067047, "ce_loss": 1.9879622757434845, "logit_z_loss": 22.529434204101562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18570521473884583, "tokens_per_second": 9172900.673571318, "eta_seconds": 18771.405463933945, "data_wait_seconds": 1.424551010131836e-05} {"step": 3130, "total_steps": 22439, "tokens": 27897364480, "source": "fineweb_hq", "phase": 1, "loss": 2.0083114206790924, "ce_loss": 2.0065670013427734, "logit_z_loss": 17.44428539276123, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18747013807296753, "tokens_per_second": 6183897.970978052, "eta_seconds": 27830.198633885386, "data_wait_seconds": 1.7344951629638672e-05} {"step": 3140, "total_steps": 22439, "tokens": 27986493440, "source": "fineweb_hq", "phase": 1, "loss": 1.996945858001709, "ce_loss": 1.9948205649852753, "logit_z_loss": 21.252644062042236, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18163971602916718, "tokens_per_second": 9169320.617109379, "eta_seconds": 18759.293854665757, "data_wait_seconds": 0.49275678396224976} {"step": 3150, "total_steps": 22439, "tokens": 28075622400, "source": "fineweb_hq", "phase": 1, "loss": 1.9995165169239044, "ce_loss": 1.9976643323898315, "logit_z_loss": 18.521650314331055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2052135169506073, "tokens_per_second": 7940184.310746594, "eta_seconds": 21651.99751236439, "data_wait_seconds": 1.4781951904296875e-05} {"step": 3160, "total_steps": 22439, "tokens": 28164751360, "source": "fineweb_hq", "phase": 1, "loss": 1.9882806837558746, "ce_loss": 1.9864446818828583, "logit_z_loss": 18.359813690185547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21110324561595917, "tokens_per_second": 8091303.5486957, "eta_seconds": 21236.59320774078, "data_wait_seconds": 0.6467385292053223} {"step": 3170, "total_steps": 22439, "tokens": 28253880320, "source": "fineweb_hq", "phase": 1, "loss": 2.0019524097442627, "ce_loss": 1.9999778270721436, "logit_z_loss": 19.746253967285156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2018856257200241, "tokens_per_second": 8378892.770578691, "eta_seconds": 20497.05106945038, "data_wait_seconds": 1.4126300811767578e-05} {"step": 3180, "total_steps": 22439, "tokens": 28343009280, "source": "fineweb_hq", "phase": 1, "loss": 1.9891491830348969, "ce_loss": 1.987442523241043, "logit_z_loss": 17.066655158996582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20981748402118683, "tokens_per_second": 7513263.251361389, "eta_seconds": 22846.725626564028, "data_wait_seconds": 1.817941665649414e-05} {"step": 3190, "total_steps": 22439, "tokens": 28432138240, "source": "fineweb_hq", "phase": 1, "loss": 1.9704856276512146, "ce_loss": 1.9685774743556976, "logit_z_loss": 19.081652641296387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18338599801063538, "tokens_per_second": 6863938.189549735, "eta_seconds": 24995.029145979883, "data_wait_seconds": 1.4543533325195312e-05} {"step": 3200, "total_steps": 22439, "tokens": 28521267200, "source": "fineweb_hq", "phase": 1, "loss": 1.9210367798805237, "ce_loss": 1.9190617203712463, "logit_z_loss": 19.75043296813965, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23610813915729523, "tokens_per_second": 9165678.857649218, "eta_seconds": 18708.402160620688, "data_wait_seconds": 2.1398067474365234e-05} {"step": 3210, "total_steps": 22439, "tokens": 28610396160, "source": "fineweb_hq", "phase": 1, "loss": 1.9407517611980438, "ce_loss": 1.9387156069278717, "logit_z_loss": 20.361408710479736, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1974746733903885, "tokens_per_second": 10026313.422140665, "eta_seconds": 17093.62853205204, "data_wait_seconds": 1.5676021575927734e-05} {"step": 3220, "total_steps": 22439, "tokens": 28699525120, "source": "fineweb_hq", "phase": 1, "loss": 1.9133681952953339, "ce_loss": 1.9111374020576477, "logit_z_loss": 22.30795383453369, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20272980630397797, "tokens_per_second": 8466403.884205423, "eta_seconds": 20232.55098230839, "data_wait_seconds": 1.5735626220703125e-05} {"step": 3230, "total_steps": 22439, "tokens": 28788654080, "source": "fineweb_hq", "phase": 1, "loss": 1.9051525592803955, "ce_loss": 1.903094321489334, "logit_z_loss": 20.582131385803223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17471495270729065, "tokens_per_second": 9418406.117685271, "eta_seconds": 18178.00348856449, "data_wait_seconds": 1.6450881958007812e-05} {"step": 3240, "total_steps": 22439, "tokens": 28877783040, "source": "fineweb_hq", "phase": 1, "loss": 1.9231311678886414, "ce_loss": 1.9214759171009064, "logit_z_loss": 16.552300453186035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20636747777462006, "tokens_per_second": 10032030.70767321, "eta_seconds": 17057.233504390715, "data_wait_seconds": 1.4126300811767578e-05} {"step": 3250, "total_steps": 22439, "tokens": 28966912000, "source": "fineweb_hq", "phase": 1, "loss": 1.914331704378128, "ce_loss": 1.9124057292938232, "logit_z_loss": 19.259663581848145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2007567584514618, "tokens_per_second": 9260169.580064928, "eta_seconds": 18469.376814889907, "data_wait_seconds": 1.6868114471435547e-05} {"step": 3260, "total_steps": 22439, "tokens": 29056040960, "source": "fineweb_hq", "phase": 1, "loss": 1.8990927636623383, "ce_loss": 1.8968956768512726, "logit_z_loss": 21.970637321472168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20045976340770721, "tokens_per_second": 8585695.996446608, "eta_seconds": 19909.909744620323, "data_wait_seconds": 1.710653305053711e-05} {"step": 3270, "total_steps": 22439, "tokens": 29145169920, "source": "fineweb_hq", "phase": 1, "loss": 1.9245414733886719, "ce_loss": 1.9224696457386017, "logit_z_loss": 20.71824359893799, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18423886597156525, "tokens_per_second": 10490650.220754812, "eta_seconds": 16286.054708600044, "data_wait_seconds": 1.4185905456542969e-05} {"step": 3280, "total_steps": 22439, "tokens": 29234298880, "source": "fineweb_hq", "phase": 1, "loss": 1.90274578332901, "ce_loss": 1.9010366797447205, "logit_z_loss": 17.09126567840576, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19897852838039398, "tokens_per_second": 9280614.929724222, "eta_seconds": 18399.87713713646, "data_wait_seconds": 1.6510486602783203e-05} {"step": 3290, "total_steps": 22439, "tokens": 29323427840, "source": "fineweb_hq", "phase": 1, "loss": 1.9395077228546143, "ce_loss": 1.937707632780075, "logit_z_loss": 18.000736236572266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22784461081027985, "tokens_per_second": 6913505.594499435, "eta_seconds": 24686.90350663662, "data_wait_seconds": 1.728534698486328e-05} {"step": 3300, "total_steps": 22439, "tokens": 29412556800, "source": "fineweb_hq", "phase": 1, "loss": 1.9820204675197601, "ce_loss": 1.9803006649017334, "logit_z_loss": 17.197694778442383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21943329274654388, "tokens_per_second": 9740588.37148272, "eta_seconds": 17512.691229557993, "data_wait_seconds": 1.8835067749023438e-05} {"step": 3310, "total_steps": 22439, "tokens": 29501685760, "source": "fineweb_hq", "phase": 1, "loss": 1.982042521238327, "ce_loss": 1.9802904427051544, "logit_z_loss": 17.52070903778076, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16774260997772217, "tokens_per_second": 8259274.9373996975, "eta_seconds": 20642.827472901343, "data_wait_seconds": 0.4023956060409546} {"step": 3320, "total_steps": 22439, "tokens": 29590814720, "source": "fineweb_hq", "phase": 1, "loss": 1.9832809269428253, "ce_loss": 1.9812615513801575, "logit_z_loss": 20.19384002685547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1943240761756897, "tokens_per_second": 9347501.474356666, "eta_seconds": 18230.075608062743, "data_wait_seconds": 1.4662742614746094e-05} {"step": 3330, "total_steps": 22439, "tokens": 29679943680, "source": "fineweb_hq", "phase": 1, "loss": 1.9842137396335602, "ce_loss": 1.982294738292694, "logit_z_loss": 19.189839363098145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2053968906402588, "tokens_per_second": 9139963.391728435, "eta_seconds": 18634.268252992628, "data_wait_seconds": 1.9729137420654297e-05} {"step": 3340, "total_steps": 22439, "tokens": 29769072640, "source": "fineweb_hq", "phase": 1, "loss": 1.9748456180095673, "ce_loss": 1.9729939997196198, "logit_z_loss": 18.516225337982178, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.179133340716362, "tokens_per_second": 9274236.658458132, "eta_seconds": 18354.86919009686, "data_wait_seconds": 1.5616416931152344e-05} {"step": 3350, "total_steps": 22439, "tokens": 29858201600, "source": "fineweb_hq", "phase": 1, "loss": 1.9709674715995789, "ce_loss": 1.9692923426628113, "logit_z_loss": 16.751634120941162, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20607367157936096, "tokens_per_second": 9257123.931771932, "eta_seconds": 18379.171867847443, "data_wait_seconds": 1.6808509826660156e-05} {"step": 3360, "total_steps": 22439, "tokens": 29947330560, "source": "fineweb_hq", "phase": 1, "loss": 1.9718958139419556, "ce_loss": 1.9699744284152985, "logit_z_loss": 19.213780403137207, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22513151168823242, "tokens_per_second": 9516806.608733807, "eta_seconds": 17868.29866101742, "data_wait_seconds": 1.627206802368164e-05} {"step": 3370, "total_steps": 22439, "tokens": 30036459520, "source": "fineweb_hq", "phase": 1, "loss": 1.993519812822342, "ce_loss": 1.9918938279151917, "logit_z_loss": 16.259662866592407, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2238585203886032, "tokens_per_second": 12276138.557492295, "eta_seconds": 13844.74548149109, "data_wait_seconds": 1.4007091522216797e-05} {"step": 3380, "total_steps": 22439, "tokens": 30125588480, "source": "fineweb_hq", "phase": 1, "loss": 1.983389288187027, "ce_loss": 1.9816990792751312, "logit_z_loss": 16.90209150314331, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21715541183948517, "tokens_per_second": 7424298.2688148655, "eta_seconds": 22880.39606080055, "data_wait_seconds": 1.7464160919189453e-05} {"step": 3390, "total_steps": 22439, "tokens": 30214717440, "source": "fineweb_hq", "phase": 1, "loss": 2.019735634326935, "ce_loss": 2.0178821682929993, "logit_z_loss": 18.53429126739502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1817789524793625, "tokens_per_second": 7912755.620522029, "eta_seconds": 21456.716730093958, "data_wait_seconds": 1.4126300811767578e-05} {"step": 3400, "total_steps": 22439, "tokens": 30303846400, "source": "fineweb_hq", "phase": 1, "loss": 2.0074733793735504, "ce_loss": 2.0059153735637665, "logit_z_loss": 15.579859495162964, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20605479180812836, "tokens_per_second": 7794195.253917155, "eta_seconds": 21771.66742887497, "data_wait_seconds": 1.8835067749023438e-05} {"step": 3410, "total_steps": 22439, "tokens": 30392975360, "source": "fineweb_hq", "phase": 1, "loss": 2.0313073992729187, "ce_loss": 2.0295435786247253, "logit_z_loss": 17.63810682296753, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18712934851646423, "tokens_per_second": 10178822.882318199, "eta_seconds": 16662.38817050457, "data_wait_seconds": 1.3649463653564453e-05} {"step": 3420, "total_steps": 22439, "tokens": 30482104320, "source": "fineweb_hq", "phase": 1, "loss": 2.0241079330444336, "ce_loss": 2.022308826446533, "logit_z_loss": 17.99134349822998, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18763582408428192, "tokens_per_second": 8565542.477791414, "eta_seconds": 19790.266578388215, "data_wait_seconds": 0.19168758392333984} {"step": 3430, "total_steps": 22439, "tokens": 30571233280, "source": "fineweb_hq", "phase": 1, "loss": 2.020588457584381, "ce_loss": 2.0189507007598877, "logit_z_loss": 16.377779483795166, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21654848754405975, "tokens_per_second": 8654333.211520959, "eta_seconds": 19576.92590787411, "data_wait_seconds": 0.22166132926940918} {"step": 3440, "total_steps": 22439, "tokens": 30660362240, "source": "fineweb_hq", "phase": 1, "loss": 2.0230143666267395, "ce_loss": 2.0211172699928284, "logit_z_loss": 18.97057867050171, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18810251355171204, "tokens_per_second": 8197452.543929684, "eta_seconds": 20657.162721776964, "data_wait_seconds": 0.23078817129135132} {"step": 3450, "total_steps": 22439, "tokens": 30749491200, "source": "fineweb_hq", "phase": 1, "loss": 2.0201457142829895, "ce_loss": 2.0182175636291504, "logit_z_loss": 19.281468391418457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20216163992881775, "tokens_per_second": 8243271.4992820425, "eta_seconds": 20531.530734944343, "data_wait_seconds": 1.4722347259521484e-05} {"step": 3460, "total_steps": 22439, "tokens": 30838620160, "source": "fineweb_hq", "phase": 1, "loss": 2.027719259262085, "ce_loss": 2.026098310947418, "logit_z_loss": 16.209577560424805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18519680202007294, "tokens_per_second": 8937468.421215279, "eta_seconds": 18926.819677758216, "data_wait_seconds": 1.436471939086914e-05} {"step": 3470, "total_steps": 22439, "tokens": 30927749120, "source": "fineweb_hq", "phase": 1, "loss": 2.063979744911194, "ce_loss": 2.062235116958618, "logit_z_loss": 17.446134090423584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20766739547252655, "tokens_per_second": 7645790.028979984, "eta_seconds": 22112.655930018427, "data_wait_seconds": 1.2695789337158203e-05} {"step": 3480, "total_steps": 22439, "tokens": 31016878080, "source": "fineweb_hq", "phase": 1, "loss": 2.0187284350395203, "ce_loss": 2.0170786380767822, "logit_z_loss": 16.497730255126953, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18718576431274414, "tokens_per_second": 8119506.751617635, "eta_seconds": 20811.55917880535, "data_wait_seconds": 1.7762184143066406e-05} {"step": 3490, "total_steps": 22439, "tokens": 31106007040, "source": "fineweb_hq", "phase": 1, "loss": 2.014032244682312, "ce_loss": 2.012311577796936, "logit_z_loss": 17.206828117370605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18984104692935944, "tokens_per_second": 8382001.254536644, "eta_seconds": 20149.18170199394, "data_wait_seconds": 1.7464160919189453e-05} {"step": 3500, "total_steps": 22439, "tokens": 31195136000, "source": "fineweb_hq", "phase": 1, "loss": 2.0031048953533173, "ce_loss": 2.001446098089218, "logit_z_loss": 16.58782148361206, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17276695370674133, "tokens_per_second": 9273340.816088524, "eta_seconds": 18202.861373448373, "data_wait_seconds": 1.5079975128173828e-05} {"step": 3510, "total_steps": 22439, "tokens": 31284264960, "source": "fineweb_hq", "phase": 1, "loss": 2.0152204036712646, "ce_loss": 2.0136008262634277, "logit_z_loss": 16.19587540626526, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20789273083209991, "tokens_per_second": 9576148.994927151, "eta_seconds": 17617.959836816786, "data_wait_seconds": 1.3470649719238281e-05} {"step": 3520, "total_steps": 22439, "tokens": 31373393920, "source": "fineweb_hq", "phase": 1, "loss": 2.0211814045906067, "ce_loss": 2.01962947845459, "logit_z_loss": 15.51942777633667, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25186488032341003, "tokens_per_second": 8947017.20289183, "eta_seconds": 18846.848687124253, "data_wait_seconds": 1.5735626220703125e-05} {"step": 3530, "total_steps": 22439, "tokens": 31462522880, "source": "fineweb_hq", "phase": 1, "loss": 2.0143243968486786, "ce_loss": 2.0127413868904114, "logit_z_loss": 15.829767942428589, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2080068141222, "tokens_per_second": 9417824.323039219, "eta_seconds": 17895.21068594456, "data_wait_seconds": 1.6868114471435547e-05} {"step": 3540, "total_steps": 22439, "tokens": 31551651840, "source": "fineweb_hq", "phase": 1, "loss": 2.0140960216522217, "ce_loss": 2.0126816034317017, "logit_z_loss": 14.14418625831604, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1737557202577591, "tokens_per_second": 8542692.833234336, "eta_seconds": 19718.00049378872, "data_wait_seconds": 1.3649463653564453e-05} {"step": 3550, "total_steps": 22439, "tokens": 31640780800, "source": "fineweb_hq", "phase": 1, "loss": 2.0150677263736725, "ce_loss": 2.0132330656051636, "logit_z_loss": 18.346596717834473, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2053932249546051, "tokens_per_second": 7120390.805074111, "eta_seconds": 23644.164646697045, "data_wait_seconds": 0.5609121918678284} {"step": 3560, "total_steps": 22439, "tokens": 31729909760, "source": "fineweb_hq", "phase": 1, "loss": 1.9984105825424194, "ce_loss": 1.9965357184410095, "logit_z_loss": 18.748400688171387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1903456151485443, "tokens_per_second": 8277456.060926463, "eta_seconds": 20328.294387245176, "data_wait_seconds": 1.2814998626708984e-05} {"step": 3570, "total_steps": 22439, "tokens": 31819038720, "source": "fineweb_hq", "phase": 1, "loss": 1.9961443543434143, "ce_loss": 1.9945581555366516, "logit_z_loss": 15.86249327659607, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19733169674873352, "tokens_per_second": 4501222.5819268515, "eta_seconds": 37362.61239318847, "data_wait_seconds": 1.5497207641601562e-05} {"step": 3580, "total_steps": 22439, "tokens": 31908167680, "source": "fineweb_hq", "phase": 1, "loss": 2.0055298507213593, "ce_loss": 2.0037553012371063, "logit_z_loss": 17.74541473388672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20338787138462067, "tokens_per_second": 4017746.7838170184, "eta_seconds": 41836.460759806636, "data_wait_seconds": 0.5243774056434631} {"step": 3590, "total_steps": 22439, "tokens": 31997296640, "source": "fineweb_hq", "phase": 1, "loss": 2.0040977597236633, "ce_loss": 2.002236008644104, "logit_z_loss": 18.617414474487305, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17227038741111755, "tokens_per_second": 5210883.890457766, "eta_seconds": 32240.05374820232, "data_wait_seconds": 2.008676528930664e-05} {"step": 3600, "total_steps": 22439, "tokens": 32086425600, "source": "fineweb_hq", "phase": 1, "loss": 1.9935815632343292, "ce_loss": 1.9919523298740387, "logit_z_loss": 16.292394161224365, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17560094594955444, "tokens_per_second": 5757844.195302383, "eta_seconds": 29161.964452075958, "data_wait_seconds": 1.3113021850585938e-05} {"step": 3610, "total_steps": 22439, "tokens": 32175554560, "source": "fineweb_hq", "phase": 1, "loss": 2.0227943062782288, "ce_loss": 2.021260142326355, "logit_z_loss": 15.341543912887573, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2411498725414276, "tokens_per_second": 4168898.8651291784, "eta_seconds": 40255.4545488596, "data_wait_seconds": 1.8596649169921875e-05} {"step": 3620, "total_steps": 22439, "tokens": 32264683520, "source": "fineweb_hq", "phase": 1, "loss": 2.028639853000641, "ce_loss": 2.027047336101532, "logit_z_loss": 15.92501163482666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20174674689769745, "tokens_per_second": 2027622.9996450138, "eta_seconds": 82723.3612231493, "data_wait_seconds": 0.34147578477859497} {"step": 3630, "total_steps": 22439, "tokens": 32353812480, "source": "fineweb_hq", "phase": 1, "loss": 2.014183223247528, "ce_loss": 2.012699455022812, "logit_z_loss": 14.837783098220825, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17238156497478485, "tokens_per_second": 2441639.4766810024, "eta_seconds": 68659.8748361826, "data_wait_seconds": 1.7702579498291016e-05} {"step": 3640, "total_steps": 22439, "tokens": 32442941440, "source": "fineweb_hq", "phase": 1, "loss": 2.0189452171325684, "ce_loss": 2.0174110531806946, "logit_z_loss": 15.341075420379639, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18487395346164703, "tokens_per_second": 6078595.432863272, "eta_seconds": 27564.51449263096, "data_wait_seconds": 0.38743650913238525} {"step": 3650, "total_steps": 22439, "tokens": 32532070400, "source": "fineweb_hq", "phase": 1, "loss": 2.019380211830139, "ce_loss": 2.0175244510173798, "logit_z_loss": 18.55750560760498, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19012200832366943, "tokens_per_second": 3126196.157479845, "eta_seconds": 53568.10465757847, "data_wait_seconds": 3.43472683429718} {"step": 3660, "total_steps": 22439, "tokens": 32621199360, "source": "fineweb_hq", "phase": 1, "loss": 2.042075514793396, "ce_loss": 2.04050475358963, "logit_z_loss": 15.70762324333191, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18277090787887573, "tokens_per_second": 2370506.565001928, "eta_seconds": 70607.38681559563, "data_wait_seconds": 0.28702014684677124} {"step": 3670, "total_steps": 22439, "tokens": 32710328320, "source": "fineweb_hq", "phase": 1, "loss": 2.031098961830139, "ce_loss": 2.0295724272727966, "logit_z_loss": 15.265360832214355, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20190803706645966, "tokens_per_second": 3556444.03085385, "eta_seconds": 47037.47439091205, "data_wait_seconds": 1.71661376953125e-05} {"step": 3680, "total_steps": 22439, "tokens": 32799457280, "source": "fineweb_hq", "phase": 1, "loss": 2.0138610005378723, "ce_loss": 2.0122361183166504, "logit_z_loss": 16.24862289428711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19060710072517395, "tokens_per_second": 1738159.3600992817, "eta_seconds": 96191.99476304054, "data_wait_seconds": 1.3135560154914856} {"step": 3690, "total_steps": 22439, "tokens": 32888586240, "source": "fineweb_hq", "phase": 1, "loss": 2.0186561942100525, "ce_loss": 2.016741156578064, "logit_z_loss": 19.15038013458252, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20956888794898987, "tokens_per_second": 2739134.6167358644, "eta_seconds": 61007.54818072319, "data_wait_seconds": 2.5140023231506348} {"step": 3700, "total_steps": 22439, "tokens": 32977715200, "source": "fineweb_hq", "phase": 1, "loss": 2.002496123313904, "ce_loss": 2.000962048768997, "logit_z_loss": 15.340475082397461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18975253403186798, "tokens_per_second": 2621433.4375164285, "eta_seconds": 63712.759497809406, "data_wait_seconds": 1.6033649444580078e-05} {"step": 3710, "total_steps": 22439, "tokens": 33066844160, "source": "fineweb_hq", "phase": 1, "loss": 2.0068032145500183, "ce_loss": 2.0051786303520203, "logit_z_loss": 16.245834350585938, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20328465104103088, "tokens_per_second": 4395752.1353482725, "eta_seconds": 37975.21426234245, "data_wait_seconds": 0.18583136796951294} {"step": 3720, "total_steps": 22439, "tokens": 33155973120, "source": "fineweb_hq", "phase": 1, "loss": 2.0054857432842255, "ce_loss": 2.00387841463089, "logit_z_loss": 16.07309126853943, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1883114129304886, "tokens_per_second": 9677045.225071821, "eta_seconds": 17240.851555776597, "data_wait_seconds": 1.4781951904296875e-05} {"step": 3730, "total_steps": 22439, "tokens": 33245102080, "source": "fineweb_hq", "phase": 1, "loss": 1.9960985779762268, "ce_loss": 1.994218498468399, "logit_z_loss": 18.800857067108154, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1899871826171875, "tokens_per_second": 7653963.696846458, "eta_seconds": 21786.27674086094, "data_wait_seconds": 1.7523765563964844e-05} {"step": 3740, "total_steps": 22439, "tokens": 33334231040, "source": "fineweb_hq", "phase": 1, "loss": 1.992706298828125, "ce_loss": 1.991164743900299, "logit_z_loss": 15.415531635284424, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18343320488929749, "tokens_per_second": 6814418.449024649, "eta_seconds": 24457.295006275177, "data_wait_seconds": 0.3401716947555542} {"step": 3750, "total_steps": 22439, "tokens": 33423360000, "source": "fineweb_hq", "phase": 1, "loss": 1.9976584911346436, "ce_loss": 1.996023416519165, "logit_z_loss": 16.351090908050537, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19040469825267792, "tokens_per_second": 8013019.812585673, "eta_seconds": 20787.807498288155, "data_wait_seconds": 1.621246337890625e-05} {"step": 3760, "total_steps": 22439, "tokens": 33512488960, "source": "fineweb_hq", "phase": 1, "loss": 1.9904023706912994, "ce_loss": 1.9889281690120697, "logit_z_loss": 14.741894721984863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19149282574653625, "tokens_per_second": 7901527.114526313, "eta_seconds": 21069.84915332794, "data_wait_seconds": 0.6908150315284729} {"step": 3770, "total_steps": 22439, "tokens": 33601617920, "source": "fineweb_hq", "phase": 1, "loss": 1.9847385883331299, "ce_loss": 1.9831404387950897, "logit_z_loss": 15.98151707649231, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18254320323467255, "tokens_per_second": 7114712.790759448, "eta_seconds": 23387.431132864953, "data_wait_seconds": 0.25848710536956787} {"step": 3780, "total_steps": 22439, "tokens": 33690746880, "source": "fineweb_hq", "phase": 1, "loss": 1.981344610452652, "ce_loss": 1.979697436094284, "logit_z_loss": 16.471930503845215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2107265293598175, "tokens_per_second": 8598893.485115858, "eta_seconds": 19340.36358885765, "data_wait_seconds": 1.710653305053711e-05} {"step": 3790, "total_steps": 22439, "tokens": 33779875840, "source": "fineweb_hq", "phase": 1, "loss": 1.981510579586029, "ce_loss": 1.979850709438324, "logit_z_loss": 16.59871006011963, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21647170186042786, "tokens_per_second": 8202798.682981015, "eta_seconds": 20263.400813293458, "data_wait_seconds": 0.0011999011039733887} {"step": 3800, "total_steps": 22439, "tokens": 33869004800, "source": "fineweb_hq", "phase": 1, "loss": 1.9681605696678162, "ce_loss": 1.9666818380355835, "logit_z_loss": 14.787270784378052, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18738049268722534, "tokens_per_second": 7151636.612698714, "eta_seconds": 23229.29387226105, "data_wait_seconds": 0.3445867896080017} {"step": 3810, "total_steps": 22439, "tokens": 33958133760, "source": "fineweb_hq", "phase": 1, "loss": 1.9961289763450623, "ce_loss": 1.9942591786384583, "logit_z_loss": 18.697981357574463, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1805267632007599, "tokens_per_second": 8194297.63413316, "eta_seconds": 20262.668870162965, "data_wait_seconds": 0.24982541799545288} {"step": 3820, "total_steps": 22439, "tokens": 34047262720, "source": "fineweb_hq", "phase": 1, "loss": 1.9889428913593292, "ce_loss": 1.9873571395874023, "logit_z_loss": 15.857444524765015, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21160614490509033, "tokens_per_second": 8111037.46941258, "eta_seconds": 20459.677476501463, "data_wait_seconds": 1.537799835205078e-05} {"step": 3830, "total_steps": 22439, "tokens": 34136391680, "source": "fineweb_hq", "phase": 1, "loss": 1.9647177755832672, "ce_loss": 1.9632617831230164, "logit_z_loss": 14.560331344604492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1892271786928177, "tokens_per_second": 6403518.193441416, "eta_seconds": 25901.399301695823, "data_wait_seconds": 1.4185905456542969e-05} {"step": 3840, "total_steps": 22439, "tokens": 34225520640, "source": "fineweb_hq", "phase": 1, "loss": 2.0133349299430847, "ce_loss": 2.0118027925491333, "logit_z_loss": 15.321550369262695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2093222439289093, "tokens_per_second": 8561988.51331573, "eta_seconds": 19361.267823028564, "data_wait_seconds": 1.5854835510253906e-05} {"step": 3850, "total_steps": 22439, "tokens": 34314649600, "source": "fineweb_hq", "phase": 1, "loss": 1.9470350742340088, "ce_loss": 1.9452430605888367, "logit_z_loss": 17.920143604278564, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23126384615898132, "tokens_per_second": 8853229.683472263, "eta_seconds": 18714.28051316738, "data_wait_seconds": 1.7464160919189453e-05} {"step": 3860, "total_steps": 22439, "tokens": 34403778560, "source": "fineweb_hq", "phase": 1, "loss": 2.0197864174842834, "ce_loss": 2.018196940422058, "logit_z_loss": 15.894863605499268, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20012108981609344, "tokens_per_second": 9701729.370673692, "eta_seconds": 17068.368788409232, "data_wait_seconds": 2.1398067474365234e-05} {"step": 3870, "total_steps": 22439, "tokens": 34492907520, "source": "fineweb_hq", "phase": 1, "loss": 1.9886919260025024, "ce_loss": 1.9870072305202484, "logit_z_loss": 16.84697437286377, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19867917895317078, "tokens_per_second": 9532605.202719161, "eta_seconds": 17361.8399487257, "data_wait_seconds": 1.7523765563964844e-05} {"step": 3880, "total_steps": 22439, "tokens": 34582036480, "source": "fineweb_hq", "phase": 1, "loss": 1.990512639284134, "ce_loss": 1.9889492392539978, "logit_z_loss": 15.63420295715332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17651021480560303, "tokens_per_second": 9748204.006837413, "eta_seconds": 16968.708979415893, "data_wait_seconds": 1.5616416931152344e-05} {"step": 3890, "total_steps": 22439, "tokens": 34671165440, "source": "fineweb_hq", "phase": 1, "loss": 2.0156864523887634, "ce_loss": 2.0142518281936646, "logit_z_loss": 14.346595764160156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2226964235305786, "tokens_per_second": 5388559.467383077, "eta_seconds": 30680.798626184464, "data_wait_seconds": 1.5556812286376953e-05} {"step": 3900, "total_steps": 22439, "tokens": 34760294400, "source": "fineweb_hq", "phase": 1, "loss": 2.0271995663642883, "ce_loss": 2.025772213935852, "logit_z_loss": 14.274163007736206, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16615518927574158, "tokens_per_second": 9071415.168359078, "eta_seconds": 18215.03876488209, "data_wait_seconds": 1.537799835205078e-05} {"step": 3910, "total_steps": 22439, "tokens": 34849423360, "source": "fineweb_hq", "phase": 1, "loss": 2.011329174041748, "ce_loss": 2.009581506252289, "logit_z_loss": 17.476916313171387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23546282947063446, "tokens_per_second": 8712731.858842604, "eta_seconds": 18954.68065121174, "data_wait_seconds": 0.319774866104126} {"step": 3920, "total_steps": 22439, "tokens": 34938552320, "source": "fineweb_hq", "phase": 1, "loss": 2.0252636671066284, "ce_loss": 2.023689091205597, "logit_z_loss": 15.746113061904907, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22219935059547424, "tokens_per_second": 8381642.118671434, "eta_seconds": 19692.79034907818, "data_wait_seconds": 0.1966601014137268} {"step": 3930, "total_steps": 22439, "tokens": 35027681280, "source": "fineweb_hq", "phase": 1, "loss": 2.00293892621994, "ce_loss": 2.001507967710495, "logit_z_loss": 14.309523582458496, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1857057362794876, "tokens_per_second": 6539662.722317886, "eta_seconds": 25225.886879611015, "data_wait_seconds": 0.3160618543624878} {"step": 3940, "total_steps": 22439, "tokens": 35116810240, "source": "fineweb_hq", "phase": 1, "loss": 2.0192794799804688, "ce_loss": 2.017723023891449, "logit_z_loss": 15.564579725265503, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1879427134990692, "tokens_per_second": 7234675.274229186, "eta_seconds": 22790.195392918587, "data_wait_seconds": 1.5497207641601562e-05} {"step": 3950, "total_steps": 22439, "tokens": 35205939200, "source": "fineweb_hq", "phase": 1, "loss": 2.0143173336982727, "ce_loss": 2.012728452682495, "logit_z_loss": 15.889164686203003, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18202178180217743, "tokens_per_second": 7091822.055290472, "eta_seconds": 23236.69895539284, "data_wait_seconds": 0.1198573112487793} {"step": 3960, "total_steps": 22439, "tokens": 35295068160, "source": "fineweb_hq", "phase": 1, "loss": 2.01665922999382, "ce_loss": 2.015286445617676, "logit_z_loss": 13.727720975875854, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24801960587501526, "tokens_per_second": 7155220.895922639, "eta_seconds": 23018.353672051428, "data_wait_seconds": 1.6689300537109375e-05} {"step": 3970, "total_steps": 22439, "tokens": 35384197120, "source": "fineweb_hq", "phase": 1, "loss": 2.011029899120331, "ce_loss": 2.009453594684601, "logit_z_loss": 15.763326406478882, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18575838208198547, "tokens_per_second": 7113450.088682471, "eta_seconds": 23140.98983922005, "data_wait_seconds": 1.6391277313232422e-05} {"step": 3980, "total_steps": 22439, "tokens": 35473326080, "source": "fineweb_hq", "phase": 1, "loss": 2.024162232875824, "ce_loss": 2.0226771235466003, "logit_z_loss": 14.850584506988525, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18836355209350586, "tokens_per_second": 6232455.675165638, "eta_seconds": 26397.804627728463, "data_wait_seconds": 1.5437602996826172e-05} {"step": 3990, "total_steps": 22439, "tokens": 35562455040, "source": "fineweb_hq", "phase": 1, "loss": 2.0134724974632263, "ce_loss": 2.012005627155304, "logit_z_loss": 14.66879653930664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2148185521364212, "tokens_per_second": 8216855.914732696, "eta_seconds": 20011.79283297062, "data_wait_seconds": 1.6629695892333984e-05} {"step": 4000, "total_steps": 22439, "tokens": 35651584000, "source": "fineweb_hq", "phase": 1, "loss": 2.013289153575897, "ce_loss": 2.0117401480674744, "logit_z_loss": 15.49019980430603, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1726105511188507, "tokens_per_second": 9496704.461298957, "eta_seconds": 17305.465281534194, "data_wait_seconds": 1.3887882232666016e-05} {"step": 4010, "total_steps": 22439, "tokens": 35740712960, "source": "fineweb_hq", "phase": 1, "loss": 2.014196217060089, "ce_loss": 2.0128510892391205, "logit_z_loss": 13.451204299926758, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18531754612922668, "tokens_per_second": 8576519.394281091, "eta_seconds": 19151.797230648994, "data_wait_seconds": 1.6510486602783203e-05} {"step": 4020, "total_steps": 22439, "tokens": 35829841920, "source": "fineweb_hq", "phase": 1, "loss": 2.023286819458008, "ce_loss": 2.0219149589538574, "logit_z_loss": 13.718217134475708, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21435010433197021, "tokens_per_second": 9750408.393474257, "eta_seconds": 16836.897984075546, "data_wait_seconds": 0.25888460874557495} {"step": 4030, "total_steps": 22439, "tokens": 35918970880, "source": "fineweb_hq", "phase": 1, "loss": 2.009142965078354, "ce_loss": 2.0075234472751617, "logit_z_loss": 16.195269107818604, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22674012184143066, "tokens_per_second": 8497111.459153835, "eta_seconds": 19309.797600364687, "data_wait_seconds": 2.3424625396728516e-05} {"step": 4040, "total_steps": 22439, "tokens": 36008099840, "source": "fineweb_hq", "phase": 1, "loss": 1.99558886885643, "ce_loss": 1.9942216873168945, "logit_z_loss": 13.672038555145264, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15926826000213623, "tokens_per_second": 9151405.939884346, "eta_seconds": 17919.473202395442, "data_wait_seconds": 1.6868114471435547e-05} {"step": 4050, "total_steps": 22439, "tokens": 36097228800, "source": "fineweb_hq", "phase": 1, "loss": 2.008376181125641, "ce_loss": 2.006798595190048, "logit_z_loss": 15.775801181793213, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21203471720218658, "tokens_per_second": 7117058.514705034, "eta_seconds": 23029.070817017553, "data_wait_seconds": 1.7881393432617188e-05} {"step": 4060, "total_steps": 22439, "tokens": 36186357760, "source": "fineweb_hq", "phase": 1, "loss": 1.9825158715248108, "ce_loss": 1.9809121489524841, "logit_z_loss": 16.03743028640747, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18083691596984863, "tokens_per_second": 9226219.824606191, "eta_seconds": 17754.846372413635, "data_wait_seconds": 1.633167266845703e-05} {"step": 4070, "total_steps": 22439, "tokens": 36275486720, "source": "fineweb_hq", "phase": 1, "loss": 1.9812988638877869, "ce_loss": 1.9797967672348022, "logit_z_loss": 15.020936489105225, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19110889732837677, "tokens_per_second": 8524408.10155301, "eta_seconds": 19206.14131486416, "data_wait_seconds": 1.722574234008789e-05} {"step": 4080, "total_steps": 22439, "tokens": 36364615680, "source": "fineweb_hq", "phase": 1, "loss": 1.974564552307129, "ce_loss": 1.9728705883026123, "logit_z_loss": 16.939283847808838, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25177374482154846, "tokens_per_second": 8951277.208108373, "eta_seconds": 18280.28044040203, "data_wait_seconds": 0.29683125019073486} {"step": 4090, "total_steps": 22439, "tokens": 36453744640, "source": "fineweb_hq", "phase": 1, "loss": 1.9960947930812836, "ce_loss": 1.994645118713379, "logit_z_loss": 14.496305465698242, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2273578643798828, "tokens_per_second": 8583574.423699426, "eta_seconds": 19052.986626696584, "data_wait_seconds": 1.817941665649414e-05} {"step": 4100, "total_steps": 22439, "tokens": 36542873600, "source": "fineweb_hq", "phase": 1, "loss": 1.9663732945919037, "ce_loss": 1.9647744596004486, "logit_z_loss": 15.98845648765564, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19134452939033508, "tokens_per_second": 8977905.10663452, "eta_seconds": 18206.207105398178, "data_wait_seconds": 2.0205974578857422e-05} {"step": 4110, "total_steps": 22439, "tokens": 36632002560, "source": "fineweb_hq", "phase": 1, "loss": 1.975569248199463, "ce_loss": 1.9741423428058624, "logit_z_loss": 14.269193887710571, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.188175231218338, "tokens_per_second": 9615604.771978978, "eta_seconds": 16989.515964722636, "data_wait_seconds": 1.9609928131103516e-05} {"step": 4120, "total_steps": 22439, "tokens": 36721131520, "source": "fineweb_hq", "phase": 1, "loss": 1.9623444378376007, "ce_loss": 1.9605815410614014, "logit_z_loss": 17.62907600402832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18757261335849762, "tokens_per_second": 10699922.106141888, "eta_seconds": 15259.488826584815, "data_wait_seconds": 1.6748905181884766e-05} {"step": 4130, "total_steps": 22439, "tokens": 36810260480, "source": "fineweb_hq", "phase": 1, "loss": 1.9992367923259735, "ce_loss": 1.9978314340114594, "logit_z_loss": 14.053593158721924, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19500380754470825, "tokens_per_second": 8328541.443347725, "eta_seconds": 19593.612395882607, "data_wait_seconds": 1.4722347259521484e-05} {"step": 4140, "total_steps": 22439, "tokens": 36899389440, "source": "fineweb_hq", "phase": 1, "loss": 1.9676138758659363, "ce_loss": 1.965960144996643, "logit_z_loss": 16.53714418411255, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20585928857326508, "tokens_per_second": 7535001.487389492, "eta_seconds": 21645.262336969376, "data_wait_seconds": 0.8097885251045227} {"step": 4150, "total_steps": 22439, "tokens": 36988518400, "source": "fineweb_hq", "phase": 1, "loss": 1.9952862858772278, "ce_loss": 1.9939564764499664, "logit_z_loss": 13.297892570495605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19545117020606995, "tokens_per_second": 8955535.693955285, "eta_seconds": 18201.921193170547, "data_wait_seconds": 1.4543533325195312e-05} {"step": 4160, "total_steps": 22439, "tokens": 37077647360, "source": "fineweb_hq", "phase": 1, "loss": 2.008711814880371, "ce_loss": 2.007059007883072, "logit_z_loss": 16.52787446975708, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22576110064983368, "tokens_per_second": 7529484.548734603, "eta_seconds": 21637.447414827348, "data_wait_seconds": 0.3027039170265198} {"step": 4170, "total_steps": 22439, "tokens": 37166776320, "source": "fineweb_hq", "phase": 1, "loss": 2.0117472410202026, "ce_loss": 2.0103432536125183, "logit_z_loss": 14.039689540863037, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22378835082054138, "tokens_per_second": 9447902.958070917, "eta_seconds": 17234.480259442327, "data_wait_seconds": 1.6748905181884766e-05} {"step": 4180, "total_steps": 22439, "tokens": 37255905280, "source": "fineweb_hq", "phase": 1, "loss": 2.009475499391556, "ce_loss": 2.00808122754097, "logit_z_loss": 13.942255020141602, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18284662067890167, "tokens_per_second": 8915905.59089651, "eta_seconds": 18252.83661932945, "data_wait_seconds": 0.17106348276138306} {"step": 4190, "total_steps": 22439, "tokens": 37345034240, "source": "fineweb_hq", "phase": 1, "loss": 1.9964328408241272, "ce_loss": 1.994914025068283, "logit_z_loss": 15.188257932662964, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21028576791286469, "tokens_per_second": 9630173.447521327, "eta_seconds": 16889.77254567146, "data_wait_seconds": 1.4781951904296875e-05} {"step": 4200, "total_steps": 22439, "tokens": 37434163200, "source": "fineweb_hq", "phase": 1, "loss": 2.0138522386550903, "ce_loss": 2.0120435655117035, "logit_z_loss": 18.08601951599121, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22232216596603394, "tokens_per_second": 9316809.041075645, "eta_seconds": 17448.281855654717, "data_wait_seconds": 1.52587890625e-05} {"step": 4210, "total_steps": 22439, "tokens": 37523292160, "source": "fineweb_hq", "phase": 1, "loss": 2.010329842567444, "ce_loss": 2.0091538429260254, "logit_z_loss": 11.759478569030762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23426799476146698, "tokens_per_second": 9492494.346951963, "eta_seconds": 17115.96291191578, "data_wait_seconds": 1.633167266845703e-05} {"step": 4220, "total_steps": 22439, "tokens": 37612421120, "source": "fineweb_hq", "phase": 1, "loss": 2.0065369606018066, "ce_loss": 2.005005270242691, "logit_z_loss": 15.317042589187622, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.210567906498909, "tokens_per_second": 8772706.84351288, "eta_seconds": 18510.142322158812, "data_wait_seconds": 1.5795230865478516e-05} {"step": 4230, "total_steps": 22439, "tokens": 37701550080, "source": "fineweb_hq", "phase": 1, "loss": 2.020060360431671, "ce_loss": 2.0184929370880127, "logit_z_loss": 15.673987627029419, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20456454157829285, "tokens_per_second": 10156262.74358934, "eta_seconds": 15979.787778377533, "data_wait_seconds": 0.1881898045539856} {"step": 4240, "total_steps": 22439, "tokens": 37790679040, "source": "fineweb_hq", "phase": 1, "loss": 1.9883332252502441, "ce_loss": 1.9868548512458801, "logit_z_loss": 14.783324956893921, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22452305257320404, "tokens_per_second": 6335700.827039603, "eta_seconds": 25601.870847773553, "data_wait_seconds": 0.5330806970596313} {"step": 4250, "total_steps": 22439, "tokens": 37879808000, "source": "fineweb_hq", "phase": 1, "loss": 1.978423833847046, "ce_loss": 1.9769282042980194, "logit_z_loss": 14.956098318099976, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19644558429718018, "tokens_per_second": 8855992.24486049, "eta_seconds": 18305.87255065441, "data_wait_seconds": 0.26529252529144287} {"step": 4260, "total_steps": 22439, "tokens": 37968936960, "source": "fineweb_hq", "phase": 1, "loss": 1.960118442773819, "ce_loss": 1.9585554003715515, "logit_z_loss": 15.630144834518433, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18521586060523987, "tokens_per_second": 9010732.920724563, "eta_seconds": 17981.615680933, "data_wait_seconds": 1.8835067749023438e-05} {"step": 4270, "total_steps": 22439, "tokens": 38058065920, "source": "fineweb_hq", "phase": 1, "loss": 2.0059992969036102, "ce_loss": 2.004631847143173, "logit_z_loss": 13.67457389831543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19425582885742188, "tokens_per_second": 9010481.420759749, "eta_seconds": 17972.225884723663, "data_wait_seconds": 2.9265880584716797e-05} {"step": 4280, "total_steps": 22439, "tokens": 38147194880, "source": "fineweb_hq", "phase": 1, "loss": 2.00497904419899, "ce_loss": 2.003651112318039, "logit_z_loss": 13.279224872589111, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18428005278110504, "tokens_per_second": 9090156.59360665, "eta_seconds": 17804.894425892828, "data_wait_seconds": 1.7523765563964844e-05} {"step": 4290, "total_steps": 22439, "tokens": 38236323840, "source": "fineweb_hq", "phase": 1, "loss": 2.0063058137893677, "ce_loss": 2.004806339740753, "logit_z_loss": 14.994685649871826, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1990157663822174, "tokens_per_second": 10610867.733293355, "eta_seconds": 15244.761650967597, "data_wait_seconds": 1.430511474609375e-05} {"step": 4300, "total_steps": 22439, "tokens": 38325452800, "source": "fineweb_hq", "phase": 1, "loss": 1.9924063086509705, "ce_loss": 1.9909553527832031, "logit_z_loss": 14.509369850158691, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19572746753692627, "tokens_per_second": 6018636.750670543, "eta_seconds": 26861.734183573724, "data_wait_seconds": 0.6764447689056396} {"step": 4310, "total_steps": 22439, "tokens": 38414581760, "source": "fineweb_hq", "phase": 1, "loss": 1.975871503353119, "ce_loss": 1.9745736122131348, "logit_z_loss": 12.978510856628418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22592823207378387, "tokens_per_second": 7204302.544511242, "eta_seconds": 22428.526645803453, "data_wait_seconds": 1.990795135498047e-05} {"step": 4320, "total_steps": 22439, "tokens": 38503710720, "source": "fineweb_hq", "phase": 1, "loss": 1.9577647149562836, "ce_loss": 1.9563293755054474, "logit_z_loss": 14.35345721244812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1944909393787384, "tokens_per_second": 5967984.423280618, "eta_seconds": 27059.84988734722, "data_wait_seconds": 1.537799835205078e-05} {"step": 4330, "total_steps": 22439, "tokens": 38592839680, "source": "fineweb_hq", "phase": 1, "loss": 1.9706190526485443, "ce_loss": 1.9690864086151123, "logit_z_loss": 15.326232671737671, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19573818147182465, "tokens_per_second": 4158427.313102705, "eta_seconds": 38813.623880219464, "data_wait_seconds": 2.121939718723297} {"step": 4340, "total_steps": 22439, "tokens": 38681968640, "source": "fineweb_hq", "phase": 1, "loss": 1.9680157601833344, "ce_loss": 1.9663476645946503, "logit_z_loss": 16.68086004257202, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23765890300273895, "tokens_per_second": 2136134.9036714374, "eta_seconds": 75517.00242655276, "data_wait_seconds": 1.7464160919189453e-05} {"step": 4350, "total_steps": 22439, "tokens": 38771097600, "source": "fineweb_hq", "phase": 1, "loss": 1.9618011116981506, "ce_loss": 1.960164338350296, "logit_z_loss": 16.367745637893677, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2015170305967331, "tokens_per_second": 7249085.476423618, "eta_seconds": 22240.788340592386, "data_wait_seconds": 0.24190247058868408} {"step": 4360, "total_steps": 22439, "tokens": 38860226560, "source": "fineweb_hq", "phase": 1, "loss": 1.962163269519806, "ce_loss": 1.9608440399169922, "logit_z_loss": 13.192247152328491, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2051548808813095, "tokens_per_second": 6659815.650738683, "eta_seconds": 24195.301376867294, "data_wait_seconds": 1.6510486602783203e-05} {"step": 4370, "total_steps": 22439, "tokens": 38949355520, "source": "fineweb_hq", "phase": 1, "loss": 1.9666244685649872, "ce_loss": 1.9649700820446014, "logit_z_loss": 16.54347276687622, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2119329869747162, "tokens_per_second": 3402233.963883552, "eta_seconds": 47335.697525095944, "data_wait_seconds": 1.5365325808525085} {"step": 4380, "total_steps": 22439, "tokens": 39038484480, "source": "fineweb_hq", "phase": 1, "loss": 1.9537762105464935, "ce_loss": 1.9521302282810211, "logit_z_loss": 16.45962619781494, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2083231657743454, "tokens_per_second": 6700504.789033837, "eta_seconds": 24021.770587706564, "data_wait_seconds": 0.5745345950126648} {"step": 4390, "total_steps": 22439, "tokens": 39127613440, "source": "fineweb_hq", "phase": 1, "loss": 1.9478802978992462, "ce_loss": 1.9464911818504333, "logit_z_loss": 13.89102840423584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21234019100666046, "tokens_per_second": 1947235.42864359, "eta_seconds": 82613.97545342446, "data_wait_seconds": 1.8477439880371094e-05} {"step": 4400, "total_steps": 22439, "tokens": 39216742400, "source": "fineweb_hq", "phase": 1, "loss": 1.8609493374824524, "ce_loss": 1.859213411808014, "logit_z_loss": 17.35906410217285, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18522140383720398, "tokens_per_second": 3333442.0908445967, "eta_seconds": 48232.34559423923, "data_wait_seconds": 1.6987323760986328e-05} {"step": 4410, "total_steps": 22439, "tokens": 39305871360, "source": "fineweb_hq", "phase": 1, "loss": 1.8330806493759155, "ce_loss": 1.8313296437263489, "logit_z_loss": 17.51021099090576, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.15611471235752106, "tokens_per_second": 8257264.909129852, "eta_seconds": 19460.511894965173, "data_wait_seconds": 1.7464160919189453e-05} {"step": 4420, "total_steps": 22439, "tokens": 39395000320, "source": "fineweb_hq", "phase": 1, "loss": 1.832968294620514, "ce_loss": 1.8309831619262695, "logit_z_loss": 19.851370811462402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21189166605472565, "tokens_per_second": 9715609.636786932, "eta_seconds": 16530.251731801032, "data_wait_seconds": 1.621246337890625e-05} {"step": 4430, "total_steps": 22439, "tokens": 39484129280, "source": "fineweb_hq", "phase": 1, "loss": 1.8309769332408905, "ce_loss": 1.8292921781539917, "logit_z_loss": 16.847557544708252, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1913435161113739, "tokens_per_second": 9503660.202447202, "eta_seconds": 16889.52894408703, "data_wait_seconds": 0.0012846589088439941} {"step": 4440, "total_steps": 22439, "tokens": 39573258240, "source": "fineweb_hq", "phase": 1, "loss": 1.8365987837314606, "ce_loss": 1.8348791599273682, "logit_z_loss": 17.196025848388672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1953689306974411, "tokens_per_second": 9400143.831865259, "eta_seconds": 17066.03834722042, "data_wait_seconds": 1.615285873413086e-05} {"step": 4450, "total_steps": 22439, "tokens": 39662387200, "source": "fineweb_hq", "phase": 1, "loss": 1.8376320898532867, "ce_loss": 1.8359610438346863, "logit_z_loss": 16.71030616760254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19924966990947723, "tokens_per_second": 7922250.689755775, "eta_seconds": 20238.45147330761, "data_wait_seconds": 1.4424324035644531e-05} {"step": 4460, "total_steps": 22439, "tokens": 39751516160, "source": "fineweb_hq", "phase": 1, "loss": 1.8333796858787537, "ce_loss": 1.8317250609397888, "logit_z_loss": 16.5462908744812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20431078970432281, "tokens_per_second": 9031602.360407738, "eta_seconds": 17742.694019222257, "data_wait_seconds": 1.5974044799804688e-05} {"step": 4470, "total_steps": 22439, "tokens": 39840645120, "source": "fineweb_hq", "phase": 1, "loss": 1.83917635679245, "ce_loss": 1.8374740779399872, "logit_z_loss": 17.0229229927063, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21110908687114716, "tokens_per_second": 4723876.325237373, "eta_seconds": 33903.47612793445, "data_wait_seconds": 1.3322392106056213} {"step": 4480, "total_steps": 22439, "tokens": 39929774080, "source": "fineweb_hq", "phase": 1, "loss": 1.8973690867424011, "ce_loss": 1.8960082232952118, "logit_z_loss": 13.608467817306519, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22226765751838684, "tokens_per_second": 6868524.774580902, "eta_seconds": 23304.3782351017, "data_wait_seconds": 1.9490718841552734e-05} {"step": 4490, "total_steps": 22439, "tokens": 40018903040, "source": "fineweb_hq", "phase": 1, "loss": 1.976199746131897, "ce_loss": 1.974863439798355, "logit_z_loss": 13.363384246826172, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22558844089508057, "tokens_per_second": 13683812.343223851, "eta_seconds": 11691.00878405571, "data_wait_seconds": 1.6450881958007812e-05} {"step": 4500, "total_steps": 22439, "tokens": 40108032000, "source": "fineweb_hq", "phase": 1, "loss": 1.961197853088379, "ce_loss": 1.959914892911911, "logit_z_loss": 12.82959532737732, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21638324856758118, "tokens_per_second": 9451938.337186415, "eta_seconds": 16915.94206819534, "data_wait_seconds": 1.531839370727539e-05} {"step": 4510, "total_steps": 22439, "tokens": 40197160960, "source": "fineweb_hq", "phase": 1, "loss": 1.9704326391220093, "ce_loss": 1.9692209959030151, "logit_z_loss": 12.11641001701355, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2459469586610794, "tokens_per_second": 9320993.474895842, "eta_seconds": 17144.021483802797, "data_wait_seconds": 1.615285873413086e-05} {"step": 4520, "total_steps": 22439, "tokens": 40286289920, "source": "fineweb_hq", "phase": 1, "loss": 1.9689655900001526, "ce_loss": 1.967558354139328, "logit_z_loss": 14.072280883789062, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21895213425159454, "tokens_per_second": 8935757.866394108, "eta_seconds": 17873.15478014946, "data_wait_seconds": 1.436471939086914e-05} {"step": 4530, "total_steps": 22439, "tokens": 40375418880, "source": "fineweb_hq", "phase": 1, "loss": 1.9667960405349731, "ce_loss": 1.9654255211353302, "logit_z_loss": 13.705326557159424, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.186772882938385, "tokens_per_second": 7244007.348062898, "eta_seconds": 22034.91062259674, "data_wait_seconds": 1.3113021850585938e-05} {"step": 4540, "total_steps": 22439, "tokens": 40464547840, "source": "fineweb_hq", "phase": 1, "loss": 1.9429318606853485, "ce_loss": 1.941700041294098, "logit_z_loss": 12.317994356155396, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19392289221286774, "tokens_per_second": 6490693.861323867, "eta_seconds": 24578.562617874148, "data_wait_seconds": 1.728534698486328e-05} {"step": 4550, "total_steps": 22439, "tokens": 40553676800, "source": "fineweb_hq", "phase": 1, "loss": 1.9613527357578278, "ce_loss": 1.9600387513637543, "logit_z_loss": 13.140104293823242, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17363189160823822, "tokens_per_second": 9458759.227337632, "eta_seconds": 16856.62915313244, "data_wait_seconds": 1.5795230865478516e-05} {"step": 4560, "total_steps": 22439, "tokens": 40642805760, "source": "fineweb_hq", "phase": 1, "loss": 1.954132467508316, "ce_loss": 1.9525698125362396, "logit_z_loss": 15.626648902893066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18971538543701172, "tokens_per_second": 9570735.764102638, "eta_seconds": 16650.095824575423, "data_wait_seconds": 1.4960765838623047e-05} {"step": 4570, "total_steps": 22439, "tokens": 40731934720, "source": "fineweb_hq", "phase": 1, "loss": 1.9234894216060638, "ce_loss": 1.9219278991222382, "logit_z_loss": 15.615320920944214, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18218210339546204, "tokens_per_second": 8171412.743781345, "eta_seconds": 19490.45331790447, "data_wait_seconds": 1.817941665649414e-05} {"step": 4580, "total_steps": 22439, "tokens": 40821063680, "source": "fineweb_hq", "phase": 1, "loss": 1.9315175712108612, "ce_loss": 1.9301519095897675, "logit_z_loss": 13.656588792800903, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19903317093849182, "tokens_per_second": 7861138.915932166, "eta_seconds": 20248.390387988093, "data_wait_seconds": 2.0563602447509766e-05} {"step": 4590, "total_steps": 22439, "tokens": 40910192640, "source": "fineweb_hq", "phase": 1, "loss": 1.9164726734161377, "ce_loss": 1.9149778485298157, "logit_z_loss": 14.947944164276123, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1655024290084839, "tokens_per_second": 9702200.723930215, "eta_seconds": 16396.927380776404, "data_wait_seconds": 1.4424324035644531e-05} {"step": 4600, "total_steps": 22439, "tokens": 40999321600, "source": "fineweb_hq", "phase": 1, "loss": 1.9279416799545288, "ce_loss": 1.9265580475330353, "logit_z_loss": 13.836423635482788, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.192914217710495, "tokens_per_second": 8602071.181491865, "eta_seconds": 18483.589404153823, "data_wait_seconds": 1.704692840576172e-05} {"step": 4610, "total_steps": 22439, "tokens": 41088450560, "source": "fineweb_hq", "phase": 1, "loss": 1.9317528307437897, "ce_loss": 1.9303003549575806, "logit_z_loss": 14.524918556213379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2032773345708847, "tokens_per_second": 9546655.332354188, "eta_seconds": 16645.413210368155, "data_wait_seconds": 1.615285873413086e-05} {"step": 4620, "total_steps": 22439, "tokens": 41177579520, "source": "fineweb_hq", "phase": 1, "loss": 1.938091218471527, "ce_loss": 1.9366885721683502, "logit_z_loss": 14.026109457015991, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2457689642906189, "tokens_per_second": 9288716.26453193, "eta_seconds": 17098.045553445816, "data_wait_seconds": 1.6927719116210938e-05} {"step": 4630, "total_steps": 22439, "tokens": 41266708480, "source": "fineweb_hq", "phase": 1, "loss": 1.9614223539829254, "ce_loss": 1.9600622951984406, "logit_z_loss": 13.600721597671509, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16093944013118744, "tokens_per_second": 6590281.234255674, "eta_seconds": 24085.431140470504, "data_wait_seconds": 0.15060395002365112} {"step": 4640, "total_steps": 22439, "tokens": 41355837440, "source": "fineweb_hq", "phase": 1, "loss": 2.0120565593242645, "ce_loss": 2.0108526945114136, "logit_z_loss": 12.038997650146484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2120845764875412, "tokens_per_second": 8051462.163790504, "eta_seconds": 19703.332472634316, "data_wait_seconds": 0.18245083093643188} {"step": 4650, "total_steps": 22439, "tokens": 41444966400, "source": "fineweb_hq", "phase": 1, "loss": 2.0059863328933716, "ce_loss": 2.0048350989818573, "logit_z_loss": 11.512678861618042, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19091440737247467, "tokens_per_second": 7180567.128840366, "eta_seconds": 22080.63849263191, "data_wait_seconds": 1.5676021575927734e-05} {"step": 4660, "total_steps": 22439, "tokens": 41534095360, "source": "fineweb_hq", "phase": 1, "loss": 1.9900573194026947, "ce_loss": 1.9889739453792572, "logit_z_loss": 10.833622455596924, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18850897252559662, "tokens_per_second": 4081374.1771964943, "eta_seconds": 38825.74130775929, "data_wait_seconds": 1.3949717283248901} {"step": 4670, "total_steps": 22439, "tokens": 41623224320, "source": "fineweb_hq", "phase": 1, "loss": 2.008682072162628, "ce_loss": 2.0074071884155273, "logit_z_loss": 12.748913049697876, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19096501171588898, "tokens_per_second": 2444210.0934278853, "eta_seconds": 64795.268397688866, "data_wait_seconds": 1.8715858459472656e-05} {"step": 4680, "total_steps": 22439, "tokens": 41712353280, "source": "fineweb_hq", "phase": 1, "loss": 2.023363709449768, "ce_loss": 2.0220730900764465, "logit_z_loss": 12.906004428863525, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2344598025083542, "tokens_per_second": 6204678.3182062255, "eta_seconds": 25510.44743118286, "data_wait_seconds": 0.17771732807159424} {"step": 4690, "total_steps": 22439, "tokens": 41801482240, "source": "fineweb_hq", "phase": 1, "loss": 2.0130672454833984, "ce_loss": 2.011850595474243, "logit_z_loss": 12.166407823562622, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2044692188501358, "tokens_per_second": 6846275.900880936, "eta_seconds": 23106.72158036232, "data_wait_seconds": 1.811981201171875e-05} {"step": 4700, "total_steps": 22439, "tokens": 41890611200, "source": "fineweb_hq", "phase": 1, "loss": 2.0076636373996735, "ce_loss": 2.0063712298870087, "logit_z_loss": 12.924352407455444, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19284594058990479, "tokens_per_second": 5779861.6252994435, "eta_seconds": 27354.61026470661, "data_wait_seconds": 0.42465537786483765} {"step": 4710, "total_steps": 22439, "tokens": 41979740160, "source": "fineweb_hq", "phase": 1, "loss": 2.0045280158519745, "ce_loss": 2.003147542476654, "logit_z_loss": 13.804114818572998, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18384291231632233, "tokens_per_second": 6509675.043374128, "eta_seconds": 24274.135364842416, "data_wait_seconds": 1.9609928131103516e-05} {"step": 4720, "total_steps": 22439, "tokens": 42068869120, "source": "fineweb_hq", "phase": 1, "loss": 1.9990189671516418, "ce_loss": 1.9976979494094849, "logit_z_loss": 13.210668325424194, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23071090877056122, "tokens_per_second": 5899351.239880979, "eta_seconds": 26770.334194779396, "data_wait_seconds": 0.4514462947845459} {"step": 4730, "total_steps": 22439, "tokens": 42157998080, "source": "fineweb_hq", "phase": 1, "loss": 1.9874045252799988, "ce_loss": 1.9859298467636108, "logit_z_loss": 14.746951818466187, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2459883987903595, "tokens_per_second": 9651281.743006716, "eta_seconds": 16354.146471619606, "data_wait_seconds": 1.728534698486328e-05} {"step": 4740, "total_steps": 22439, "tokens": 42247127040, "source": "fineweb_hq", "phase": 1, "loss": 1.98481947183609, "ce_loss": 1.9835534691810608, "logit_z_loss": 12.6598379611969, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2217044234275818, "tokens_per_second": 8713630.503548022, "eta_seconds": 18103.745188617708, "data_wait_seconds": 1.5556812286376953e-05} {"step": 4750, "total_steps": 22439, "tokens": 42336256000, "source": "fineweb_hq", "phase": 1, "loss": 1.984474927186966, "ce_loss": 1.9831495881080627, "logit_z_loss": 13.253314733505249, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2136678546667099, "tokens_per_second": 9667319.598258758, "eta_seconds": 16308.576099252701, "data_wait_seconds": 0.2771451473236084} {"step": 4760, "total_steps": 22439, "tokens": 42425384960, "source": "fineweb_hq", "phase": 1, "loss": 1.9787940084934235, "ce_loss": 1.977463960647583, "logit_z_loss": 13.300655841827393, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20394966006278992, "tokens_per_second": 8228402.739017736, "eta_seconds": 19149.65679023266, "data_wait_seconds": 1.6748905181884766e-05} {"step": 4770, "total_steps": 22439, "tokens": 42514513920, "source": "fineweb_hq", "phase": 1, "loss": 1.9719809293746948, "ce_loss": 1.9707292318344116, "logit_z_loss": 12.516911029815674, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19357027113437653, "tokens_per_second": 9656359.704386214, "eta_seconds": 16308.62605009079, "data_wait_seconds": 1.8715858459472656e-05} {"step": 4780, "total_steps": 22439, "tokens": 42603642880, "source": "fineweb_hq", "phase": 1, "loss": 1.9777229130268097, "ce_loss": 1.9764506816864014, "logit_z_loss": 12.722278356552124, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2255581021308899, "tokens_per_second": 9983368.530827047, "eta_seconds": 15765.503394770622, "data_wait_seconds": 1.5020370483398438e-05} {"step": 4790, "total_steps": 22439, "tokens": 42692771840, "source": "fineweb_hq", "phase": 1, "loss": 1.9756270051002502, "ce_loss": 1.9741376042366028, "logit_z_loss": 14.893866062164307, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18356896936893463, "tokens_per_second": 7839603.477159446, "eta_seconds": 20065.262479448316, "data_wait_seconds": 1.4424324035644531e-05} {"step": 4800, "total_steps": 22439, "tokens": 42781900800, "source": "fineweb_hq", "phase": 1, "loss": 1.9368297457695007, "ce_loss": 1.9354324042797089, "logit_z_loss": 13.97371244430542, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2063993364572525, "tokens_per_second": 8119091.287410859, "eta_seconds": 19363.567544531823, "data_wait_seconds": 1.817941665649414e-05} {"step": 4810, "total_steps": 22439, "tokens": 42871029760, "source": "fineweb_hq", "phase": 1, "loss": 1.935621291399002, "ce_loss": 1.933936059474945, "logit_z_loss": 16.852194786071777, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24960418045520782, "tokens_per_second": 9239998.645611402, "eta_seconds": 17004.92062935829, "data_wait_seconds": 2.5570392608642578e-05} {"step": 4820, "total_steps": 22439, "tokens": 42960158720, "source": "fineweb_hq", "phase": 1, "loss": 1.9354044198989868, "ce_loss": 1.9338865280151367, "logit_z_loss": 15.178691625595093, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2437986135482788, "tokens_per_second": 9295142.208697667, "eta_seconds": 16894.449928593636, "data_wait_seconds": 1.8715858459472656e-05} {"step": 4830, "total_steps": 22439, "tokens": 43049287680, "source": "fineweb_hq", "phase": 1, "loss": 1.9247901141643524, "ce_loss": 1.923174798488617, "logit_z_loss": 16.15331721305847, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22697550058364868, "tokens_per_second": 9207508.0986038, "eta_seconds": 17045.565855956076, "data_wait_seconds": 1.6391277313232422e-05} {"step": 4840, "total_steps": 22439, "tokens": 43138416640, "source": "fineweb_hq", "phase": 1, "loss": 1.9241527020931244, "ce_loss": 1.9228351414203644, "logit_z_loss": 13.175996780395508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20056889951229095, "tokens_per_second": 8823919.928472787, "eta_seconds": 17776.45966594219, "data_wait_seconds": 1.6570091247558594e-05} {"step": 4850, "total_steps": 22439, "tokens": 43227545600, "source": "fineweb_hq", "phase": 1, "loss": 1.9350804686546326, "ce_loss": 1.9338257610797882, "logit_z_loss": 12.547303199768066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20107927918434143, "tokens_per_second": 10405254.634032724, "eta_seconds": 15066.3230509758, "data_wait_seconds": 1.6987323760986328e-05} {"step": 4860, "total_steps": 22439, "tokens": 43316674560, "source": "fineweb_hq", "phase": 1, "loss": 1.9173273742198944, "ce_loss": 1.9157485961914062, "logit_z_loss": 15.787574291229248, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22031724452972412, "tokens_per_second": 8579760.12416342, "eta_seconds": 18261.559357905386, "data_wait_seconds": 1.5914440155029297e-05} {"step": 4870, "total_steps": 22439, "tokens": 43405803520, "source": "fineweb_hq", "phase": 1, "loss": 1.9217920899391174, "ce_loss": 1.9205093085765839, "logit_z_loss": 12.827725648880005, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.195821151137352, "tokens_per_second": 8486700.471991586, "eta_seconds": 18451.30157954693, "data_wait_seconds": 1.6033649444580078e-05} {"step": 4880, "total_steps": 22439, "tokens": 43494932480, "source": "fineweb_hq", "phase": 1, "loss": 1.9351547360420227, "ce_loss": 1.9337486326694489, "logit_z_loss": 14.061205387115479, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1819906383752823, "tokens_per_second": 8004518.6402127575, "eta_seconds": 19551.64924943447, "data_wait_seconds": 1.8894672393798828e-05} {"step": 4890, "total_steps": 22439, "tokens": 43584061440, "source": "fineweb_hq", "phase": 1, "loss": 1.9426590204238892, "ce_loss": 1.9413783550262451, "logit_z_loss": 12.80677080154419, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19205857813358307, "tokens_per_second": 6774394.770030458, "eta_seconds": 23088.765448975562, "data_wait_seconds": 0.36379390954971313} {"step": 4900, "total_steps": 22439, "tokens": 43673190400, "source": "fineweb_hq", "phase": 1, "loss": 1.9468111097812653, "ce_loss": 1.9454936981201172, "logit_z_loss": 13.174278736114502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20360566675662994, "tokens_per_second": 10587106.32615153, "eta_seconds": 14765.439972758295, "data_wait_seconds": 1.5974044799804688e-05} {"step": 4910, "total_steps": 22439, "tokens": 43762319360, "source": "fineweb_hq", "phase": 1, "loss": 1.9254435002803802, "ce_loss": 1.9241173565387726, "logit_z_loss": 13.261284828186035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21674533188343048, "tokens_per_second": 5059076.724998153, "eta_seconds": 30881.949904417994, "data_wait_seconds": 1.207154393196106} {"step": 4920, "total_steps": 22439, "tokens": 43851448320, "source": "fineweb_hq", "phase": 1, "loss": 1.9480097591876984, "ce_loss": 1.946428805589676, "logit_z_loss": 15.80956220626831, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23152299225330353, "tokens_per_second": 4068518.8381361202, "eta_seconds": 38378.83791034222, "data_wait_seconds": 0.17842251062393188} {"step": 4930, "total_steps": 22439, "tokens": 43940577280, "source": "fineweb_hq", "phase": 1, "loss": 1.930438905954361, "ce_loss": 1.928987294435501, "logit_z_loss": 14.516259908676147, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2146085649728775, "tokens_per_second": 7037735.107931035, "eta_seconds": 22174.164510416984, "data_wait_seconds": 1.4841556549072266e-05} {"step": 4940, "total_steps": 22439, "tokens": 44029706240, "source": "fineweb_hq", "phase": 1, "loss": 1.9224145710468292, "ce_loss": 1.920941710472107, "logit_z_loss": 14.728908777236938, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19323144853115082, "tokens_per_second": 7307126.550396826, "eta_seconds": 21344.473238325118, "data_wait_seconds": 0.4955800771713257} {"step": 4950, "total_steps": 22439, "tokens": 44118835200, "source": "fineweb_hq", "phase": 1, "loss": 1.9297244846820831, "ce_loss": 1.9283996522426605, "logit_z_loss": 13.248131036758423, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22289793193340302, "tokens_per_second": 5375493.410792076, "eta_seconds": 28997.82889344692, "data_wait_seconds": 1.8358230590820312e-05} {"step": 4960, "total_steps": 22439, "tokens": 44207964160, "source": "fineweb_hq", "phase": 1, "loss": 1.9220939874649048, "ce_loss": 1.9206450581550598, "logit_z_loss": 14.489745140075684, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2227603942155838, "tokens_per_second": 977790.3672313232, "eta_seconds": 159327.1056915045, "data_wait_seconds": 2.6524066925048828e-05} {"step": 4970, "total_steps": 22439, "tokens": 44297093120, "source": "fineweb_hq", "phase": 1, "loss": 1.9241835176944733, "ce_loss": 1.9227491617202759, "logit_z_loss": 14.343350172042847, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22136454284191132, "tokens_per_second": 1373514.782542555, "eta_seconds": 113358.35784437656, "data_wait_seconds": 2.2709369659423828e-05} {"step": 4980, "total_steps": 22439, "tokens": 44386222080, "source": "fineweb_hq", "phase": 1, "loss": 1.9190736711025238, "ce_loss": 1.9176415503025055, "logit_z_loss": 14.321149587631226, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21908871829509735, "tokens_per_second": 6405639.930315435, "eta_seconds": 24292.694087839125, "data_wait_seconds": 0.13851898908615112} {"step": 4990, "total_steps": 22439, "tokens": 44475351040, "source": "fineweb_hq", "phase": 1, "loss": 1.8262707591056824, "ce_loss": 1.8246736824512482, "logit_z_loss": 15.970652103424072, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24139004945755005, "tokens_per_second": 5872187.648707185, "eta_seconds": 26484.358404016497, "data_wait_seconds": 1.9371509552001953e-05} {"step": 5000, "total_steps": 22439, "tokens": 44564480000, "source": "fineweb_hq", "phase": 1, "loss": 1.8128168880939484, "ce_loss": 1.8107105493545532, "logit_z_loss": 21.063279628753662, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2280053347349167, "tokens_per_second": 4357554.118882979, "eta_seconds": 35669.5497298479, "data_wait_seconds": 1.9550323486328125e-05} {"step": 5010, "total_steps": 22439, "tokens": 44653608960, "source": "fineweb_hq", "phase": 1, "loss": 1.791325181722641, "ce_loss": 1.789629191160202, "logit_z_loss": 16.959412097930908, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20356540381908417, "tokens_per_second": 5517812.242447476, "eta_seconds": 28152.98121037483, "data_wait_seconds": 0.5228837132453918} {"step": 5020, "total_steps": 22439, "tokens": 44742737920, "source": "fineweb_hq", "phase": 1, "loss": 1.777832955121994, "ce_loss": 1.7763317227363586, "logit_z_loss": 15.0121328830719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21476830542087555, "tokens_per_second": 7267015.356674922, "eta_seconds": 21364.167791581156, "data_wait_seconds": 1.6570091247558594e-05} {"step": 5030, "total_steps": 22439, "tokens": 44831866880, "source": "fineweb_hq", "phase": 1, "loss": 1.7875211238861084, "ce_loss": 1.7858860194683075, "logit_z_loss": 16.351019859313965, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23335939645767212, "tokens_per_second": 2676743.6849432606, "eta_seconds": 57967.67443099022, "data_wait_seconds": 2.4623053669929504} {"step": 5040, "total_steps": 22439, "tokens": 44920995840, "source": "fineweb_hq", "phase": 1, "loss": 1.784106194972992, "ce_loss": 1.7826716899871826, "logit_z_loss": 14.344892740249634, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21449518203735352, "tokens_per_second": 1968084.4725996873, "eta_seconds": 78795.13286294937, "data_wait_seconds": 1.0343797206878662} {"step": 5050, "total_steps": 22439, "tokens": 45010124800, "source": "fineweb_hq", "phase": 1, "loss": 1.7995936274528503, "ce_loss": 1.797973871231079, "logit_z_loss": 16.197598218917847, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2139223963022232, "tokens_per_second": 4728243.746929182, "eta_seconds": 32778.840694212915, "data_wait_seconds": 2.2590160369873047e-05} {"step": 5060, "total_steps": 22439, "tokens": 45099253760, "source": "fineweb_hq", "phase": 1, "loss": 1.7714814245700836, "ce_loss": 1.7698956429958344, "logit_z_loss": 15.858154296875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19944678246974945, "tokens_per_second": 3960440.1465606913, "eta_seconds": 39111.11236424446, "data_wait_seconds": 1.2342281937599182} {"step": 5070, "total_steps": 22439, "tokens": 45188382720, "source": "fineweb_hq", "phase": 1, "loss": 1.7655299603939056, "ce_loss": 1.7637669444084167, "logit_z_loss": 17.630144596099854, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19136641919612885, "tokens_per_second": 4877291.65661918, "eta_seconds": 31740.585046601296, "data_wait_seconds": 1.8775463104248047e-05} {"step": 5080, "total_steps": 22439, "tokens": 45277511680, "source": "fineweb_hq", "phase": 1, "loss": 1.768740862607956, "ce_loss": 1.7670588195323944, "logit_z_loss": 16.82042360305786, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2161574810743332, "tokens_per_second": 5387945.226549653, "eta_seconds": 28715.763646149637, "data_wait_seconds": 1.895427703857422e-05} {"step": 5090, "total_steps": 22439, "tokens": 45366640640, "source": "fineweb_hq", "phase": 1, "loss": 1.9092300236225128, "ce_loss": 1.9081338346004486, "logit_z_loss": 10.961602926254272, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24069197475910187, "tokens_per_second": 4516248.094043858, "eta_seconds": 34238.56030139924, "data_wait_seconds": 0.7464557886123657} {"step": 5100, "total_steps": 22439, "tokens": 45455769600, "source": "fineweb_hq", "phase": 1, "loss": 2.0327460765838623, "ce_loss": 2.0317960381507874, "logit_z_loss": 9.501094818115234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24642358720302582, "tokens_per_second": 9020810.757366309, "eta_seconds": 17131.575852847098, "data_wait_seconds": 1.4424324035644531e-05} {"step": 5110, "total_steps": 22439, "tokens": 45544898560, "source": "fineweb_hq", "phase": 1, "loss": 2.0201022922992706, "ce_loss": 2.0189713835716248, "logit_z_loss": 11.308960914611816, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23121531307697296, "tokens_per_second": 9722324.71461314, "eta_seconds": 15886.280217719079, "data_wait_seconds": 1.5497207641601562e-05} {"step": 5120, "total_steps": 22439, "tokens": 45634027520, "source": "fineweb_hq", "phase": 1, "loss": 2.0021351873874664, "ce_loss": 2.001129537820816, "logit_z_loss": 10.056825399398804, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20682285726070404, "tokens_per_second": 9504452.244423054, "eta_seconds": 16241.067013049127, "data_wait_seconds": 0.16866308450698853} {"step": 5130, "total_steps": 22439, "tokens": 45723156480, "source": "fineweb_hq", "phase": 1, "loss": 2.015974283218384, "ce_loss": 2.0148515701293945, "logit_z_loss": 11.227347612380981, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2078121304512024, "tokens_per_second": 8597894.55913424, "eta_seconds": 17943.15059378147, "data_wait_seconds": 0.3081827163696289} {"step": 5140, "total_steps": 22439, "tokens": 45812285440, "source": "fineweb_hq", "phase": 1, "loss": 2.0168784260749817, "ce_loss": 2.0157880783081055, "logit_z_loss": 10.903477191925049, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21882997453212738, "tokens_per_second": 8331107.451804976, "eta_seconds": 18507.045887470245, "data_wait_seconds": 1.6570091247558594e-05} {"step": 5150, "total_steps": 22439, "tokens": 45901414400, "source": "fineweb_hq", "phase": 1, "loss": 2.0096565783023834, "ce_loss": 2.008663594722748, "logit_z_loss": 9.92967176437378, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19914552569389343, "tokens_per_second": 7926915.671571952, "eta_seconds": 19439.472466778756, "data_wait_seconds": 1.4841556549072266e-05} {"step": 5160, "total_steps": 22439, "tokens": 45990543360, "source": "fineweb_hq", "phase": 1, "loss": 2.0146279335021973, "ce_loss": 2.0134292542934418, "logit_z_loss": 11.98681640625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21943171322345734, "tokens_per_second": 9140048.30934586, "eta_seconds": 16849.575053834917, "data_wait_seconds": 1.4066696166992188e-05} {"step": 5170, "total_steps": 22439, "tokens": 46079672320, "source": "fineweb_hq", "phase": 1, "loss": 2.0185574293136597, "ce_loss": 2.0171836614608765, "logit_z_loss": 13.737868070602417, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18862800300121307, "tokens_per_second": 8213256.0247997595, "eta_seconds": 18740.04664645195, "data_wait_seconds": 1.895427703857422e-05} {"step": 5180, "total_steps": 22439, "tokens": 46168801280, "source": "fineweb_hq", "phase": 1, "loss": 2.006345361471176, "ce_loss": 2.005410611629486, "logit_z_loss": 9.347771167755127, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22518965601921082, "tokens_per_second": 6647498.787338906, "eta_seconds": 23140.68448677063, "data_wait_seconds": 0.22946149110794067} {"step": 5190, "total_steps": 22439, "tokens": 46257930240, "source": "fineweb_hq", "phase": 1, "loss": 1.989258497953415, "ce_loss": 1.9880693852901459, "logit_z_loss": 11.890935897827148, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22930318117141724, "tokens_per_second": 8426866.780876031, "eta_seconds": 18243.855884003642, "data_wait_seconds": 1.6689300537109375e-05} {"step": 5200, "total_steps": 22439, "tokens": 46347059200, "source": "fineweb_hq", "phase": 1, "loss": 1.9901953041553497, "ce_loss": 1.9890007972717285, "logit_z_loss": 11.944582462310791, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20931528508663177, "tokens_per_second": 9437354.129537556, "eta_seconds": 16280.984271121024, "data_wait_seconds": 1.4126300811767578e-05} {"step": 5210, "total_steps": 22439, "tokens": 46436188160, "source": "fineweb_hq", "phase": 1, "loss": 1.9916885793209076, "ce_loss": 1.9904950857162476, "logit_z_loss": 11.935065746307373, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1997367888689041, "tokens_per_second": 8974464.193419829, "eta_seconds": 17110.802592158318, "data_wait_seconds": 0.2546226382255554} {"step": 5220, "total_steps": 22439, "tokens": 46525317120, "source": "fineweb_hq", "phase": 1, "loss": 2.0061209201812744, "ce_loss": 2.005035161972046, "logit_z_loss": 10.857096433639526, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.227605402469635, "tokens_per_second": 9087945.66135079, "eta_seconds": 16887.332070732118, "data_wait_seconds": 1.7344951629638672e-05} {"step": 5230, "total_steps": 22439, "tokens": 46614446080, "source": "fineweb_hq", "phase": 1, "loss": 2.0069627463817596, "ce_loss": 2.0055638253688812, "logit_z_loss": 13.988910436630249, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2414417266845703, "tokens_per_second": 10042576.157044964, "eta_seconds": 15273.17541489601, "data_wait_seconds": 1.71661376953125e-05} {"step": 5240, "total_steps": 22439, "tokens": 46703575040, "source": "fineweb_hq", "phase": 1, "loss": 2.004990875720978, "ce_loss": 2.0037719011306763, "logit_z_loss": 12.18923807144165, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23021064698696136, "tokens_per_second": 5711844.451294164, "eta_seconds": 26837.722842621806, "data_wait_seconds": 1.6629695892333984e-05} {"step": 5250, "total_steps": 22439, "tokens": 46792704000, "source": "fineweb_hq", "phase": 1, "loss": 2.0162060260772705, "ce_loss": 2.014938235282898, "logit_z_loss": 12.678077220916748, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19790969789028168, "tokens_per_second": 9060182.63659166, "eta_seconds": 16909.56744351387, "data_wait_seconds": 1.4841556549072266e-05} {"step": 5260, "total_steps": 22439, "tokens": 46881832960, "source": "fineweb_hq", "phase": 1, "loss": 2.0076197385787964, "ce_loss": 2.006219059228897, "logit_z_loss": 14.00635313987732, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2395176738500595, "tokens_per_second": 7710788.6358875735, "eta_seconds": 19857.195886731148, "data_wait_seconds": 1.609325408935547e-05} {"step": 5270, "total_steps": 22439, "tokens": 46970961920, "source": "fineweb_hq", "phase": 1, "loss": 2.0078548789024353, "ce_loss": 2.006584346294403, "logit_z_loss": 12.704899787902832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1951933056116104, "tokens_per_second": 6786494.357234577, "eta_seconds": 22548.535866808892, "data_wait_seconds": 0.15169423818588257} {"step": 5280, "total_steps": 22439, "tokens": 47060090880, "source": "fineweb_hq", "phase": 1, "loss": 2.0089115500450134, "ce_loss": 2.0077077746391296, "logit_z_loss": 12.037396907806396, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2243223488330841, "tokens_per_second": 7671994.704789966, "eta_seconds": 19934.370179963113, "data_wait_seconds": 1.5497207641601562e-05} {"step": 5290, "total_steps": 22439, "tokens": 47149219840, "source": "fineweb_hq", "phase": 1, "loss": 2.0014482736587524, "ce_loss": 2.0002733767032623, "logit_z_loss": 11.749072074890137, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21692048013210297, "tokens_per_second": 9406389.534941576, "eta_seconds": 16249.300854086874, "data_wait_seconds": 1.52587890625e-05} {"step": 5300, "total_steps": 22439, "tokens": 47238348800, "source": "fineweb_hq", "phase": 1, "loss": 2.0236311554908752, "ce_loss": 2.0226978063583374, "logit_z_loss": 9.333601236343384, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2600855529308319, "tokens_per_second": 8240925.707502102, "eta_seconds": 18536.524896097184, "data_wait_seconds": 1.615285873413086e-05} {"step": 5310, "total_steps": 22439, "tokens": 47327477760, "source": "fineweb_hq", "phase": 1, "loss": 2.014042854309082, "ce_loss": 2.0129928588867188, "logit_z_loss": 10.500086545944214, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22044628858566284, "tokens_per_second": 8859154.568936648, "eta_seconds": 17232.90799319744, "data_wait_seconds": 1.5676021575927734e-05} {"step": 5320, "total_steps": 22439, "tokens": 47416606720, "source": "fineweb_hq", "phase": 1, "loss": 2.024823784828186, "ce_loss": 2.02367627620697, "logit_z_loss": 11.474820375442505, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2347201108932495, "tokens_per_second": 7992640.969456496, "eta_seconds": 19090.043854975702, "data_wait_seconds": 1.3172626495361328e-05} {"step": 5330, "total_steps": 22439, "tokens": 47505735680, "source": "fineweb_hq", "phase": 1, "loss": 2.012104570865631, "ce_loss": 2.0108433961868286, "logit_z_loss": 12.611134767532349, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18771439790725708, "tokens_per_second": 6095486.95368498, "eta_seconds": 25016.99024584293, "data_wait_seconds": 0.1549704670906067} {"step": 5340, "total_steps": 22439, "tokens": 47594864640, "source": "fineweb_hq", "phase": 1, "loss": 2.0008276402950287, "ce_loss": 1.9995937943458557, "logit_z_loss": 12.338387250900269, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18979685008525848, "tokens_per_second": 7296700.122983318, "eta_seconds": 20886.374132871628, "data_wait_seconds": 1.5735626220703125e-05} {"step": 5350, "total_steps": 22439, "tokens": 47683993600, "source": "fineweb_hq", "phase": 1, "loss": 2.0030734539031982, "ce_loss": 2.0019955337047577, "logit_z_loss": 10.779303073883057, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18997220695018768, "tokens_per_second": 7303315.5925348215, "eta_seconds": 20855.250990343095, "data_wait_seconds": 0.2638198137283325} {"step": 5360, "total_steps": 22439, "tokens": 47773122560, "source": "fineweb_hq", "phase": 1, "loss": 2.009579360485077, "ce_loss": 2.0084381997585297, "logit_z_loss": 11.411734342575073, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22031071782112122, "tokens_per_second": 8513697.870608283, "eta_seconds": 17879.815926933286, "data_wait_seconds": 1.4543533325195312e-05} {"step": 5370, "total_steps": 22439, "tokens": 47862251520, "source": "fineweb_hq", "phase": 1, "loss": 2.0171879529953003, "ce_loss": 2.015793740749359, "logit_z_loss": 13.94193172454834, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2008735090494156, "tokens_per_second": 7604016.692816372, "eta_seconds": 20007.08677661419, "data_wait_seconds": 1.9311904907226562e-05} {"step": 5380, "total_steps": 22439, "tokens": 47951380480, "source": "fineweb_hq", "phase": 1, "loss": 2.0107290744781494, "ce_loss": 2.009596526622772, "logit_z_loss": 11.325459480285645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2080981284379959, "tokens_per_second": 9361217.615115616, "eta_seconds": 16242.02097582817, "data_wait_seconds": 1.52587890625e-05} {"step": 5390, "total_steps": 22439, "tokens": 48040509440, "source": "fineweb_hq", "phase": 1, "loss": 2.0088918805122375, "ce_loss": 2.00749871134758, "logit_z_loss": 13.931640386581421, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21525202691555023, "tokens_per_second": 8383328.501296349, "eta_seconds": 18125.970356583595, "data_wait_seconds": 0.1358514428138733} {"step": 5400, "total_steps": 22439, "tokens": 48129638400, "source": "fineweb_hq", "phase": 1, "loss": 2.0181971192359924, "ce_loss": 2.01674547791481, "logit_z_loss": 14.516597509384155, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2781437039375305, "tokens_per_second": 7835305.055631692, "eta_seconds": 19382.376801633836, "data_wait_seconds": 1.9609928131103516e-05} {"step": 5410, "total_steps": 22439, "tokens": 48218767360, "source": "fineweb_hq", "phase": 1, "loss": 2.0146546959877014, "ce_loss": 2.0134798288345337, "logit_z_loss": 11.748496770858765, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23286861181259155, "tokens_per_second": 5958287.732221063, "eta_seconds": 25473.376380133628, "data_wait_seconds": 0.2600446343421936} {"step": 5420, "total_steps": 22439, "tokens": 48307896320, "source": "fineweb_hq", "phase": 1, "loss": 2.011179655790329, "ce_loss": 2.0099997222423553, "logit_z_loss": 11.7990083694458, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21857789158821106, "tokens_per_second": 8780995.082568856, "eta_seconds": 17274.645481252668, "data_wait_seconds": 1.7404556274414062e-05} {"step": 5430, "total_steps": 22439, "tokens": 48397025280, "source": "fineweb_hq", "phase": 1, "loss": 1.9739348888397217, "ce_loss": 1.972514271736145, "logit_z_loss": 14.206259489059448, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19245418906211853, "tokens_per_second": 7210400.423323547, "eta_seconds": 21025.10806107521, "data_wait_seconds": 1.4483928680419922e-05} {"step": 5440, "total_steps": 22439, "tokens": 48486154240, "source": "fineweb_hq", "phase": 1, "loss": 1.9682352542877197, "ce_loss": 1.9669893682003021, "logit_z_loss": 12.458537817001343, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1996881663799286, "tokens_per_second": 9730303.337790612, "eta_seconds": 15570.975934076308, "data_wait_seconds": 1.8417835235595703e-05} {"step": 5450, "total_steps": 22439, "tokens": 48575283200, "source": "fineweb_hq", "phase": 1, "loss": 1.972813606262207, "ce_loss": 1.9713543951511383, "logit_z_loss": 14.592121362686157, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20855791866779327, "tokens_per_second": 10406085.037267966, "eta_seconds": 14551.215908932685, "data_wait_seconds": 1.4901161193847656e-05} {"step": 5460, "total_steps": 22439, "tokens": 48664412160, "source": "fineweb_hq", "phase": 1, "loss": 1.9598568677902222, "ce_loss": 1.9584215879440308, "logit_z_loss": 14.352530479431152, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22815361618995667, "tokens_per_second": 8576484.567374006, "eta_seconds": 17644.99894976616, "data_wait_seconds": 1.6510486602783203e-05} {"step": 5470, "total_steps": 22439, "tokens": 48753541120, "source": "fineweb_hq", "phase": 1, "loss": 1.9681492745876312, "ce_loss": 1.966657966375351, "logit_z_loss": 14.913087844848633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23434779047966003, "tokens_per_second": 9195635.825969826, "eta_seconds": 16447.251183748245, "data_wait_seconds": 1.4722347259521484e-05} {"step": 5480, "total_steps": 22439, "tokens": 48842670080, "source": "fineweb_hq", "phase": 1, "loss": 1.961938202381134, "ce_loss": 1.9605918228626251, "logit_z_loss": 13.463966131210327, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23453539609909058, "tokens_per_second": 8554741.03214446, "eta_seconds": 17669.009815263747, "data_wait_seconds": 1.6391277313232422e-05} {"step": 5490, "total_steps": 22439, "tokens": 48931799040, "source": "fineweb_hq", "phase": 1, "loss": 1.9480843842029572, "ce_loss": 1.9467613995075226, "logit_z_loss": 13.229806423187256, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17044900357723236, "tokens_per_second": 9432854.181567818, "eta_seconds": 16014.736515188217, "data_wait_seconds": 1.722574234008789e-05} {"step": 5500, "total_steps": 22439, "tokens": 49020928000, "source": "fineweb_hq", "phase": 1, "loss": 1.9662136435508728, "ce_loss": 1.9648878872394562, "logit_z_loss": 13.257642030715942, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26496562361717224, "tokens_per_second": 9506328.252889713, "eta_seconds": 15881.583438706399, "data_wait_seconds": 1.627206802368164e-05} {"step": 5510, "total_steps": 22439, "tokens": 49110056960, "source": "fineweb_hq", "phase": 1, "loss": 1.9648931622505188, "ce_loss": 1.96379753947258, "logit_z_loss": 10.956216096878052, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21322432160377502, "tokens_per_second": 9709502.977656951, "eta_seconds": 15540.076225447656, "data_wait_seconds": 2.014636993408203e-05} {"step": 5520, "total_steps": 22439, "tokens": 49199185920, "source": "fineweb_hq", "phase": 1, "loss": 1.9884890019893646, "ce_loss": 1.9872646927833557, "logit_z_loss": 12.243282556533813, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2299475222826004, "tokens_per_second": 5305695.8290337045, "eta_seconds": 28421.773935627938, "data_wait_seconds": 0.3293812870979309} {"step": 5530, "total_steps": 22439, "tokens": 49288314880, "source": "fineweb_hq", "phase": 1, "loss": 2.0203389525413513, "ce_loss": 2.019119918346405, "logit_z_loss": 12.190390586853027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21537725627422333, "tokens_per_second": 9512664.344948672, "eta_seconds": 15842.896690034866, "data_wait_seconds": 1.436471939086914e-05} {"step": 5540, "total_steps": 22439, "tokens": 49377443840, "source": "fineweb_hq", "phase": 1, "loss": 2.0281168818473816, "ce_loss": 2.02681702375412, "logit_z_loss": 12.998560190200806, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23477181792259216, "tokens_per_second": 7663638.904499293, "eta_seconds": 19653.72212612629, "data_wait_seconds": 0.3375650644302368} {"step": 5550, "total_steps": 22439, "tokens": 49466572800, "source": "fineweb_hq", "phase": 1, "loss": 2.011066734790802, "ce_loss": 2.009914219379425, "logit_z_loss": 11.524907350540161, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2197342813014984, "tokens_per_second": 7808809.442976858, "eta_seconds": 19276.933525300024, "data_wait_seconds": 2.1576881408691406e-05} {"step": 5560, "total_steps": 22439, "tokens": 49555701760, "source": "fineweb_hq", "phase": 1, "loss": 2.014617770910263, "ce_loss": 2.0132881700992584, "logit_z_loss": 13.295682668685913, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2075764238834381, "tokens_per_second": 8248688.327101704, "eta_seconds": 18238.144735050202, "data_wait_seconds": 0.2573619484901428} {"step": 5570, "total_steps": 22439, "tokens": 49644830720, "source": "fineweb_hq", "phase": 1, "loss": 2.0139881372451782, "ce_loss": 2.0128089487552643, "logit_z_loss": 11.791869640350342, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2267211675643921, "tokens_per_second": 6594268.133654698, "eta_seconds": 22800.353212308884, "data_wait_seconds": 0.9360297322273254} {"step": 5580, "total_steps": 22439, "tokens": 49733959680, "source": "fineweb_hq", "phase": 1, "loss": 2.011192709207535, "ce_loss": 2.0100789070129395, "logit_z_loss": 11.138370990753174, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2028122991323471, "tokens_per_second": 8809845.294357732, "eta_seconds": 17056.203445506093, "data_wait_seconds": 1.615285873413086e-05} {"step": 5590, "total_steps": 22439, "tokens": 49823088640, "source": "fineweb_hq", "phase": 1, "loss": 2.024988681077957, "ce_loss": 2.0238985121250153, "logit_z_loss": 10.901957750320435, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21464401483535767, "tokens_per_second": 8036931.644985118, "eta_seconds": 18685.41270942688, "data_wait_seconds": 1.436471939086914e-05} {"step": 5600, "total_steps": 22439, "tokens": 49912217600, "source": "fineweb_hq", "phase": 1, "loss": 2.0165117979049683, "ce_loss": 2.0151993930339813, "logit_z_loss": 13.123906135559082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2381175309419632, "tokens_per_second": 8774638.514883902, "eta_seconds": 17104.3234988451, "data_wait_seconds": 1.5974044799804688e-05} {"step": 5610, "total_steps": 22439, "tokens": 50001346560, "source": "fineweb_hq", "phase": 1, "loss": 2.024297058582306, "ce_loss": 2.023118019104004, "logit_z_loss": 11.790086507797241, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2407684028148651, "tokens_per_second": 9532649.686079444, "eta_seconds": 15734.882925891876, "data_wait_seconds": 1.3649463653564453e-05} {"step": 5620, "total_steps": 22439, "tokens": 50090475520, "source": "fineweb_hq", "phase": 1, "loss": 2.008453220129013, "ce_loss": 2.00696924328804, "logit_z_loss": 14.839844465255737, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25149640440940857, "tokens_per_second": 9952197.145816822, "eta_seconds": 15062.6033254385, "data_wait_seconds": 1.4126300811767578e-05} {"step": 5630, "total_steps": 22439, "tokens": 50179604480, "source": "fineweb_hq", "phase": 1, "loss": 1.9914971888065338, "ce_loss": 1.9903620481491089, "logit_z_loss": 11.351336002349854, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2360241711139679, "tokens_per_second": 7232215.433504852, "eta_seconds": 20715.21102232933, "data_wait_seconds": 1.3172626495361328e-05} {"step": 5640, "total_steps": 22439, "tokens": 50268733440, "source": "fineweb_hq", "phase": 1, "loss": 1.9716931283473969, "ce_loss": 1.9704622328281403, "logit_z_loss": 12.30916953086853, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18373313546180725, "tokens_per_second": 8775659.36397272, "eta_seconds": 17061.70826532841, "data_wait_seconds": 0.18433105945587158} {"step": 5650, "total_steps": 22439, "tokens": 50357862400, "source": "fineweb_hq", "phase": 1, "loss": 1.9691078066825867, "ce_loss": 1.9678218960762024, "logit_z_loss": 12.85893726348877, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16973237693309784, "tokens_per_second": 8017717.36252381, "eta_seconds": 18663.49288432598, "data_wait_seconds": 1.4960765838623047e-05} {"step": 5660, "total_steps": 22439, "tokens": 50446991360, "source": "fineweb_hq", "phase": 1, "loss": 1.9806541800498962, "ce_loss": 1.979079931974411, "logit_z_loss": 15.742248058319092, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2624415457248688, "tokens_per_second": 6678208.308409307, "eta_seconds": 22393.653368926047, "data_wait_seconds": 1.4662742614746094e-05} {"step": 5670, "total_steps": 22439, "tokens": 50536120320, "source": "fineweb_hq", "phase": 1, "loss": 2.0061881244182587, "ce_loss": 2.0050492584705353, "logit_z_loss": 11.388577938079834, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23640362918376923, "tokens_per_second": 7566018.769831344, "eta_seconds": 19754.161015295984, "data_wait_seconds": 1.424551010131836e-05} {"step": 5680, "total_steps": 22439, "tokens": 50625249280, "source": "fineweb_hq", "phase": 1, "loss": 2.006544202566147, "ce_loss": 2.0053344070911407, "logit_z_loss": 12.097575664520264, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.201458141207695, "tokens_per_second": 8947541.638343297, "eta_seconds": 16694.107733893394, "data_wait_seconds": 1.4781951904296875e-05} {"step": 5690, "total_steps": 22439, "tokens": 50714378240, "source": "fineweb_hq", "phase": 1, "loss": 2.007665306329727, "ce_loss": 2.0062213242053986, "logit_z_loss": 14.439881324768066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22943365573883057, "tokens_per_second": 8519148.726835426, "eta_seconds": 17523.12348225117, "data_wait_seconds": 1.4126300811767578e-05} {"step": 5700, "total_steps": 22439, "tokens": 50803507200, "source": "fineweb_hq", "phase": 1, "loss": 2.0036712884902954, "ce_loss": 2.0024193227291107, "logit_z_loss": 12.519181489944458, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1788892149925232, "tokens_per_second": 8012141.888528652, "eta_seconds": 18620.859218382837, "data_wait_seconds": 1.6927719116210938e-05} {"step": 5710, "total_steps": 22439, "tokens": 50892636160, "source": "fineweb_hq", "phase": 1, "loss": 2.006936252117157, "ce_loss": 2.005753129720688, "logit_z_loss": 11.831526517868042, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22187143564224243, "tokens_per_second": 5693556.042597151, "eta_seconds": 26188.174151349067, "data_wait_seconds": 0.7393584251403809} {"step": 5720, "total_steps": 22439, "tokens": 50981765120, "source": "fineweb_hq", "phase": 1, "loss": 1.9613114595413208, "ce_loss": 1.9602410197257996, "logit_z_loss": 10.704434394836426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23504319787025452, "tokens_per_second": 8848394.738420425, "eta_seconds": 16840.874828624725, "data_wait_seconds": 1.424551010131836e-05} {"step": 5730, "total_steps": 22439, "tokens": 51070894080, "source": "fineweb_hq", "phase": 1, "loss": 1.9607211351394653, "ce_loss": 1.9594091475009918, "logit_z_loss": 13.119874000549316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2013673037290573, "tokens_per_second": 8983979.746879054, "eta_seconds": 16576.79374396801, "data_wait_seconds": 1.3649463653564453e-05} {"step": 5740, "total_steps": 22439, "tokens": 51160023040, "source": "fineweb_hq", "phase": 1, "loss": 1.9605124294757843, "ce_loss": 1.9590208530426025, "logit_z_loss": 14.916010856628418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20702841877937317, "tokens_per_second": 8170528.521446563, "eta_seconds": 18216.257358789444, "data_wait_seconds": 1.6808509826660156e-05} {"step": 5750, "total_steps": 22439, "tokens": 51249152000, "source": "fineweb_hq", "phase": 1, "loss": 1.9549205601215363, "ce_loss": 1.953627198934555, "logit_z_loss": 12.933178901672363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22294814884662628, "tokens_per_second": 9406340.305122722, "eta_seconds": 15813.516895937919, "data_wait_seconds": 1.5974044799804688e-05} {"step": 5760, "total_steps": 22439, "tokens": 51338280960, "source": "fineweb_hq", "phase": 1, "loss": 1.9602347016334534, "ce_loss": 1.958995372056961, "logit_z_loss": 12.393464803695679, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22673195600509644, "tokens_per_second": 9461875.797706055, "eta_seconds": 15711.281310629845, "data_wait_seconds": 2.473592758178711e-05} {"step": 5770, "total_steps": 22439, "tokens": 51427409920, "source": "fineweb_hq", "phase": 1, "loss": 1.9577779471874237, "ce_loss": 1.956751972436905, "logit_z_loss": 10.25979232788086, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29282301664352417, "tokens_per_second": 9752463.92206543, "eta_seconds": 15234.002874684333, "data_wait_seconds": 1.627206802368164e-05} {"step": 5780, "total_steps": 22439, "tokens": 51516538880, "source": "fineweb_hq", "phase": 1, "loss": 1.9511056244373322, "ce_loss": 1.9497516453266144, "logit_z_loss": 13.53992509841919, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.189003124833107, "tokens_per_second": 9513852.288738687, "eta_seconds": 15606.710085225104, "data_wait_seconds": 0.30675244331359863} {"step": 5790, "total_steps": 22439, "tokens": 51605667840, "source": "fineweb_hq", "phase": 1, "loss": 1.9783653914928436, "ce_loss": 1.9770946502685547, "logit_z_loss": 12.707156419754028, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21547554433345795, "tokens_per_second": 8074741.587324956, "eta_seconds": 18377.158438968658, "data_wait_seconds": 1.8894672393798828e-05} {"step": 5800, "total_steps": 22439, "tokens": 51694796800, "source": "fineweb_hq", "phase": 1, "loss": 1.9503794312477112, "ce_loss": 1.9491828382015228, "logit_z_loss": 11.966075897216797, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1721031367778778, "tokens_per_second": 9617557.828452861, "eta_seconds": 15419.889247274401, "data_wait_seconds": 1.5735626220703125e-05} {"step": 5810, "total_steps": 22439, "tokens": 51783925760, "source": "fineweb_hq", "phase": 1, "loss": 2.0080070197582245, "ce_loss": 2.006805509328842, "logit_z_loss": 12.01528525352478, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24894820153713226, "tokens_per_second": 6581750.0851577865, "eta_seconds": 22518.713969135286, "data_wait_seconds": 1.4185905456542969e-05} {"step": 5820, "total_steps": 22439, "tokens": 51873054720, "source": "fineweb_hq", "phase": 1, "loss": 2.0001573264598846, "ce_loss": 1.9990771412849426, "logit_z_loss": 10.802175045013428, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20058758556842804, "tokens_per_second": 7393849.323948283, "eta_seconds": 20033.329343652724, "data_wait_seconds": 0.0003275871276855469} {"step": 5830, "total_steps": 22439, "tokens": 51962183680, "source": "fineweb_hq", "phase": 1, "loss": 2.02036589384079, "ce_loss": 2.0190812945365906, "logit_z_loss": 12.846141576766968, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24564217031002045, "tokens_per_second": 6454371.658272717, "eta_seconds": 22935.507513618468, "data_wait_seconds": 0.3035966753959656} {"step": 5840, "total_steps": 22439, "tokens": 52051312640, "source": "fineweb_hq", "phase": 1, "loss": 2.01377409696579, "ce_loss": 2.0125288367271423, "logit_z_loss": 12.452828884124756, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2803601324558258, "tokens_per_second": 6894721.928711989, "eta_seconds": 21457.741477274893, "data_wait_seconds": 0.20828282833099365} {"step": 5850, "total_steps": 22439, "tokens": 52140441600, "source": "fineweb_hq", "phase": 1, "loss": 2.007071375846863, "ce_loss": 2.0058701634407043, "logit_z_loss": 12.012275218963623, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23964758217334747, "tokens_per_second": 8475004.034076488, "eta_seconds": 17446.13113451004, "data_wait_seconds": 1.627206802368164e-05} {"step": 5860, "total_steps": 22439, "tokens": 52229570560, "source": "fineweb_hq", "phase": 1, "loss": 2.001677393913269, "ce_loss": 2.0004810094833374, "logit_z_loss": 11.964157581329346, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20118387043476105, "tokens_per_second": 7592316.579779094, "eta_seconds": 19462.68984324932, "data_wait_seconds": 0.26497864723205566} {"step": 5870, "total_steps": 22439, "tokens": 52318699520, "source": "fineweb_hq", "phase": 1, "loss": 1.994822382926941, "ce_loss": 1.993666797876358, "logit_z_loss": 11.555924654006958, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.17736630141735077, "tokens_per_second": 7303374.091573258, "eta_seconds": 20220.486034584046, "data_wait_seconds": 1.6570091247558594e-05} {"step": 5880, "total_steps": 22439, "tokens": 52407828480, "source": "fineweb_hq", "phase": 1, "loss": 1.9961349368095398, "ce_loss": 1.9948787987232208, "logit_z_loss": 12.561392545700073, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21894453465938568, "tokens_per_second": 6957253.96637428, "eta_seconds": 21213.634801506996, "data_wait_seconds": 0.3633086681365967} {"step": 5890, "total_steps": 22439, "tokens": 52496957440, "source": "fineweb_hq", "phase": 1, "loss": 2.010244697332382, "ce_loss": 2.0090945065021515, "logit_z_loss": 11.502035140991211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20281729102134705, "tokens_per_second": 8118846.895817573, "eta_seconds": 18167.5449477911, "data_wait_seconds": 1.5795230865478516e-05} {"step": 5900, "total_steps": 22439, "tokens": 52586086400, "source": "fineweb_hq", "phase": 1, "loss": 2.0066109895706177, "ce_loss": 2.0054738521575928, "logit_z_loss": 11.371031999588013, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2273981124162674, "tokens_per_second": 7139702.939394718, "eta_seconds": 20646.57146036625, "data_wait_seconds": 1.627206802368164e-05} {"step": 5910, "total_steps": 22439, "tokens": 52675215360, "source": "fineweb_hq", "phase": 1, "loss": 1.9703890681266785, "ce_loss": 1.9691291153430939, "logit_z_loss": 12.59943175315857, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24817176163196564, "tokens_per_second": 7763043.458044084, "eta_seconds": 18977.255348396302, "data_wait_seconds": 1.7702579498291016e-05} {"step": 5920, "total_steps": 22439, "tokens": 52764344320, "source": "fineweb_hq", "phase": 1, "loss": 1.975309431552887, "ce_loss": 1.9741350710391998, "logit_z_loss": 11.743650197982788, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20484232902526855, "tokens_per_second": 9857624.67177434, "eta_seconds": 14935.862738370895, "data_wait_seconds": 2.014636993408203e-05} {"step": 5930, "total_steps": 22439, "tokens": 52853473280, "source": "fineweb_hq", "phase": 1, "loss": 1.9796601235866547, "ce_loss": 1.978322148323059, "logit_z_loss": 13.3796067237854, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19606496393680573, "tokens_per_second": 10017419.6549926, "eta_seconds": 14688.71277551651, "data_wait_seconds": 2.014636993408203e-05} {"step": 5940, "total_steps": 22439, "tokens": 52942602240, "source": "fineweb_hq", "phase": 1, "loss": 2.0088162422180176, "ce_loss": 2.0073867440223694, "logit_z_loss": 14.295376300811768, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32460319995880127, "tokens_per_second": 9456637.601079568, "eta_seconds": 15550.333776903151, "data_wait_seconds": 1.4960765838623047e-05} {"step": 5950, "total_steps": 22439, "tokens": 53031731200, "source": "fineweb_hq", "phase": 1, "loss": 1.9975827634334564, "ce_loss": 1.996362179517746, "logit_z_loss": 12.205964088439941, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22289404273033142, "tokens_per_second": 9779346.22882544, "eta_seconds": 15028.074342107771, "data_wait_seconds": 1.424551010131836e-05} {"step": 5960, "total_steps": 22439, "tokens": 53120860160, "source": "fineweb_hq", "phase": 1, "loss": 1.974843591451645, "ce_loss": 1.973590910434723, "logit_z_loss": 12.526656150817871, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19482547044754028, "tokens_per_second": 8850848.53635911, "eta_seconds": 16594.52340424061, "data_wait_seconds": 1.5556812286376953e-05} {"step": 5970, "total_steps": 22439, "tokens": 53209989120, "source": "fineweb_hq", "phase": 1, "loss": 1.9873593151569366, "ce_loss": 1.9862628877162933, "logit_z_loss": 10.964555978775024, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.254472553730011, "tokens_per_second": 9461302.748206679, "eta_seconds": 15514.405164957047, "data_wait_seconds": 1.4662742614746094e-05} {"step": 5980, "total_steps": 22439, "tokens": 53299118080, "source": "fineweb_hq", "phase": 1, "loss": 1.983314424753189, "ce_loss": 1.98216712474823, "logit_z_loss": 11.473066568374634, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25378838181495667, "tokens_per_second": 9263351.970865266, "eta_seconds": 15836.31451394558, "data_wait_seconds": 1.6510486602783203e-05} {"step": 5990, "total_steps": 22439, "tokens": 53388247040, "source": "fineweb_hq", "phase": 1, "loss": 1.9851772785186768, "ce_loss": 1.9839249849319458, "logit_z_loss": 12.522953510284424, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2546936273574829, "tokens_per_second": 7710750.147293097, "eta_seconds": 19013.48422701359, "data_wait_seconds": 1.4662742614746094e-05} {"step": 6000, "total_steps": 22439, "tokens": 53477376000, "source": "fineweb_hq", "phase": 1, "loss": 1.9921368956565857, "ce_loss": 1.991080492734909, "logit_z_loss": 10.564032316207886, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22537802159786224, "tokens_per_second": 7452347.006852486, "eta_seconds": 19660.799102520945, "data_wait_seconds": 1.436471939086914e-05} {"step": 6010, "total_steps": 22439, "tokens": 53566504960, "source": "fineweb_hq", "phase": 1, "loss": 2.002196252346039, "ce_loss": 2.0010679960250854, "logit_z_loss": 11.282443761825562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32415226101875305, "tokens_per_second": 9165881.788415447, "eta_seconds": 15975.54624466896, "data_wait_seconds": 1.4543533325195312e-05} {"step": 6020, "total_steps": 22439, "tokens": 53655633920, "source": "fineweb_hq", "phase": 1, "loss": 2.0296688079833984, "ce_loss": 2.028572380542755, "logit_z_loss": 10.96389651298523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22786971926689148, "tokens_per_second": 7209371.992753639, "eta_seconds": 20298.69447312355, "data_wait_seconds": 2.0623207092285156e-05} {"step": 6030, "total_steps": 22439, "tokens": 53744762880, "source": "fineweb_hq", "phase": 1, "loss": 2.009367197751999, "ce_loss": 2.0082267224788666, "logit_z_loss": 11.404394388198853, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23074659705162048, "tokens_per_second": 4980501.116591948, "eta_seconds": 29364.85848317146, "data_wait_seconds": 1.0866626501083374} {"step": 6040, "total_steps": 22439, "tokens": 53833891840, "source": "fineweb_hq", "phase": 1, "loss": 2.003167897462845, "ce_loss": 2.001765936613083, "logit_z_loss": 14.019824981689453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2171223759651184, "tokens_per_second": 6001339.33367553, "eta_seconds": 24354.993673467634, "data_wait_seconds": 0.14283466339111328} {"step": 6050, "total_steps": 22439, "tokens": 53923020800, "source": "fineweb_hq", "phase": 1, "loss": 1.998241901397705, "ce_loss": 1.997107744216919, "logit_z_loss": 11.341441631317139, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22674313187599182, "tokens_per_second": 3618365.81336844, "eta_seconds": 40370.00681476593, "data_wait_seconds": 2.181529998779297e-05} {"step": 6060, "total_steps": 22439, "tokens": 54012149760, "source": "fineweb_hq", "phase": 1, "loss": 2.0256268084049225, "ce_loss": 2.0242999494075775, "logit_z_loss": 13.268969774246216, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23198780417442322, "tokens_per_second": 3618238.1961571337, "eta_seconds": 40346.797438335416, "data_wait_seconds": 0.555010199546814} {"step": 6070, "total_steps": 22439, "tokens": 54101278720, "source": "fineweb_hq", "phase": 1, "loss": 2.0191237926483154, "ce_loss": 2.018145442008972, "logit_z_loss": 9.783325433731079, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2658344805240631, "tokens_per_second": 2975190.118661421, "eta_seconds": 49037.26780648232, "data_wait_seconds": 3.0114004015922546} {"step": 6080, "total_steps": 22439, "tokens": 54190407680, "source": "fineweb_hq", "phase": 1, "loss": 2.002726048231125, "ce_loss": 2.0014487504959106, "logit_z_loss": 12.773172855377197, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22198204696178436, "tokens_per_second": 3774187.141325423, "eta_seconds": 38632.44195485115, "data_wait_seconds": 1.430511474609375e-05} {"step": 6090, "total_steps": 22439, "tokens": 54279536640, "source": "fineweb_hq", "phase": 1, "loss": 2.001925528049469, "ce_loss": 2.0008004903793335, "logit_z_loss": 11.250019550323486, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2241288274526596, "tokens_per_second": 6214433.63530898, "eta_seconds": 23448.14431295395, "data_wait_seconds": 1.5676021575927734e-05} {"step": 6100, "total_steps": 22439, "tokens": 54368665600, "source": "fineweb_hq", "phase": 1, "loss": 1.9737262725830078, "ce_loss": 1.9725613296031952, "logit_z_loss": 11.649639129638672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1950242519378662, "tokens_per_second": 8944958.387201553, "eta_seconds": 16280.434345269205, "data_wait_seconds": 1.5676021575927734e-05} {"step": 6110, "total_steps": 22439, "tokens": 54457794560, "source": "fineweb_hq", "phase": 1, "loss": 1.9912846088409424, "ce_loss": 1.9901497066020966, "logit_z_loss": 11.34935712814331, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24305903911590576, "tokens_per_second": 8838614.87046387, "eta_seconds": 16466.231521224978, "data_wait_seconds": 1.8358230590820312e-05} {"step": 6120, "total_steps": 22439, "tokens": 54546923520, "source": "fineweb_hq", "phase": 1, "loss": 1.9889513850212097, "ce_loss": 1.987822413444519, "logit_z_loss": 11.289864540100098, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20497381687164307, "tokens_per_second": 10788041.720703172, "eta_seconds": 13482.479359054565, "data_wait_seconds": 1.5854835510253906e-05} {"step": 6130, "total_steps": 22439, "tokens": 54636052480, "source": "fineweb_hq", "phase": 1, "loss": 2.004156678915024, "ce_loss": 2.002680480480194, "logit_z_loss": 14.762540578842163, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2355896383523941, "tokens_per_second": 8415861.0534679, "eta_seconds": 17272.19828612804, "data_wait_seconds": 1.7404556274414062e-05} {"step": 6140, "total_steps": 22439, "tokens": 54725181440, "source": "fineweb_hq", "phase": 1, "loss": 1.9786819815635681, "ce_loss": 1.9774917960166931, "logit_z_loss": 11.90186333656311, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21587814390659332, "tokens_per_second": 9716066.43075005, "eta_seconds": 14951.656922006607, "data_wait_seconds": 1.519918441772461e-05} {"step": 6150, "total_steps": 22439, "tokens": 54814310400, "source": "fineweb_hq", "phase": 1, "loss": 1.9885307848453522, "ce_loss": 1.9873755276203156, "logit_z_loss": 11.552455425262451, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24901385605335236, "tokens_per_second": 6384355.763763881, "eta_seconds": 22740.29961926937, "data_wait_seconds": 0.7352779507637024} {"step": 6160, "total_steps": 22439, "tokens": 54903439360, "source": "fineweb_hq", "phase": 1, "loss": 1.996585488319397, "ce_loss": 1.995606243610382, "logit_z_loss": 9.79226803779602, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2238760143518448, "tokens_per_second": 8967709.879718142, "eta_seconds": 16179.496876025201, "data_wait_seconds": 1.430511474609375e-05} {"step": 6170, "total_steps": 22439, "tokens": 54992568320, "source": "fineweb_hq", "phase": 1, "loss": 1.997759610414505, "ce_loss": 1.9964163601398468, "logit_z_loss": 13.432455778121948, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2042696177959442, "tokens_per_second": 8599540.50796309, "eta_seconds": 16861.820104193685, "data_wait_seconds": 1.4603137969970703e-05} {"step": 6180, "total_steps": 22439, "tokens": 55081697280, "source": "fineweb_hq", "phase": 1, "loss": 1.9973941445350647, "ce_loss": 1.9962872862815857, "logit_z_loss": 11.068610906600952, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19889509677886963, "tokens_per_second": 9240155.547865627, "eta_seconds": 15683.153309845926, "data_wait_seconds": 1.5676021575927734e-05} {"step": 6190, "total_steps": 22439, "tokens": 55170826240, "source": "fineweb_hq", "phase": 1, "loss": 1.9986288845539093, "ce_loss": 1.997528225183487, "logit_z_loss": 11.00624680519104, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.16894400119781494, "tokens_per_second": 9441217.16703494, "eta_seconds": 15339.722044491768, "data_wait_seconds": 1.5556812286376953e-05} {"step": 6200, "total_steps": 22439, "tokens": 55259955200, "source": "fineweb_hq", "phase": 1, "loss": 1.993092030286789, "ce_loss": 1.991854339838028, "logit_z_loss": 12.376844882965088, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.246305450797081, "tokens_per_second": 8571733.64222646, "eta_seconds": 16885.326141142843, "data_wait_seconds": 1.6629695892333984e-05} {"step": 6210, "total_steps": 22439, "tokens": 55349084160, "source": "fineweb_hq", "phase": 1, "loss": 1.9910789728164673, "ce_loss": 1.9900774657726288, "logit_z_loss": 10.014959573745728, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18672165274620056, "tokens_per_second": 8784509.457995178, "eta_seconds": 16466.188564729688, "data_wait_seconds": 1.8358230590820312e-05} {"step": 6220, "total_steps": 22439, "tokens": 55438213120, "source": "fineweb_hq", "phase": 1, "loss": 1.9918632507324219, "ce_loss": 1.9906085729599, "logit_z_loss": 12.546756505966187, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23964442312717438, "tokens_per_second": 6847891.308370476, "eta_seconds": 21109.89408481121, "data_wait_seconds": 1.6987323760986328e-05} {"step": 6230, "total_steps": 22439, "tokens": 55527342080, "source": "fineweb_hq", "phase": 1, "loss": 2.0152849555015564, "ce_loss": 2.014135956764221, "logit_z_loss": 11.490167617797852, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25147545337677, "tokens_per_second": 7549469.391869944, "eta_seconds": 19136.329159712794, "data_wait_seconds": 1.615285873413086e-05} {"step": 6240, "total_steps": 22439, "tokens": 55616471040, "source": "fineweb_hq", "phase": 1, "loss": 2.026666134595871, "ce_loss": 2.0254487097263336, "logit_z_loss": 12.174232482910156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24396613240242004, "tokens_per_second": 9040016.271611517, "eta_seconds": 15971.210445427894, "data_wait_seconds": 0.12740224599838257} {"step": 6250, "total_steps": 22439, "tokens": 55705600000, "source": "fineweb_hq", "phase": 1, "loss": 2.0086555778980255, "ce_loss": 2.007555067539215, "logit_z_loss": 11.00511908531189, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23772817850112915, "tokens_per_second": 7202561.671946139, "eta_seconds": 20033.271482563017, "data_wait_seconds": 1.7762184143066406e-05} {"step": 6260, "total_steps": 22439, "tokens": 55794728960, "source": "fineweb_hq", "phase": 1, "loss": 2.000760316848755, "ce_loss": 1.9996784627437592, "logit_z_loss": 10.818356990814209, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1870465874671936, "tokens_per_second": 7750597.909996654, "eta_seconds": 18605.241306352615, "data_wait_seconds": 1.811981201171875e-05} {"step": 6270, "total_steps": 22439, "tokens": 55883857920, "source": "fineweb_hq", "phase": 1, "loss": 2.005427211523056, "ce_loss": 2.0042780339717865, "logit_z_loss": 11.491944074630737, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22916530072689056, "tokens_per_second": 7912049.397939685, "eta_seconds": 18214.32200126648, "data_wait_seconds": 1.5676021575927734e-05} {"step": 6280, "total_steps": 22439, "tokens": 55972986880, "source": "fineweb_hq", "phase": 1, "loss": 1.9847108721733093, "ce_loss": 1.9835356771945953, "logit_z_loss": 11.75174856185913, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30603450536727905, "tokens_per_second": 6264601.365539621, "eta_seconds": 22990.04805896282, "data_wait_seconds": 1.4960765838623047e-05} {"step": 6290, "total_steps": 22439, "tokens": 56062115840, "source": "fineweb_hq", "phase": 1, "loss": 1.9054923057556152, "ce_loss": 1.9041027426719666, "logit_z_loss": 13.895813226699829, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23422536253929138, "tokens_per_second": 7553668.169891421, "eta_seconds": 19054.895484781267, "data_wait_seconds": 1.6510486602783203e-05} {"step": 6300, "total_steps": 22439, "tokens": 56151244800, "source": "fineweb_hq", "phase": 1, "loss": 1.8963500559329987, "ce_loss": 1.895009458065033, "logit_z_loss": 13.406005144119263, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2013084441423416, "tokens_per_second": 9866673.79222783, "eta_seconds": 14578.897769713403, "data_wait_seconds": 1.4901161193847656e-05} {"step": 6310, "total_steps": 22439, "tokens": 56240373760, "source": "fineweb_hq", "phase": 1, "loss": 1.8774710297584534, "ce_loss": 1.8762050867080688, "logit_z_loss": 12.65914797782898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20220988988876343, "tokens_per_second": 9583241.787092268, "eta_seconds": 15000.779775547982, "data_wait_seconds": 1.4424324035644531e-05} {"step": 6320, "total_steps": 22439, "tokens": 56329502720, "source": "fineweb_hq", "phase": 1, "loss": 1.8952285647392273, "ce_loss": 1.8939172625541687, "logit_z_loss": 13.112923383712769, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2375485748052597, "tokens_per_second": 9395850.498799197, "eta_seconds": 15290.4700476408, "data_wait_seconds": 1.800060272216797e-05} {"step": 6330, "total_steps": 22439, "tokens": 56418631680, "source": "fineweb_hq", "phase": 1, "loss": 1.8783281743526459, "ce_loss": 1.8769936263561249, "logit_z_loss": 13.345377445220947, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2104564607143402, "tokens_per_second": 9297262.041959373, "eta_seconds": 15443.024087738992, "data_wait_seconds": 1.9371509552001953e-05} {"step": 6340, "total_steps": 22439, "tokens": 56507760640, "source": "fineweb_hq", "phase": 1, "loss": 1.8800076246261597, "ce_loss": 1.8784876763820648, "logit_z_loss": 15.199727535247803, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21672973036766052, "tokens_per_second": 9632100.412195843, "eta_seconds": 14896.928661823273, "data_wait_seconds": 1.4185905456542969e-05} {"step": 6350, "total_steps": 22439, "tokens": 56596889600, "source": "fineweb_hq", "phase": 1, "loss": 1.8757444322109222, "ce_loss": 1.8743791282176971, "logit_z_loss": 13.6531982421875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22262978553771973, "tokens_per_second": 9651104.089910999, "eta_seconds": 14858.36049513817, "data_wait_seconds": 1.823902130126953e-05} {"step": 6360, "total_steps": 22439, "tokens": 56686018560, "source": "fineweb_hq", "phase": 1, "loss": 1.8901613652706146, "ce_loss": 1.8887836039066315, "logit_z_loss": 13.7774498462677, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22466664016246796, "tokens_per_second": 8228466.853919702, "eta_seconds": 17416.422442746163, "data_wait_seconds": 1.5079975128173828e-05} {"step": 6370, "total_steps": 22439, "tokens": 56775147520, "source": "fineweb_hq", "phase": 1, "loss": 1.9812983572483063, "ce_loss": 1.9801912903785706, "logit_z_loss": 11.070777177810669, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2183818221092224, "tokens_per_second": 7675885.0185371805, "eta_seconds": 18658.607506251334, "data_wait_seconds": 0.00017559528350830078} {"step": 6380, "total_steps": 22439, "tokens": 56864276480, "source": "fineweb_hq", "phase": 1, "loss": 1.988649994134903, "ce_loss": 1.9874993860721588, "logit_z_loss": 11.505933046340942, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23794029653072357, "tokens_per_second": 9374436.884457922, "eta_seconds": 15268.35143573284, "data_wait_seconds": 1.4126300811767578e-05} {"step": 6390, "total_steps": 22439, "tokens": 56953405440, "source": "fineweb_hq", "phase": 1, "loss": 1.9924761950969696, "ce_loss": 1.991448551416397, "logit_z_loss": 10.276340246200562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2665437161922455, "tokens_per_second": 8357888.346245746, "eta_seconds": 17114.73783545494, "data_wait_seconds": 0.0005000829696655273} {"step": 6400, "total_steps": 22439, "tokens": 57042534400, "source": "fineweb_hq", "phase": 1, "loss": 1.9824386537075043, "ce_loss": 1.9812292754650116, "logit_z_loss": 12.093842267990112, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20342686772346497, "tokens_per_second": 7250461.480482689, "eta_seconds": 19716.529675912854, "data_wait_seconds": 1.800060272216797e-05} {"step": 6410, "total_steps": 22439, "tokens": 57131663360, "source": "fineweb_hq", "phase": 1, "loss": 1.990576982498169, "ce_loss": 1.9893251061439514, "logit_z_loss": 12.519010066986084, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21483829617500305, "tokens_per_second": 6487640.708213171, "eta_seconds": 22021.0730540514, "data_wait_seconds": 0.2353464961051941} {"step": 6420, "total_steps": 22439, "tokens": 57220792320, "source": "fineweb_hq", "phase": 1, "loss": 1.9899623095989227, "ce_loss": 1.988793522119522, "logit_z_loss": 11.688085794448853, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24305927753448486, "tokens_per_second": 6749581.7272275565, "eta_seconds": 21153.2635345459, "data_wait_seconds": 1.537799835205078e-05} {"step": 6430, "total_steps": 22439, "tokens": 57309921280, "source": "fineweb_hq", "phase": 1, "loss": 1.9783995151519775, "ce_loss": 1.9772008657455444, "logit_z_loss": 11.986393928527832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21169444918632507, "tokens_per_second": 6658393.057544753, "eta_seconds": 21429.577802157404, "data_wait_seconds": 0.19973701238632202} {"step": 6440, "total_steps": 22439, "tokens": 57399050240, "source": "fineweb_hq", "phase": 1, "loss": 1.9622238278388977, "ce_loss": 1.9610405266284943, "logit_z_loss": 11.832814931869507, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2539670467376709, "tokens_per_second": 7730907.64759569, "eta_seconds": 18445.10756099224, "data_wait_seconds": 1.4424324035644531e-05} {"step": 6450, "total_steps": 22439, "tokens": 57488179200, "source": "fineweb_hq", "phase": 1, "loss": 1.9586611092090607, "ce_loss": 1.957602858543396, "logit_z_loss": 10.582813024520874, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2033395767211914, "tokens_per_second": 9213603.906169865, "eta_seconds": 15467.160906338691, "data_wait_seconds": 0.21252375841140747} {"step": 6460, "total_steps": 22439, "tokens": 57577308160, "source": "fineweb_hq", "phase": 1, "loss": 1.9560359120368958, "ce_loss": 1.9547692239284515, "logit_z_loss": 12.666981220245361, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22891877591609955, "tokens_per_second": 7972670.033392174, "eta_seconds": 17863.42148709297, "data_wait_seconds": 1.4424324035644531e-05} {"step": 6470, "total_steps": 22439, "tokens": 57666437120, "source": "fineweb_hq", "phase": 1, "loss": 1.9669020175933838, "ce_loss": 1.9656788408756256, "logit_z_loss": 12.23178744316101, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2224837690591812, "tokens_per_second": 7767999.559891572, "eta_seconds": 18322.611262607574, "data_wait_seconds": 0.19842928647994995} {"step": 6480, "total_steps": 22439, "tokens": 57755566080, "source": "fineweb_hq", "phase": 1, "loss": 1.9515435099601746, "ce_loss": 1.9501761496067047, "logit_z_loss": 13.67340874671936, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21402356028556824, "tokens_per_second": 8349984.771123649, "eta_seconds": 17034.87026178837, "data_wait_seconds": 2.0444393157958984e-05} {"step": 6490, "total_steps": 22439, "tokens": 57844695040, "source": "fineweb_hq", "phase": 1, "loss": 1.9646234214305878, "ce_loss": 1.9636367857456207, "logit_z_loss": 9.86618161201477, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2586990296840668, "tokens_per_second": 8058709.3595723035, "eta_seconds": 17639.521660518647, "data_wait_seconds": 1.627206802368164e-05} {"step": 6500, "total_steps": 22439, "tokens": 57933824000, "source": "fineweb_hq", "phase": 1, "loss": 1.9550819993019104, "ce_loss": 1.953910082578659, "logit_z_loss": 11.71947431564331, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24905270338058472, "tokens_per_second": 9237107.527928038, "eta_seconds": 15379.55998828411, "data_wait_seconds": 1.728534698486328e-05} {"step": 6510, "total_steps": 22439, "tokens": 58022952960, "source": "fineweb_hq", "phase": 1, "loss": 1.9517082571983337, "ce_loss": 1.9502789080142975, "logit_z_loss": 14.293398380279541, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23877230286598206, "tokens_per_second": 9074826.863122141, "eta_seconds": 15644.763533830643, "data_wait_seconds": 1.4960765838623047e-05} {"step": 6520, "total_steps": 22439, "tokens": 58112081920, "source": "fineweb_hq", "phase": 1, "loss": 1.9567711055278778, "ce_loss": 1.955569088459015, "logit_z_loss": 12.01995038986206, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24084295332431793, "tokens_per_second": 6641551.164903461, "eta_seconds": 21363.14061295986, "data_wait_seconds": 1.6629695892333984e-05} {"step": 6530, "total_steps": 22439, "tokens": 58201210880, "source": "fineweb_hq", "phase": 1, "loss": 1.806110918521881, "ce_loss": 1.804332047700882, "logit_z_loss": 17.78849220275879, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22094067931175232, "tokens_per_second": 7519085.961792715, "eta_seconds": 18858.045138001442, "data_wait_seconds": 1.990795135498047e-05} {"step": 6540, "total_steps": 22439, "tokens": 58290339840, "source": "fineweb_hq", "phase": 1, "loss": 1.7793630063533783, "ce_loss": 1.7777847349643707, "logit_z_loss": 15.782868385314941, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23182539641857147, "tokens_per_second": 8473989.695309535, "eta_seconds": 16722.481215953827, "data_wait_seconds": 1.8596649169921875e-05} {"step": 6550, "total_steps": 22439, "tokens": 58379468800, "source": "fineweb_hq", "phase": 1, "loss": 1.7613504528999329, "ce_loss": 1.7599114775657654, "logit_z_loss": 14.389745473861694, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22374287247657776, "tokens_per_second": 8866578.356258163, "eta_seconds": 15972.001696014406, "data_wait_seconds": 3.075599670410156e-05} {"step": 6560, "total_steps": 22439, "tokens": 58468597760, "source": "fineweb_hq", "phase": 1, "loss": 1.7595321834087372, "ce_loss": 1.758188396692276, "logit_z_loss": 13.438002109527588, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19838939607143402, "tokens_per_second": 9782440.372736266, "eta_seconds": 14467.542882084846, "data_wait_seconds": 2.0444393157958984e-05} {"step": 6570, "total_steps": 22439, "tokens": 58557726720, "source": "fineweb_hq", "phase": 1, "loss": 1.79065403342247, "ce_loss": 1.78900945186615, "logit_z_loss": 16.445826530456543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26906800270080566, "tokens_per_second": 10229489.252085656, "eta_seconds": 13826.569747376443, "data_wait_seconds": 1.7344951629638672e-05} {"step": 6580, "total_steps": 22439, "tokens": 58646855680, "source": "fineweb_hq", "phase": 1, "loss": 1.7713771164417267, "ce_loss": 1.769859939813614, "logit_z_loss": 15.171475648880005, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21401245892047882, "tokens_per_second": 7735356.026819838, "eta_seconds": 18273.188354086877, "data_wait_seconds": 2.0444393157958984e-05} {"step": 6590, "total_steps": 22439, "tokens": 58735984640, "source": "fineweb_hq", "phase": 1, "loss": 1.9261522591114044, "ce_loss": 1.9249387085437775, "logit_z_loss": 12.13562822341919, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2606394290924072, "tokens_per_second": 7730430.288487807, "eta_seconds": 18273.302187895773, "data_wait_seconds": 1.8656253814697266e-05} {"step": 6600, "total_steps": 22439, "tokens": 58825113600, "source": "fineweb_hq", "phase": 1, "loss": 1.9618745744228363, "ce_loss": 1.9609417617321014, "logit_z_loss": 9.327852010726929, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2063012421131134, "tokens_per_second": 9367763.31320274, "eta_seconds": 15069.91103682518, "data_wait_seconds": 1.4722347259521484e-05} {"step": 6610, "total_steps": 22439, "tokens": 58914242560, "source": "fineweb_hq", "phase": 1, "loss": 1.9610922634601593, "ce_loss": 1.9599985778331757, "logit_z_loss": 10.936864137649536, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2029678225517273, "tokens_per_second": 9288151.996910194, "eta_seconds": 15189.483422636986, "data_wait_seconds": 1.4483928680419922e-05} {"step": 6620, "total_steps": 22439, "tokens": 59003371520, "source": "fineweb_hq", "phase": 1, "loss": 1.966588020324707, "ce_loss": 1.965598315000534, "logit_z_loss": 9.896987438201904, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26481854915618896, "tokens_per_second": 9563262.190468095, "eta_seconds": 14743.201536870001, "data_wait_seconds": 1.4781951904296875e-05} {"step": 6630, "total_steps": 22439, "tokens": 59092500480, "source": "fineweb_hq", "phase": 1, "loss": 1.9706448316574097, "ce_loss": 1.9694980084896088, "logit_z_loss": 11.468404054641724, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23569618165493011, "tokens_per_second": 9514407.748795008, "eta_seconds": 14809.536923813821, "data_wait_seconds": 1.329183578491211e-05} {"step": 6640, "total_steps": 22439, "tokens": 59181629440, "source": "fineweb_hq", "phase": 1, "loss": 1.9663733541965485, "ce_loss": 1.9654026329517365, "logit_z_loss": 9.707217931747437, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25992754101753235, "tokens_per_second": 8817604.24204385, "eta_seconds": 15969.739629793168, "data_wait_seconds": 1.6391277313232422e-05} {"step": 6650, "total_steps": 22439, "tokens": 59270758400, "source": "fineweb_hq", "phase": 1, "loss": 1.9691114127635956, "ce_loss": 1.9678321182727814, "logit_z_loss": 12.793001651763916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20802271366119385, "tokens_per_second": 8477872.96840864, "eta_seconds": 16599.177112984657, "data_wait_seconds": 1.8298625946044922e-05} {"step": 6660, "total_steps": 22439, "tokens": 59359887360, "source": "fineweb_hq", "phase": 1, "loss": 1.9575040638446808, "ce_loss": 1.9565265774726868, "logit_z_loss": 9.774902582168579, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2557617127895355, "tokens_per_second": 8255604.974745841, "eta_seconds": 17035.28528971672, "data_wait_seconds": 1.7762184143066406e-05} {"step": 6670, "total_steps": 22439, "tokens": 59449016320, "source": "fineweb_hq", "phase": 1, "loss": 1.9595872163772583, "ce_loss": 1.9583707749843597, "logit_z_loss": 12.164523363113403, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22304393351078033, "tokens_per_second": 9788274.69216512, "eta_seconds": 14358.756925415992, "data_wait_seconds": 1.4901161193847656e-05} {"step": 6680, "total_steps": 22439, "tokens": 59538145280, "source": "fineweb_hq", "phase": 1, "loss": 1.9705747067928314, "ce_loss": 1.9696902334690094, "logit_z_loss": 8.844924926757812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19049693644046783, "tokens_per_second": 7313167.46778498, "eta_seconds": 19206.223388528822, "data_wait_seconds": 0.0012183189392089844} {"step": 6690, "total_steps": 22439, "tokens": 59627274240, "source": "fineweb_hq", "phase": 1, "loss": 1.9884958267211914, "ce_loss": 1.9873493313789368, "logit_z_loss": 11.465104818344116, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23227667808532715, "tokens_per_second": 8604952.923899993, "eta_seconds": 16312.605117702486, "data_wait_seconds": 1.627206802368164e-05} {"step": 6700, "total_steps": 22439, "tokens": 59716403200, "source": "fineweb_hq", "phase": 1, "loss": 2.0007064640522003, "ce_loss": 1.9997450411319733, "logit_z_loss": 9.613909721374512, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26664021611213684, "tokens_per_second": 4294499.460017924, "eta_seconds": 32665.057115507127, "data_wait_seconds": 0.8107930421829224} {"step": 6710, "total_steps": 22439, "tokens": 59805532160, "source": "fineweb_hq", "phase": 1, "loss": 1.9957325160503387, "ce_loss": 1.9945044219493866, "logit_z_loss": 12.281381607055664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24364924430847168, "tokens_per_second": 4480301.365349581, "eta_seconds": 31290.515916681292, "data_wait_seconds": 1.5974044799804688e-05} {"step": 6720, "total_steps": 22439, "tokens": 59894661120, "source": "fineweb_hq", "phase": 1, "loss": 1.996661126613617, "ce_loss": 1.995722234249115, "logit_z_loss": 9.388777256011963, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2150561511516571, "tokens_per_second": 4054299.221946095, "eta_seconds": 34556.35722830296, "data_wait_seconds": 2.4497509002685547e-05} {"step": 6730, "total_steps": 22439, "tokens": 59983790080, "source": "fineweb_hq", "phase": 1, "loss": 1.9928942918777466, "ce_loss": 1.9917815029621124, "logit_z_loss": 11.127943277359009, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2550276219844818, "tokens_per_second": 7142469.766364247, "eta_seconds": 19602.838772010804, "data_wait_seconds": 1.895427703857422e-05} {"step": 6740, "total_steps": 22439, "tokens": 60072919040, "source": "fineweb_hq", "phase": 1, "loss": 1.997251182794571, "ce_loss": 1.996102511882782, "logit_z_loss": 11.486827611923218, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27585670351982117, "tokens_per_second": 7055543.219111387, "eta_seconds": 19831.719537198544, "data_wait_seconds": 1.6033649444580078e-05} {"step": 6750, "total_steps": 22439, "tokens": 60162048000, "source": "fineweb_hq", "phase": 1, "loss": 1.9887326955795288, "ce_loss": 1.987666368484497, "logit_z_loss": 10.663506269454956, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22009029984474182, "tokens_per_second": 2561859.2623156877, "eta_seconds": 54583.180036830905, "data_wait_seconds": 1.9311904907226562e-05} {"step": 6760, "total_steps": 22439, "tokens": 60251176960, "source": "fineweb_hq", "phase": 1, "loss": 1.992307722568512, "ce_loss": 1.991100251674652, "logit_z_loss": 12.074588537216187, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2149585783481598, "tokens_per_second": 4937583.5891297655, "eta_seconds": 28302.36569395065, "data_wait_seconds": 1.5556812286376953e-05} {"step": 6770, "total_steps": 22439, "tokens": 60340305920, "source": "fineweb_hq", "phase": 1, "loss": 1.980958878993988, "ce_loss": 1.9797934889793396, "logit_z_loss": 11.653820514678955, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2303876131772995, "tokens_per_second": 6175428.474670761, "eta_seconds": 22614.814177966116, "data_wait_seconds": 0.4787556529045105} {"step": 6780, "total_steps": 22439, "tokens": 60429434880, "source": "fineweb_hq", "phase": 1, "loss": 1.9108600616455078, "ce_loss": 1.9095641076564789, "logit_z_loss": 12.959605693817139, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18961113691329956, "tokens_per_second": 7388567.300618656, "eta_seconds": 18889.594258999827, "data_wait_seconds": 1.531839370727539e-05} {"step": 6790, "total_steps": 22439, "tokens": 60518563840, "source": "fineweb_hq", "phase": 1, "loss": 1.9040821492671967, "ce_loss": 1.9028999209403992, "logit_z_loss": 11.822202920913696, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1976955235004425, "tokens_per_second": 8937339.578061048, "eta_seconds": 15606.200064992907, "data_wait_seconds": 1.4185905456542969e-05} {"step": 6800, "total_steps": 22439, "tokens": 60607692800, "source": "fineweb_hq", "phase": 1, "loss": 1.9102002084255219, "ce_loss": 1.9088170528411865, "logit_z_loss": 13.831884145736694, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19686879217624664, "tokens_per_second": 9533959.335818313, "eta_seconds": 14620.240724158288, "data_wait_seconds": 1.7523765563964844e-05} {"step": 6810, "total_steps": 22439, "tokens": 60696821760, "source": "fineweb_hq", "phase": 1, "loss": 1.9166541695594788, "ce_loss": 1.9153572022914886, "logit_z_loss": 12.969868183135986, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2252587527036667, "tokens_per_second": 10041954.350108042, "eta_seconds": 13871.767061209679, "data_wait_seconds": 1.4662742614746094e-05} {"step": 6820, "total_steps": 22439, "tokens": 60785950720, "source": "fineweb_hq", "phase": 1, "loss": 1.887886494398117, "ce_loss": 1.886525422334671, "logit_z_loss": 13.610793590545654, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21931593120098114, "tokens_per_second": 9941745.6365429, "eta_seconds": 14002.623655176163, "data_wait_seconds": 1.3649463653564453e-05} {"step": 6830, "total_steps": 22439, "tokens": 60875079680, "source": "fineweb_hq", "phase": 1, "loss": 1.897227704524994, "ce_loss": 1.8961079120635986, "logit_z_loss": 11.198261499404907, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24089981615543365, "tokens_per_second": 9150232.422302295, "eta_seconds": 15204.137692165375, "data_wait_seconds": 1.817941665649414e-05} {"step": 6840, "total_steps": 22439, "tokens": 60964208640, "source": "fineweb_hq", "phase": 1, "loss": 1.887050300836563, "ce_loss": 1.8858513534069061, "logit_z_loss": 11.98935866355896, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18910232186317444, "tokens_per_second": 9306564.43164536, "eta_seconds": 14939.161032533646, "data_wait_seconds": 1.5616416931152344e-05} {"step": 6850, "total_steps": 22439, "tokens": 61053337600, "source": "fineweb_hq", "phase": 1, "loss": 1.9115367829799652, "ce_loss": 1.9103162586688995, "logit_z_loss": 12.205183267593384, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2278459668159485, "tokens_per_second": 9519643.008729493, "eta_seconds": 14595.414514660837, "data_wait_seconds": 1.5974044799804688e-05} {"step": 6860, "total_steps": 22439, "tokens": 61142466560, "source": "fineweb_hq", "phase": 1, "loss": 1.9023090302944183, "ce_loss": 1.901096910238266, "logit_z_loss": 12.121150016784668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2561206817626953, "tokens_per_second": 10069492.404253023, "eta_seconds": 13789.573615980149, "data_wait_seconds": 1.4722347259521484e-05} {"step": 6870, "total_steps": 22439, "tokens": 61231595520, "source": "fineweb_hq", "phase": 1, "loss": 1.8287105858325958, "ce_loss": 1.8272550702095032, "logit_z_loss": 14.55555772781372, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24272726476192474, "tokens_per_second": 6800448.458552939, "eta_seconds": 20405.253957843783, "data_wait_seconds": 1.7881393432617188e-05} {"step": 6880, "total_steps": 22439, "tokens": 61320724480, "source": "fineweb_hq", "phase": 1, "loss": 1.7584210634231567, "ce_loss": 1.7565883696079254, "logit_z_loss": 18.327032566070557, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22975710034370422, "tokens_per_second": 8852549.584370289, "eta_seconds": 15665.063216233255, "data_wait_seconds": 1.7702579498291016e-05} {"step": 6890, "total_steps": 22439, "tokens": 61409853440, "source": "fineweb_hq", "phase": 1, "loss": 1.736674278974533, "ce_loss": 1.73518905043602, "logit_z_loss": 14.852051734924316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20028190314769745, "tokens_per_second": 9190480.319858668, "eta_seconds": 15079.366374850275, "data_wait_seconds": 1.8298625946044922e-05} {"step": 6900, "total_steps": 22439, "tokens": 61498982400, "source": "fineweb_hq", "phase": 1, "loss": 1.7390581369400024, "ce_loss": 1.7374717593193054, "logit_z_loss": 15.863895654678345, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21036358177661896, "tokens_per_second": 9314979.692020122, "eta_seconds": 14868.254738402367, "data_wait_seconds": 1.7881393432617188e-05} {"step": 6910, "total_steps": 22439, "tokens": 61588111360, "source": "fineweb_hq", "phase": 1, "loss": 1.7448373138904572, "ce_loss": 1.7432083189487457, "logit_z_loss": 16.289783716201782, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23889167606830597, "tokens_per_second": 9188822.653809022, "eta_seconds": 15062.687266755103, "data_wait_seconds": 1.8715858459472656e-05} {"step": 6920, "total_steps": 22439, "tokens": 61677240320, "source": "fineweb_hq", "phase": 1, "loss": 1.7564705312252045, "ce_loss": 1.7550113499164581, "logit_z_loss": 14.591771841049194, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2312733680009842, "tokens_per_second": 10027648.190480758, "eta_seconds": 13793.785980176926, "data_wait_seconds": 1.4543533325195312e-05} {"step": 6930, "total_steps": 22439, "tokens": 61766369280, "source": "fineweb_hq", "phase": 1, "loss": 1.8352457582950592, "ce_loss": 1.8338981568813324, "logit_z_loss": 13.476242780685425, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24532122910022736, "tokens_per_second": 6941737.529257425, "eta_seconds": 19912.896948552134, "data_wait_seconds": 0.3315439224243164} {"step": 6940, "total_steps": 22439, "tokens": 61855498240, "source": "fineweb_hq", "phase": 1, "loss": 1.9666257500648499, "ce_loss": 1.9654018580913544, "logit_z_loss": 12.238805055618286, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23233672976493835, "tokens_per_second": 9642323.278401671, "eta_seconds": 14326.523921203614, "data_wait_seconds": 1.4781951904296875e-05} {"step": 6950, "total_steps": 22439, "tokens": 61944627200, "source": "fineweb_hq", "phase": 1, "loss": 1.9783292710781097, "ce_loss": 1.977391242980957, "logit_z_loss": 9.380282878875732, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2297414392232895, "tokens_per_second": 9816840.729787719, "eta_seconds": 14062.757046175004, "data_wait_seconds": 2.002716064453125e-05} {"step": 6960, "total_steps": 22439, "tokens": 62033756160, "source": "fineweb_hq", "phase": 1, "loss": 1.9734284579753876, "ce_loss": 1.972451001405716, "logit_z_loss": 9.774367809295654, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26508623361587524, "tokens_per_second": 9323525.984008787, "eta_seconds": 14797.268481969833, "data_wait_seconds": 1.4185905456542969e-05} {"step": 6970, "total_steps": 22439, "tokens": 62122885120, "source": "fineweb_hq", "phase": 1, "loss": 1.9780553877353668, "ce_loss": 1.9769511818885803, "logit_z_loss": 11.042064666748047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21980394423007965, "tokens_per_second": 8486551.738526983, "eta_seconds": 16246.12592628002, "data_wait_seconds": 1.615285873413086e-05} {"step": 6980, "total_steps": 22439, "tokens": 62212014080, "source": "fineweb_hq", "phase": 1, "loss": 1.9776247441768646, "ce_loss": 1.9766126573085785, "logit_z_loss": 10.121233940124512, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24678879976272583, "tokens_per_second": 8639217.43665207, "eta_seconds": 15948.719924497605, "data_wait_seconds": 1.537799835205078e-05} {"step": 6990, "total_steps": 22439, "tokens": 62301143040, "source": "fineweb_hq", "phase": 1, "loss": 1.9700899124145508, "ce_loss": 1.9690771698951721, "logit_z_loss": 10.127516746520996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21051400899887085, "tokens_per_second": 9330825.507217467, "eta_seconds": 14757.036255526542, "data_wait_seconds": 0.04037749767303467} {"step": 7000, "total_steps": 22439, "tokens": 62390272000, "source": "fineweb_hq", "phase": 1, "loss": 1.9817489385604858, "ce_loss": 1.980793446302414, "logit_z_loss": 9.554725408554077, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20286960899829865, "tokens_per_second": 8802881.597369265, "eta_seconds": 15631.949586272242, "data_wait_seconds": 0.165824294090271} {"step": 7010, "total_steps": 22439, "tokens": 62479400960, "source": "fineweb_hq", "phase": 1, "loss": 1.930584967136383, "ce_loss": 1.9294216930866241, "logit_z_loss": 11.632541179656982, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21106398105621338, "tokens_per_second": 7030210.638248289, "eta_seconds": 19560.875123119356, "data_wait_seconds": 1.4960765838623047e-05} {"step": 7020, "total_steps": 22439, "tokens": 62568529920, "source": "fineweb_hq", "phase": 1, "loss": 1.9036860764026642, "ce_loss": 1.9023014605045319, "logit_z_loss": 13.846097230911255, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19611120223999023, "tokens_per_second": 7371473.981924689, "eta_seconds": 18643.210809803008, "data_wait_seconds": 1.5854835510253906e-05} {"step": 7030, "total_steps": 22439, "tokens": 62657658880, "source": "fineweb_hq", "phase": 1, "loss": 1.8962359726428986, "ce_loss": 1.8950378596782684, "logit_z_loss": 11.98128056526184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2671765387058258, "tokens_per_second": 8812581.67355151, "eta_seconds": 15584.40188715458, "data_wait_seconds": 2.092123031616211e-05} {"step": 7040, "total_steps": 22439, "tokens": 62746787840, "source": "fineweb_hq", "phase": 1, "loss": 1.9083806872367859, "ce_loss": 1.9071391224861145, "logit_z_loss": 12.415739297866821, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24434299767017365, "tokens_per_second": 9281966.168042755, "eta_seconds": 14786.703918027877, "data_wait_seconds": 2.104043960571289e-05} {"step": 7050, "total_steps": 22439, "tokens": 62835916800, "source": "fineweb_hq", "phase": 1, "loss": 1.8898747861385345, "ce_loss": 1.8887270092964172, "logit_z_loss": 11.47790813446045, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2110738307237625, "tokens_per_second": 9473617.382165354, "eta_seconds": 14478.160876774788, "data_wait_seconds": 1.5854835510253906e-05} {"step": 7060, "total_steps": 22439, "tokens": 62925045760, "source": "fineweb_hq", "phase": 1, "loss": 1.894276648759842, "ce_loss": 1.8931117057800293, "logit_z_loss": 11.649487495422363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19916681945323944, "tokens_per_second": 9812371.153950782, "eta_seconds": 13969.24611120224, "data_wait_seconds": 1.4424324035644531e-05} {"step": 7070, "total_steps": 22439, "tokens": 63014174720, "source": "fineweb_hq", "phase": 1, "loss": 1.890110343694687, "ce_loss": 1.8890402019023895, "logit_z_loss": 10.70152735710144, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2932957708835602, "tokens_per_second": 10691014.459208634, "eta_seconds": 12812.843827557563, "data_wait_seconds": 0.000516057014465332} {"step": 7080, "total_steps": 22439, "tokens": 63103303680, "source": "fineweb_hq", "phase": 1, "loss": 1.8844675719738007, "ce_loss": 1.8832889795303345, "logit_z_loss": 11.785886287689209, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27069810032844543, "tokens_per_second": 9639801.074130094, "eta_seconds": 14200.829312896729, "data_wait_seconds": 2.944469451904297e-05} {"step": 7090, "total_steps": 22439, "tokens": 63192432640, "source": "fineweb_hq", "phase": 1, "loss": 1.9343699216842651, "ce_loss": 1.9330984354019165, "logit_z_loss": 12.714935779571533, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2843683660030365, "tokens_per_second": 7341990.2576011075, "eta_seconds": 18633.10027718544, "data_wait_seconds": 1.7583370208740234e-05} {"step": 7100, "total_steps": 22439, "tokens": 63281561600, "source": "fineweb_hq", "phase": 1, "loss": 1.9513115584850311, "ce_loss": 1.950265645980835, "logit_z_loss": 10.459370851516724, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24334318935871124, "tokens_per_second": 8178942.004531309, "eta_seconds": 16715.476362133024, "data_wait_seconds": 1.627206802368164e-05} {"step": 7110, "total_steps": 22439, "tokens": 63370690560, "source": "fineweb_hq", "phase": 1, "loss": 1.951532006263733, "ce_loss": 1.9503538012504578, "logit_z_loss": 11.782203197479248, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22543010115623474, "tokens_per_second": 8389522.735030444, "eta_seconds": 16285.286672329901, "data_wait_seconds": 1.7583370208740234e-05} {"step": 7120, "total_steps": 22439, "tokens": 63459819520, "source": "fineweb_hq", "phase": 1, "loss": 1.9640423655509949, "ce_loss": 1.9628539681434631, "logit_z_loss": 11.88397741317749, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2826698124408722, "tokens_per_second": 8481160.974191345, "eta_seconds": 16098.816452074048, "data_wait_seconds": 1.6450881958007812e-05} {"step": 7130, "total_steps": 22439, "tokens": 63548948480, "source": "fineweb_hq", "phase": 1, "loss": 1.971077561378479, "ce_loss": 1.9701322317123413, "logit_z_loss": 9.45353627204895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22617441415786743, "tokens_per_second": 5986192.454105583, "eta_seconds": 22793.70833966732, "data_wait_seconds": 0.47798246145248413} {"step": 7140, "total_steps": 22439, "tokens": 63638077440, "source": "fineweb_hq", "phase": 1, "loss": 1.9512504637241364, "ce_loss": 1.9500724971294403, "logit_z_loss": 11.77951979637146, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18828798830509186, "tokens_per_second": 7705932.4074213635, "eta_seconds": 17695.249412345886, "data_wait_seconds": 1.4781951904296875e-05} {"step": 7150, "total_steps": 22439, "tokens": 63727206400, "source": "fineweb_hq", "phase": 1, "loss": 1.9600306451320648, "ce_loss": 1.9590215981006622, "logit_z_loss": 10.090453863143921, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22103653848171234, "tokens_per_second": 5501978.331177533, "eta_seconds": 24767.321632623672, "data_wait_seconds": 0.4380279779434204} {"step": 7160, "total_steps": 22439, "tokens": 63816335360, "source": "fineweb_hq", "phase": 1, "loss": 1.975834846496582, "ce_loss": 1.9746473133563995, "logit_z_loss": 11.875659227371216, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2512766420841217, "tokens_per_second": 5119521.456739405, "eta_seconds": 26600.169397616388, "data_wait_seconds": 1.895427703857422e-05} {"step": 7170, "total_steps": 22439, "tokens": 63905464320, "source": "fineweb_hq", "phase": 1, "loss": 1.986248791217804, "ce_loss": 1.9850322604179382, "logit_z_loss": 12.165544748306274, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2298029363155365, "tokens_per_second": 5470227.514659881, "eta_seconds": 24878.491554379463, "data_wait_seconds": 1.901388168334961e-05} {"step": 7180, "total_steps": 22439, "tokens": 63994593280, "source": "fineweb_hq", "phase": 1, "loss": 1.9620662033557892, "ce_loss": 1.960978239774704, "logit_z_loss": 10.87970495223999, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24280770123004913, "tokens_per_second": 4382621.128418925, "eta_seconds": 31032.086981487275, "data_wait_seconds": 0.2879440188407898} {"step": 7190, "total_steps": 22439, "tokens": 64083722240, "source": "fineweb_hq", "phase": 1, "loss": 1.9886162877082825, "ce_loss": 1.9876437187194824, "logit_z_loss": 9.725605726242065, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2753882110118866, "tokens_per_second": 3262498.7708385945, "eta_seconds": 41659.09649341107, "data_wait_seconds": 2.384185791015625e-05} {"step": 7200, "total_steps": 22439, "tokens": 64172851200, "source": "fineweb_hq", "phase": 1, "loss": 1.998477190732956, "ce_loss": 1.9973210394382477, "logit_z_loss": 11.561469554901123, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23070698976516724, "tokens_per_second": 3808917.751974698, "eta_seconds": 35659.37386639118, "data_wait_seconds": 0.2683829665184021} {"step": 7210, "total_steps": 22439, "tokens": 64261980160, "source": "fineweb_hq", "phase": 1, "loss": 1.9962268769741058, "ce_loss": 1.995232880115509, "logit_z_loss": 9.940195322036743, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23668058216571808, "tokens_per_second": 5243985.747864094, "eta_seconds": 25883.840977120402, "data_wait_seconds": 2.2351741790771484e-05} {"step": 7220, "total_steps": 22439, "tokens": 64351109120, "source": "fineweb_hq", "phase": 1, "loss": 1.9997197091579437, "ce_loss": 1.99870166182518, "logit_z_loss": 10.180602788925171, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2096046507358551, "tokens_per_second": 5218112.775618178, "eta_seconds": 25995.100155329703, "data_wait_seconds": 0.5487311482429504} {"step": 7230, "total_steps": 22439, "tokens": 64440238080, "source": "fineweb_hq", "phase": 1, "loss": 1.991894781589508, "ce_loss": 1.9908315539360046, "logit_z_loss": 10.632148027420044, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23968468606472015, "tokens_per_second": 8351280.6288314, "eta_seconds": 16231.790223407745, "data_wait_seconds": 0.20181888341903687} {"step": 7240, "total_steps": 22439, "tokens": 64529367040, "source": "fineweb_hq", "phase": 1, "loss": 2.001039892435074, "ce_loss": 1.9999109208583832, "logit_z_loss": 11.28990888595581, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21666836738586426, "tokens_per_second": 10095797.484593425, "eta_seconds": 13418.167956590652, "data_wait_seconds": 1.4603137969970703e-05} {"step": 7250, "total_steps": 22439, "tokens": 64618496000, "source": "fineweb_hq", "phase": 1, "loss": 1.9948257803916931, "ce_loss": 1.9935543239116669, "logit_z_loss": 12.714847087860107, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2144669145345688, "tokens_per_second": 8345232.322596933, "eta_seconds": 16222.193955874443, "data_wait_seconds": 1.6629695892333984e-05} {"step": 7260, "total_steps": 22439, "tokens": 64707624960, "source": "fineweb_hq", "phase": 1, "loss": 2.0032939016819, "ce_loss": 2.0022692680358887, "logit_z_loss": 10.246254682540894, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26602721214294434, "tokens_per_second": 8880059.732903607, "eta_seconds": 15235.128192067146, "data_wait_seconds": 1.5497207641601562e-05} {"step": 7270, "total_steps": 22439, "tokens": 64796753920, "source": "fineweb_hq", "phase": 1, "loss": 1.9877611100673676, "ce_loss": 1.9865706861019135, "logit_z_loss": 11.9039945602417, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18761396408081055, "tokens_per_second": 8367800.6336979, "eta_seconds": 16157.139174604416, "data_wait_seconds": 1.3709068298339844e-05} {"step": 7280, "total_steps": 22439, "tokens": 64885882880, "source": "fineweb_hq", "phase": 1, "loss": 1.9922626912593842, "ce_loss": 1.9912661015987396, "logit_z_loss": 9.965501308441162, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25126883387565613, "tokens_per_second": 1476789.5405164675, "eta_seconds": 91489.40099937917, "data_wait_seconds": 5.732384443283081} {"step": 7290, "total_steps": 22439, "tokens": 64975011840, "source": "fineweb_hq", "phase": 1, "loss": 1.9732365608215332, "ce_loss": 1.9722038507461548, "logit_z_loss": 10.32718276977539, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25690314173698425, "tokens_per_second": 1097126.9964344967, "eta_seconds": 123068.21538691521, "data_wait_seconds": 2.1304209232330322} {"step": 7300, "total_steps": 22439, "tokens": 65064140800, "source": "fineweb_hq", "phase": 1, "loss": 1.9465417861938477, "ce_loss": 1.945367693901062, "logit_z_loss": 11.740894317626953, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21318717300891876, "tokens_per_second": 2468983.5753523665, "eta_seconds": 54650.96402058601, "data_wait_seconds": 3.892183303833008e-05} {"step": 7310, "total_steps": 22439, "tokens": 65153269760, "source": "fineweb_hq", "phase": 1, "loss": 1.9631838500499725, "ce_loss": 1.9619705975055695, "logit_z_loss": 12.132465124130249, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2325650304555893, "tokens_per_second": 2259028.3096637917, "eta_seconds": 59690.79847612381, "data_wait_seconds": 0.03899902105331421} {"step": 7320, "total_steps": 22439, "tokens": 65242398720, "source": "fineweb_hq", "phase": 1, "loss": 1.9607330858707428, "ce_loss": 1.9595470130443573, "logit_z_loss": 11.860872983932495, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25413817167282104, "tokens_per_second": 8578857.378958795, "eta_seconds": 15707.694937849046, "data_wait_seconds": 1.537799835205078e-05} {"step": 7330, "total_steps": 22439, "tokens": 65331527680, "source": "fineweb_hq", "phase": 1, "loss": 1.9592967331409454, "ce_loss": 1.958094745874405, "logit_z_loss": 12.01988697052002, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20698370039463043, "tokens_per_second": 8957899.24001932, "eta_seconds": 15033.09448518753, "data_wait_seconds": 0.04350888729095459} {"step": 7340, "total_steps": 22439, "tokens": 65420656640, "source": "fineweb_hq", "phase": 1, "loss": 1.9566158652305603, "ce_loss": 1.9556148648262024, "logit_z_loss": 10.010141611099243, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20918945968151093, "tokens_per_second": 8816394.377958694, "eta_seconds": 15264.269148445132, "data_wait_seconds": 1.9073486328125e-05} {"step": 7350, "total_steps": 22439, "tokens": 65509785600, "source": "fineweb_hq", "phase": 1, "loss": 1.9631330370903015, "ce_loss": 1.9619735777378082, "logit_z_loss": 11.59448790550232, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25446662306785583, "tokens_per_second": 10064438.958458023, "eta_seconds": 13362.561817812919, "data_wait_seconds": 1.4841556549072266e-05} {"step": 7360, "total_steps": 22439, "tokens": 65598914560, "source": "fineweb_hq", "phase": 1, "loss": 1.9501678347587585, "ce_loss": 1.9490523934364319, "logit_z_loss": 11.154137372970581, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2126377522945404, "tokens_per_second": 7484749.574953489, "eta_seconds": 17956.186434578896, "data_wait_seconds": 1.5020370483398438e-05} {"step": 7370, "total_steps": 22439, "tokens": 65688043520, "source": "fineweb_hq", "phase": 1, "loss": 1.9048364758491516, "ce_loss": 1.9036806523799896, "logit_z_loss": 11.558385133743286, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21018904447555542, "tokens_per_second": 6905490.33124908, "eta_seconds": 19449.513847875594, "data_wait_seconds": 1.8537044525146484e-05} {"step": 7380, "total_steps": 22439, "tokens": 65777172480, "source": "fineweb_hq", "phase": 1, "loss": 1.9065347909927368, "ce_loss": 1.9054855406284332, "logit_z_loss": 10.492486953735352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2314237505197525, "tokens_per_second": 8792428.54487117, "eta_seconds": 15265.327455210685, "data_wait_seconds": 1.710653305053711e-05} {"step": 7390, "total_steps": 22439, "tokens": 65866301440, "source": "fineweb_hq", "phase": 1, "loss": 1.921977549791336, "ce_loss": 1.9207119941711426, "logit_z_loss": 12.655275821685791, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21814028918743134, "tokens_per_second": 10386159.552978953, "eta_seconds": 12914.318446564674, "data_wait_seconds": 1.621246337890625e-05} {"step": 7400, "total_steps": 22439, "tokens": 65955430400, "source": "fineweb_hq", "phase": 1, "loss": 1.9189012348651886, "ce_loss": 1.9178725183010101, "logit_z_loss": 10.286842584609985, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26899954676628113, "tokens_per_second": 8420399.749398507, "eta_seconds": 15918.608015441894, "data_wait_seconds": 1.531839370727539e-05} {"step": 7410, "total_steps": 22439, "tokens": 66044559360, "source": "fineweb_hq", "phase": 1, "loss": 1.9210856556892395, "ce_loss": 1.9200465381145477, "logit_z_loss": 10.391279220581055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2340809851884842, "tokens_per_second": 8597325.486725066, "eta_seconds": 15580.649376463889, "data_wait_seconds": 1.901388168334961e-05} {"step": 7420, "total_steps": 22439, "tokens": 66133688320, "source": "fineweb_hq", "phase": 1, "loss": 1.9318804442882538, "ce_loss": 1.93068727850914, "logit_z_loss": 11.931803464889526, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.259391725063324, "tokens_per_second": 9020918.291050795, "eta_seconds": 14839.152811837195, "data_wait_seconds": 1.728534698486328e-05} {"step": 7430, "total_steps": 22439, "tokens": 66222817280, "source": "fineweb_hq", "phase": 1, "loss": 1.9167798161506653, "ce_loss": 1.9156050086021423, "logit_z_loss": 11.7478666305542, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2588948905467987, "tokens_per_second": 8262933.188114605, "eta_seconds": 16189.608825159074, "data_wait_seconds": 0.3291075825691223} {"step": 7440, "total_steps": 22439, "tokens": 66311946240, "source": "fineweb_hq", "phase": 1, "loss": 1.912913590669632, "ce_loss": 1.911586582660675, "logit_z_loss": 13.270169496536255, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21743524074554443, "tokens_per_second": 7514112.4233004525, "eta_seconds": 17791.126825499534, "data_wait_seconds": 1.7762184143066406e-05} {"step": 7450, "total_steps": 22439, "tokens": 66401075200, "source": "fineweb_hq", "phase": 1, "loss": 1.907210886478424, "ce_loss": 1.905951589345932, "logit_z_loss": 12.59314513206482, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2175215780735016, "tokens_per_second": 6811566.889503352, "eta_seconds": 19613.020074701308, "data_wait_seconds": 1.5676021575927734e-05} {"step": 7460, "total_steps": 22439, "tokens": 66490204160, "source": "fineweb_hq", "phase": 1, "loss": 1.928541898727417, "ce_loss": 1.927463710308075, "logit_z_loss": 10.781832456588745, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21586571633815765, "tokens_per_second": 7868396.983799162, "eta_seconds": 16967.403838276863, "data_wait_seconds": 2.2470951080322266e-05} {"step": 7470, "total_steps": 22439, "tokens": 66579333120, "source": "fineweb_hq", "phase": 1, "loss": 1.9647235870361328, "ce_loss": 1.9638323783874512, "logit_z_loss": 8.912199974060059, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2311590611934662, "tokens_per_second": 9837959.042170878, "eta_seconds": 13561.465305161477, "data_wait_seconds": 1.5020370483398438e-05} {"step": 7480, "total_steps": 22439, "tokens": 66668462080, "source": "fineweb_hq", "phase": 1, "loss": 1.9764987528324127, "ce_loss": 1.9753252863883972, "logit_z_loss": 11.734873056411743, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2184082567691803, "tokens_per_second": 9123689.505648084, "eta_seconds": 14613.387619280815, "data_wait_seconds": 1.5974044799804688e-05} {"step": 7490, "total_steps": 22439, "tokens": 66757591040, "source": "fineweb_hq", "phase": 1, "loss": 1.997413992881775, "ce_loss": 1.996349036693573, "logit_z_loss": 10.649714946746826, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2534415125846863, "tokens_per_second": 9231744.47439251, "eta_seconds": 14432.68741607666, "data_wait_seconds": 1.633167266845703e-05} {"step": 7500, "total_steps": 22439, "tokens": 66846720000, "source": "fineweb_hq", "phase": 1, "loss": 1.972757250070572, "ce_loss": 1.9715384244918823, "logit_z_loss": 12.188449621200562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2743736207485199, "tokens_per_second": 10007241.432508491, "eta_seconds": 13305.340361976625, "data_wait_seconds": 2.1278858184814453e-05} {"step": 7510, "total_steps": 22439, "tokens": 66935848960, "source": "fineweb_hq", "phase": 1, "loss": 1.9708179533481598, "ce_loss": 1.9696734547615051, "logit_z_loss": 11.444740533828735, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23543556034564972, "tokens_per_second": 8924697.919224018, "eta_seconds": 14909.258059859276, "data_wait_seconds": 1.7523765563964844e-05} {"step": 7520, "total_steps": 22439, "tokens": 67024977920, "source": "fineweb_hq", "phase": 1, "loss": 1.9976481199264526, "ce_loss": 1.996623933315277, "logit_z_loss": 10.241751670837402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22860144078731537, "tokens_per_second": 7838483.067202912, "eta_seconds": 16963.932215452194, "data_wait_seconds": 2.396106719970703e-05} {"step": 7530, "total_steps": 22439, "tokens": 67114106880, "source": "fineweb_hq", "phase": 1, "loss": 2.0063165426254272, "ce_loss": 2.0051088631153107, "logit_z_loss": 12.077316999435425, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27150261402130127, "tokens_per_second": 7285533.7650670465, "eta_seconds": 18239.20810046196, "data_wait_seconds": 1.8656253814697266e-05} {"step": 7540, "total_steps": 22439, "tokens": 67203235840, "source": "fineweb_hq", "phase": 1, "loss": 1.9959568977355957, "ce_loss": 1.9949128329753876, "logit_z_loss": 10.440777778625488, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23669669032096863, "tokens_per_second": 9304911.18148472, "eta_seconds": 14271.306293416023, "data_wait_seconds": 1.8298625946044922e-05} {"step": 7550, "total_steps": 22439, "tokens": 67292364800, "source": "fineweb_hq", "phase": 1, "loss": 1.9984630644321442, "ce_loss": 1.997382789850235, "logit_z_loss": 10.802919149398804, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2467525154352188, "tokens_per_second": 9738158.335154362, "eta_seconds": 13627.228473472594, "data_wait_seconds": 0.1268436312675476} {"step": 7560, "total_steps": 22439, "tokens": 67381493760, "source": "fineweb_hq", "phase": 1, "loss": 1.9958812296390533, "ce_loss": 1.9949126839637756, "logit_z_loss": 9.685303688049316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2845987379550934, "tokens_per_second": 8639992.74851596, "eta_seconds": 15348.968852639198, "data_wait_seconds": 1.4901161193847656e-05} {"step": 7570, "total_steps": 22439, "tokens": 67470622720, "source": "fineweb_hq", "phase": 1, "loss": 1.9894706010818481, "ce_loss": 1.9883977174758911, "logit_z_loss": 10.729084014892578, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24270012974739075, "tokens_per_second": 7830653.912361156, "eta_seconds": 16923.982608246803, "data_wait_seconds": 1.817941665649414e-05} {"step": 7580, "total_steps": 22439, "tokens": 67559751680, "source": "fineweb_hq", "phase": 1, "loss": 1.9551620781421661, "ce_loss": 1.953979253768921, "logit_z_loss": 11.828157663345337, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23123402893543243, "tokens_per_second": 8058800.216663305, "eta_seconds": 16433.801323199274, "data_wait_seconds": 1.901388168334961e-05} {"step": 7590, "total_steps": 22439, "tokens": 67648880640, "source": "fineweb_hq", "phase": 1, "loss": 1.9517155885696411, "ce_loss": 1.9507694840431213, "logit_z_loss": 9.460927248001099, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23728343844413757, "tokens_per_second": 9218275.735451723, "eta_seconds": 14357.08764872551, "data_wait_seconds": 1.8894672393798828e-05} {"step": 7600, "total_steps": 22439, "tokens": 67738009600, "source": "fineweb_hq", "phase": 1, "loss": 1.9378353357315063, "ce_loss": 1.9365760684013367, "logit_z_loss": 12.592628240585327, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22969956696033478, "tokens_per_second": 10197860.167241719, "eta_seconds": 12969.23683743477, "data_wait_seconds": 1.5497207641601562e-05} {"step": 7610, "total_steps": 22439, "tokens": 67827138560, "source": "fineweb_hq", "phase": 1, "loss": 1.944096714258194, "ce_loss": 1.9426604807376862, "logit_z_loss": 14.362026691436768, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2270064502954483, "tokens_per_second": 9570612.272666505, "eta_seconds": 13809.914247751236, "data_wait_seconds": 0.15091800689697266} {"step": 7620, "total_steps": 22439, "tokens": 67916267520, "source": "fineweb_hq", "phase": 1, "loss": 1.9454587399959564, "ce_loss": 1.944312036037445, "logit_z_loss": 11.467211961746216, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2418987900018692, "tokens_per_second": 9472499.709398042, "eta_seconds": 13943.542874217033, "data_wait_seconds": 0.14144611358642578} {"step": 7630, "total_steps": 22439, "tokens": 68005396480, "source": "fineweb_hq", "phase": 1, "loss": 1.9402319192886353, "ce_loss": 1.9390808641910553, "logit_z_loss": 11.510528326034546, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24256743490695953, "tokens_per_second": 9198513.259698598, "eta_seconds": 14349.175039219857, "data_wait_seconds": 1.71661376953125e-05} {"step": 7640, "total_steps": 22439, "tokens": 68094525440, "source": "fineweb_hq", "phase": 1, "loss": 1.9401544630527496, "ce_loss": 1.939155638217926, "logit_z_loss": 9.988338947296143, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2140854150056839, "tokens_per_second": 9582914.079030123, "eta_seconds": 13764.2836840868, "data_wait_seconds": 1.609325408935547e-05} {"step": 7650, "total_steps": 22439, "tokens": 68183654400, "source": "fineweb_hq", "phase": 1, "loss": 1.9657266438007355, "ce_loss": 1.964601308107376, "logit_z_loss": 11.253700971603394, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29131051898002625, "tokens_per_second": 8865277.859216096, "eta_seconds": 14868.43627884388, "data_wait_seconds": 1.5974044799804688e-05} {"step": 7660, "total_steps": 22439, "tokens": 68272783360, "source": "fineweb_hq", "phase": 1, "loss": 1.934909999370575, "ce_loss": 1.9337891936302185, "logit_z_loss": 11.208128452301025, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20254871249198914, "tokens_per_second": 8533476.001033055, "eta_seconds": 15436.111845636367, "data_wait_seconds": 1.3530254364013672e-05} {"step": 7670, "total_steps": 22439, "tokens": 68361912320, "source": "fineweb_hq", "phase": 1, "loss": 1.9682147204875946, "ce_loss": 1.9669981598854065, "logit_z_loss": 12.165347337722778, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22536244988441467, "tokens_per_second": 7332715.139275882, "eta_seconds": 17951.68072450161, "data_wait_seconds": 0.0011347532272338867} {"step": 7680, "total_steps": 22439, "tokens": 68451041280, "source": "fineweb_hq", "phase": 1, "loss": 1.986441045999527, "ce_loss": 1.9855188727378845, "logit_z_loss": 9.221740007400513, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23201218247413635, "tokens_per_second": 8201366.762498693, "eta_seconds": 16039.452431941032, "data_wait_seconds": 1.4722347259521484e-05} {"step": 7690, "total_steps": 22439, "tokens": 68540170240, "source": "fineweb_hq", "phase": 1, "loss": 1.9896650314331055, "ce_loss": 1.988651603460312, "logit_z_loss": 10.134317874908447, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2843405306339264, "tokens_per_second": 7297053.059472101, "eta_seconds": 18014.98523206711, "data_wait_seconds": 1.5079975128173828e-05} {"step": 7700, "total_steps": 22439, "tokens": 68629299200, "source": "fineweb_hq", "phase": 1, "loss": 1.9789898693561554, "ce_loss": 1.9779371619224548, "logit_z_loss": 10.526857376098633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1996348351240158, "tokens_per_second": 8811378.58712784, "eta_seconds": 14908.810561823844, "data_wait_seconds": 1.52587890625e-05} {"step": 7710, "total_steps": 22439, "tokens": 68718428160, "source": "fineweb_hq", "phase": 1, "loss": 1.9898049533367157, "ce_loss": 1.988630473613739, "logit_z_loss": 11.745019435882568, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2258560061454773, "tokens_per_second": 8573535.538258933, "eta_seconds": 15312.008050608634, "data_wait_seconds": 0.04471713304519653} {"step": 7720, "total_steps": 22439, "tokens": 68807557120, "source": "fineweb_hq", "phase": 1, "loss": 1.9701182842254639, "ce_loss": 1.9690752625465393, "logit_z_loss": 10.43011999130249, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2363399714231491, "tokens_per_second": 6920835.872989056, "eta_seconds": 18955.6462010622, "data_wait_seconds": 0.17359685897827148} {"step": 7730, "total_steps": 22439, "tokens": 68896686080, "source": "fineweb_hq", "phase": 1, "loss": 1.9450894594192505, "ce_loss": 1.9439434707164764, "logit_z_loss": 11.460116624832153, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21699951589107513, "tokens_per_second": 8533978.20677088, "eta_seconds": 15362.095389461516, "data_wait_seconds": 1.3887882232666016e-05} {"step": 7740, "total_steps": 22439, "tokens": 68985815040, "source": "fineweb_hq", "phase": 1, "loss": 1.9632772207260132, "ce_loss": 1.9621867835521698, "logit_z_loss": 10.904575824737549, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2647365629673004, "tokens_per_second": 8088204.25122753, "eta_seconds": 16197.743557739259, "data_wait_seconds": 1.6868114471435547e-05} {"step": 7750, "total_steps": 22439, "tokens": 69074944000, "source": "fineweb_hq", "phase": 1, "loss": 1.9558674097061157, "ce_loss": 1.9545800685882568, "logit_z_loss": 12.873423337936401, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21281187236309052, "tokens_per_second": 9762365.785703361, "eta_seconds": 13410.840386223792, "data_wait_seconds": 1.4007091522216797e-05} {"step": 7760, "total_steps": 22439, "tokens": 69164072960, "source": "fineweb_hq", "phase": 1, "loss": 1.9625158607959747, "ce_loss": 1.961598426103592, "logit_z_loss": 9.174124240875244, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25376713275909424, "tokens_per_second": 10235788.180042826, "eta_seconds": 12781.858913326263, "data_wait_seconds": 1.5854835510253906e-05} {"step": 7770, "total_steps": 22439, "tokens": 69253201920, "source": "fineweb_hq", "phase": 1, "loss": 1.9399366974830627, "ce_loss": 1.9386760890483856, "logit_z_loss": 12.606060266494751, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21274767816066742, "tokens_per_second": 6201178.197195249, "eta_seconds": 21083.617865252494, "data_wait_seconds": 1.5139579772949219e-05} {"step": 7780, "total_steps": 22439, "tokens": 69342330880, "source": "fineweb_hq", "phase": 1, "loss": 1.917101889848709, "ce_loss": 1.9158382713794708, "logit_z_loss": 12.636018991470337, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2261967957019806, "tokens_per_second": 8175353.976068026, "eta_seconds": 15981.466104888917, "data_wait_seconds": 1.3768672943115234e-05} {"step": 7790, "total_steps": 22439, "tokens": 69431459840, "source": "fineweb_hq", "phase": 1, "loss": 1.9290503561496735, "ce_loss": 1.9280401766300201, "logit_z_loss": 10.102169752120972, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22676590085029602, "tokens_per_second": 9112132.656795127, "eta_seconds": 14328.699813938141, "data_wait_seconds": 1.4901161193847656e-05} {"step": 7800, "total_steps": 22439, "tokens": 69520588800, "source": "fineweb_hq", "phase": 1, "loss": 1.9214677810668945, "ce_loss": 1.9202551543712616, "logit_z_loss": 12.12648606300354, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19471603631973267, "tokens_per_second": 8784062.163984392, "eta_seconds": 14853.70687367916, "data_wait_seconds": 1.4841556549072266e-05} {"step": 7810, "total_steps": 22439, "tokens": 69609717760, "source": "fineweb_hq", "phase": 1, "loss": 1.9188733994960785, "ce_loss": 1.9176443219184875, "logit_z_loss": 12.29084062576294, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19664739072322845, "tokens_per_second": 10725785.186965618, "eta_seconds": 12156.383268094063, "data_wait_seconds": 1.4603137969970703e-05} {"step": 7820, "total_steps": 22439, "tokens": 69698846720, "source": "fineweb_hq", "phase": 1, "loss": 1.930962473154068, "ce_loss": 1.929665893316269, "logit_z_loss": 12.965639114379883, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27560290694236755, "tokens_per_second": 7749012.856385734, "eta_seconds": 16814.738733673097, "data_wait_seconds": 1.329183578491211e-05} {"step": 7830, "total_steps": 22439, "tokens": 69787975680, "source": "fineweb_hq", "phase": 1, "loss": 1.9182350933551788, "ce_loss": 1.9173836410045624, "logit_z_loss": 8.514637470245361, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2585478127002716, "tokens_per_second": 9397220.622070674, "eta_seconds": 13856.064777088166, "data_wait_seconds": 1.6689300537109375e-05} {"step": 7840, "total_steps": 22439, "tokens": 69877104640, "source": "fineweb_hq", "phase": 1, "loss": 1.9384737610816956, "ce_loss": 1.9373933672904968, "logit_z_loss": 10.803682327270508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27061259746551514, "tokens_per_second": 8639673.062768342, "eta_seconds": 15060.682014083863, "data_wait_seconds": 1.7404556274414062e-05} {"step": 7850, "total_steps": 22439, "tokens": 69966233600, "source": "fineweb_hq", "phase": 1, "loss": 1.9164933562278748, "ce_loss": 1.9153032302856445, "logit_z_loss": 11.901301860809326, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23016679286956787, "tokens_per_second": 9903336.621796547, "eta_seconds": 13129.942433524131, "data_wait_seconds": 0.04400068521499634} {"step": 7860, "total_steps": 22439, "tokens": 70055362560, "source": "fineweb_hq", "phase": 1, "loss": 1.9418779909610748, "ce_loss": 1.9409274458885193, "logit_z_loss": 9.505511283874512, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24499212205410004, "tokens_per_second": 8596992.40933605, "eta_seconds": 15114.717403133713, "data_wait_seconds": 0.45268213748931885} {"step": 7870, "total_steps": 22439, "tokens": 70144491520, "source": "fineweb_hq", "phase": 1, "loss": 1.962842434644699, "ce_loss": 1.9617250263690948, "logit_z_loss": 11.174340724945068, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2501915693283081, "tokens_per_second": 7398715.840578291, "eta_seconds": 17550.61075758934, "data_wait_seconds": 1.4841556549072266e-05} {"step": 7880, "total_steps": 22439, "tokens": 70233620480, "source": "fineweb_hq", "phase": 1, "loss": 2.0095474123954773, "ce_loss": 2.008485585451126, "logit_z_loss": 10.618240594863892, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26948848366737366, "tokens_per_second": 6247503.706278883, "eta_seconds": 20770.352282238007, "data_wait_seconds": 1.8417835235595703e-05} {"step": 7890, "total_steps": 22439, "tokens": 70322749440, "source": "fineweb_hq", "phase": 1, "loss": 1.9911494255065918, "ce_loss": 1.9901473820209503, "logit_z_loss": 10.02032470703125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2431233674287796, "tokens_per_second": 3663896.521552462, "eta_seconds": 35392.299739146234, "data_wait_seconds": 0.49699848890304565} {"step": 7900, "total_steps": 22439, "tokens": 70411878400, "source": "fineweb_hq", "phase": 1, "loss": 1.9889827072620392, "ce_loss": 1.9878938794136047, "logit_z_loss": 10.88799238204956, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27191200852394104, "tokens_per_second": 3272065.518936287, "eta_seconds": 39603.30078785419, "data_wait_seconds": 0.3693193793296814} {"step": 7910, "total_steps": 22439, "tokens": 70501007360, "source": "fineweb_hq", "phase": 1, "loss": 2.0008821189403534, "ce_loss": 1.9997710287570953, "logit_z_loss": 11.111002922058105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21051952242851257, "tokens_per_second": 5951516.539587379, "eta_seconds": 21758.39806923866, "data_wait_seconds": 1.9669532775878906e-05} {"step": 7920, "total_steps": 22439, "tokens": 70590136320, "source": "fineweb_hq", "phase": 1, "loss": 1.9787099659442902, "ce_loss": 1.9775347411632538, "logit_z_loss": 11.752112627029419, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25308921933174133, "tokens_per_second": 1819876.7493745484, "eta_seconds": 71107.19836850166, "data_wait_seconds": 2.2590160369873047e-05} {"step": 7930, "total_steps": 22439, "tokens": 70679265280, "source": "fineweb_hq", "phase": 1, "loss": 1.9780389070510864, "ce_loss": 1.9768904149532318, "logit_z_loss": 11.484946489334106, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20358876883983612, "tokens_per_second": 1851927.8100276943, "eta_seconds": 69828.42817294598, "data_wait_seconds": 3.179032325744629} {"step": 7940, "total_steps": 22439, "tokens": 70768394240, "source": "fineweb_hq", "phase": 1, "loss": 1.990407407283783, "ce_loss": 1.9893649220466614, "logit_z_loss": 10.424901723861694, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22046047449111938, "tokens_per_second": 2156948.7474968857, "eta_seconds": 59912.44773616791, "data_wait_seconds": 1.71661376953125e-05} {"step": 7950, "total_steps": 22439, "tokens": 70857523200, "source": "fineweb_hq", "phase": 1, "loss": 1.9876392483711243, "ce_loss": 1.9864566922187805, "logit_z_loss": 11.825453519821167, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24217422306537628, "tokens_per_second": 2488011.234006579, "eta_seconds": 51904.488363599776, "data_wait_seconds": 0.03655153512954712} {"step": 7960, "total_steps": 22439, "tokens": 70946652160, "source": "fineweb_hq", "phase": 1, "loss": 1.9747990667819977, "ce_loss": 1.9736371338367462, "logit_z_loss": 11.6197190284729, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.199081152677536, "tokens_per_second": 7593593.065144998, "eta_seconds": 16994.566350460052, "data_wait_seconds": 1.4960765838623047e-05} {"step": 7970, "total_steps": 22439, "tokens": 71035781120, "source": "fineweb_hq", "phase": 1, "loss": 1.9348758161067963, "ce_loss": 1.9335948824882507, "logit_z_loss": 12.809338331222534, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21147681772708893, "tokens_per_second": 8943524.605314063, "eta_seconds": 14419.448474192617, "data_wait_seconds": 1.430511474609375e-05} {"step": 7980, "total_steps": 22439, "tokens": 71124910080, "source": "fineweb_hq", "phase": 1, "loss": 1.9675132036209106, "ce_loss": 1.9664198160171509, "logit_z_loss": 10.934125661849976, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2755220830440521, "tokens_per_second": 9794236.8337338, "eta_seconds": 13157.89738922119, "data_wait_seconds": 1.436471939086914e-05} {"step": 7990, "total_steps": 22439, "tokens": 71214039040, "source": "fineweb_hq", "phase": 1, "loss": 1.9873037338256836, "ce_loss": 1.9861025214195251, "logit_z_loss": 12.011919498443604, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26438647508621216, "tokens_per_second": 9751174.441426614, "eta_seconds": 13206.863960599898, "data_wait_seconds": 1.4483928680419922e-05} {"step": 8000, "total_steps": 22439, "tokens": 71303168000, "source": "fineweb_hq", "phase": 1, "loss": 1.9861089289188385, "ce_loss": 1.9850241243839264, "logit_z_loss": 10.847880363464355, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24476023018360138, "tokens_per_second": 8908659.914267298, "eta_seconds": 14445.865773582458, "data_wait_seconds": 1.33514404296875e-05} {"step": 8010, "total_steps": 22439, "tokens": 71392296960, "source": "fineweb_hq", "phase": 1, "loss": 1.9682909548282623, "ce_loss": 1.9671496152877808, "logit_z_loss": 11.41340970993042, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20946669578552246, "tokens_per_second": 7620830.429618421, "eta_seconds": 16875.34942178726, "data_wait_seconds": 1.4781951904296875e-05} {"step": 8020, "total_steps": 22439, "tokens": 71481425920, "source": "fineweb_hq", "phase": 1, "loss": 1.938660055398941, "ce_loss": 1.93734672665596, "logit_z_loss": 13.133638143539429, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22100628912448883, "tokens_per_second": 7691470.2993082525, "eta_seconds": 16708.7751005888, "data_wait_seconds": 1.341104507446289e-05} {"step": 8030, "total_steps": 22439, "tokens": 71570554880, "source": "fineweb_hq", "phase": 1, "loss": 1.9426443576812744, "ce_loss": 1.941657692193985, "logit_z_loss": 9.86672306060791, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26276150345802307, "tokens_per_second": 9138836.594959717, "eta_seconds": 14052.764499020575, "data_wait_seconds": 1.3947486877441406e-05} {"step": 8040, "total_steps": 22439, "tokens": 71659683840, "source": "fineweb_hq", "phase": 1, "loss": 1.9286833107471466, "ce_loss": 1.927419900894165, "logit_z_loss": 12.633856534957886, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20426559448242188, "tokens_per_second": 8788755.755314957, "eta_seconds": 14602.384350752829, "data_wait_seconds": 1.7762184143066406e-05} {"step": 8050, "total_steps": 22439, "tokens": 71748812800, "source": "fineweb_hq", "phase": 1, "loss": 1.9449174404144287, "ce_loss": 1.9438039362430573, "logit_z_loss": 11.135719299316406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25766846537590027, "tokens_per_second": 8675112.75737781, "eta_seconds": 14783.399839377404, "data_wait_seconds": 0.8080645203590393} {"step": 8060, "total_steps": 22439, "tokens": 71837941760, "source": "fineweb_hq", "phase": 1, "loss": 1.9410999119281769, "ce_loss": 1.9400656819343567, "logit_z_loss": 10.342421054840088, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2915087342262268, "tokens_per_second": 8400099.296510415, "eta_seconds": 15256.787695026398, "data_wait_seconds": 1.6510486602783203e-05} {"step": 8070, "total_steps": 22439, "tokens": 71927070720, "source": "fineweb_hq", "phase": 1, "loss": 1.978082537651062, "ce_loss": 1.9769321084022522, "logit_z_loss": 11.504378318786621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24764782190322876, "tokens_per_second": 7969509.215210437, "eta_seconds": 16069.923399996758, "data_wait_seconds": 0.644727349281311} {"step": 8080, "total_steps": 22439, "tokens": 72016199680, "source": "fineweb_hq", "phase": 1, "loss": 1.982535034418106, "ce_loss": 1.9814945757389069, "logit_z_loss": 10.404739618301392, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2617088556289673, "tokens_per_second": 9023032.69757802, "eta_seconds": 14183.731562709809, "data_wait_seconds": 0.25449347496032715} {"step": 8090, "total_steps": 22439, "tokens": 72105328640, "source": "fineweb_hq", "phase": 1, "loss": 1.9857604801654816, "ce_loss": 1.9848065078258514, "logit_z_loss": 9.53982663154602, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22578176856040955, "tokens_per_second": 9160401.320571719, "eta_seconds": 13961.303684020042, "data_wait_seconds": 1.329183578491211e-05} {"step": 8100, "total_steps": 22439, "tokens": 72194457600, "source": "fineweb_hq", "phase": 1, "loss": 1.9937688708305359, "ce_loss": 1.9927449226379395, "logit_z_loss": 10.239494562149048, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3244858980178833, "tokens_per_second": 9274741.24988141, "eta_seconds": 13779.577489089967, "data_wait_seconds": 1.3947486877441406e-05} {"step": 8110, "total_steps": 22439, "tokens": 72283586560, "source": "fineweb_hq", "phase": 1, "loss": 1.9548275172710419, "ce_loss": 1.953749656677246, "logit_z_loss": 10.778625011444092, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2615872323513031, "tokens_per_second": 9027258.381918415, "eta_seconds": 14147.472176027299, "data_wait_seconds": 0.0007421970367431641} {"step": 8120, "total_steps": 22439, "tokens": 72372715520, "source": "fineweb_hq", "phase": 1, "loss": 1.9523809254169464, "ce_loss": 1.95108762383461, "logit_z_loss": 12.932783603668213, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2767868936061859, "tokens_per_second": 7679744.413130587, "eta_seconds": 16618.22984704971, "data_wait_seconds": 1.7523765563964844e-05} {"step": 8130, "total_steps": 22439, "tokens": 72461844480, "source": "fineweb_hq", "phase": 1, "loss": 1.9852288663387299, "ce_loss": 1.9843705594539642, "logit_z_loss": 8.583121538162231, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2560323476791382, "tokens_per_second": 8355166.694883616, "eta_seconds": 15264.163304138185, "data_wait_seconds": 1.3887882232666016e-05} {"step": 8140, "total_steps": 22439, "tokens": 72550973440, "source": "fineweb_hq", "phase": 1, "loss": 1.9733418226242065, "ce_loss": 1.9723313748836517, "logit_z_loss": 10.104345083236694, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20624759793281555, "tokens_per_second": 9188534.012684973, "eta_seconds": 13870.058023190499, "data_wait_seconds": 0.23296958208084106} {"step": 8150, "total_steps": 22439, "tokens": 72640102400, "source": "fineweb_hq", "phase": 1, "loss": 1.9849000573158264, "ce_loss": 1.9837299287319183, "logit_z_loss": 11.701084852218628, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22809816896915436, "tokens_per_second": 8021409.455585447, "eta_seconds": 15877.056476068497, "data_wait_seconds": 1.2516975402832031e-05} {"step": 8160, "total_steps": 22439, "tokens": 72729231360, "source": "fineweb_hq", "phase": 1, "loss": 1.9661142230033875, "ce_loss": 1.9649686217308044, "logit_z_loss": 11.4558687210083, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22320255637168884, "tokens_per_second": 6928163.351399409, "eta_seconds": 18369.5498401165, "data_wait_seconds": 0.3375697731971741} {"step": 8170, "total_steps": 22439, "tokens": 72818360320, "source": "fineweb_hq", "phase": 1, "loss": 1.9341128170490265, "ce_loss": 1.9327414631843567, "logit_z_loss": 13.713727951049805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26481059193611145, "tokens_per_second": 7517313.909213051, "eta_seconds": 16918.02611410618, "data_wait_seconds": 1.4543533325195312e-05} {"step": 8180, "total_steps": 22439, "tokens": 72907489280, "source": "fineweb_hq", "phase": 1, "loss": 1.9498012959957123, "ce_loss": 1.9487719535827637, "logit_z_loss": 10.29348611831665, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25363385677337646, "tokens_per_second": 9377249.493750773, "eta_seconds": 13552.906334495545, "data_wait_seconds": 1.5556812286376953e-05} {"step": 8190, "total_steps": 22439, "tokens": 72996618240, "source": "fineweb_hq", "phase": 1, "loss": 1.943226307630539, "ce_loss": 1.9419905543327332, "logit_z_loss": 12.357670545578003, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2363884598016739, "tokens_per_second": 7706017.707757002, "eta_seconds": 16480.607743239405, "data_wait_seconds": 0.0004754066467285156} {"step": 8200, "total_steps": 22439, "tokens": 73085747200, "source": "fineweb_hq", "phase": 1, "loss": 1.946824699640274, "ce_loss": 1.9458690583705902, "logit_z_loss": 9.556395292282104, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23288418352603912, "tokens_per_second": 7779435.887378733, "eta_seconds": 16313.615534758568, "data_wait_seconds": 1.4722347259521484e-05} {"step": 8210, "total_steps": 22439, "tokens": 73174876160, "source": "fineweb_hq", "phase": 1, "loss": 1.9538345336914062, "ce_loss": 1.9525202214717865, "logit_z_loss": 13.143277883529663, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21668027341365814, "tokens_per_second": 6602748.752017912, "eta_seconds": 19207.39406375885, "data_wait_seconds": 1.3709068298339844e-05} {"step": 8220, "total_steps": 22439, "tokens": 73264005120, "source": "fineweb_hq", "phase": 1, "loss": 1.9974925220012665, "ce_loss": 1.996342420578003, "logit_z_loss": 11.501118659973145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25644341111183167, "tokens_per_second": 7769879.02814833, "eta_seconds": 16310.738914322854, "data_wait_seconds": 1.5854835510253906e-05} {"step": 8230, "total_steps": 22439, "tokens": 73353134080, "source": "fineweb_hq", "phase": 1, "loss": 1.9921355247497559, "ce_loss": 1.9910812675952911, "logit_z_loss": 10.542568445205688, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2753584086894989, "tokens_per_second": 8302248.886584546, "eta_seconds": 15254.100544810295, "data_wait_seconds": 1.5676021575927734e-05} {"step": 8240, "total_steps": 22439, "tokens": 73442263040, "source": "fineweb_hq", "phase": 1, "loss": 1.9819845259189606, "ce_loss": 1.980973094701767, "logit_z_loss": 10.114187717437744, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20985530316829681, "tokens_per_second": 8860790.553535314, "eta_seconds": 14282.496526622772, "data_wait_seconds": 1.424551010131836e-05} {"step": 8250, "total_steps": 22439, "tokens": 73531392000, "source": "fineweb_hq", "phase": 1, "loss": 1.9833978116512299, "ce_loss": 1.9823423027992249, "logit_z_loss": 10.555265665054321, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22500577569007874, "tokens_per_second": 7829398.809223509, "eta_seconds": 16152.591587877274, "data_wait_seconds": 1.4781951904296875e-05} {"step": 8260, "total_steps": 22439, "tokens": 73620520960, "source": "fineweb_hq", "phase": 1, "loss": 2.002697080373764, "ce_loss": 2.0018325746059418, "logit_z_loss": 8.64513111114502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29006314277648926, "tokens_per_second": 8763989.39489118, "eta_seconds": 14419.911605286597, "data_wait_seconds": 1.3232231140136719e-05} {"step": 8270, "total_steps": 22439, "tokens": 73709649920, "source": "fineweb_hq", "phase": 1, "loss": 1.9744898974895477, "ce_loss": 1.9732938706874847, "logit_z_loss": 11.96019196510315, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3123934268951416, "tokens_per_second": 7255257.884957976, "eta_seconds": 17406.24874076843, "data_wait_seconds": 0.3219226002693176} {"step": 8280, "total_steps": 22439, "tokens": 73798778880, "source": "fineweb_hq", "phase": 1, "loss": 1.992130070924759, "ce_loss": 1.9911434650421143, "logit_z_loss": 9.866095066070557, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28652316331863403, "tokens_per_second": 8484860.551086808, "eta_seconds": 14873.27855350971, "data_wait_seconds": 1.9669532775878906e-05} {"step": 8290, "total_steps": 22439, "tokens": 73887907840, "source": "fineweb_hq", "phase": 1, "loss": 1.9930383563041687, "ce_loss": 1.9919603168964386, "logit_z_loss": 10.780581712722778, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2841373682022095, "tokens_per_second": 7762085.681154591, "eta_seconds": 16246.737112188339, "data_wait_seconds": 0.4228833317756653} {"step": 8300, "total_steps": 22439, "tokens": 73977036800, "source": "fineweb_hq", "phase": 1, "loss": 1.9567842483520508, "ce_loss": 1.9555871188640594, "logit_z_loss": 11.9712495803833, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26696208119392395, "tokens_per_second": 7108966.091635112, "eta_seconds": 17726.83044476509, "data_wait_seconds": 1.436471939086914e-05} {"step": 8310, "total_steps": 22439, "tokens": 74066165760, "source": "fineweb_hq", "phase": 1, "loss": 1.9177355766296387, "ce_loss": 1.916596680879593, "logit_z_loss": 11.388879299163818, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2508114278316498, "tokens_per_second": 8036401.235211237, "eta_seconds": 15669.987585020064, "data_wait_seconds": 0.2527974247932434} {"step": 8320, "total_steps": 22439, "tokens": 74155294720, "source": "fineweb_hq", "phase": 1, "loss": 1.9296352863311768, "ce_loss": 1.928376019001007, "logit_z_loss": 12.59277892112732, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2533150613307953, "tokens_per_second": 8833083.481782604, "eta_seconds": 14246.574130487443, "data_wait_seconds": 1.3828277587890625e-05} {"step": 8330, "total_steps": 22439, "tokens": 74244423680, "source": "fineweb_hq", "phase": 1, "loss": 1.9021632969379425, "ce_loss": 1.900888830423355, "logit_z_loss": 12.744550228118896, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30746397376060486, "tokens_per_second": 9444075.723286329, "eta_seconds": 13315.442754650116, "data_wait_seconds": 1.5020370483398438e-05} {"step": 8340, "total_steps": 22439, "tokens": 74333552640, "source": "fineweb_hq", "phase": 1, "loss": 1.8983747363090515, "ce_loss": 1.8971244990825653, "logit_z_loss": 12.50223994255066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19828732311725616, "tokens_per_second": 9479339.501778407, "eta_seconds": 13256.505970740318, "data_wait_seconds": 1.3172626495361328e-05} {"step": 8350, "total_steps": 22439, "tokens": 74422681600, "source": "fineweb_hq", "phase": 1, "loss": 1.908560425043106, "ce_loss": 1.9073510766029358, "logit_z_loss": 12.093585014343262, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23123101890087128, "tokens_per_second": 8917094.426741106, "eta_seconds": 14082.366490077971, "data_wait_seconds": 1.4901161193847656e-05} {"step": 8360, "total_steps": 22439, "tokens": 74511810560, "source": "fineweb_hq", "phase": 1, "loss": 1.9192444682121277, "ce_loss": 1.9179983735084534, "logit_z_loss": 12.461066007614136, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2619861960411072, "tokens_per_second": 9344573.068257855, "eta_seconds": 13428.613791918755, "data_wait_seconds": 1.615285873413086e-05} {"step": 8370, "total_steps": 22439, "tokens": 74600939520, "source": "fineweb_hq", "phase": 1, "loss": 1.908671349287033, "ce_loss": 1.907367765903473, "logit_z_loss": 13.035980224609375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2291405349969864, "tokens_per_second": 10198583.508959834, "eta_seconds": 12295.387267637254, "data_wait_seconds": 1.52587890625e-05} {"step": 8380, "total_steps": 22439, "tokens": 74690068480, "source": "fineweb_hq", "phase": 1, "loss": 1.8933826088905334, "ce_loss": 1.8922486007213593, "logit_z_loss": 11.339924812316895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24871478974819183, "tokens_per_second": 9419001.74865195, "eta_seconds": 13303.575921082496, "data_wait_seconds": 1.7523765563964844e-05} {"step": 8390, "total_steps": 22439, "tokens": 74779197440, "source": "fineweb_hq", "phase": 1, "loss": 1.904881238937378, "ce_loss": 1.9037631750106812, "logit_z_loss": 11.180635452270508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26619771122932434, "tokens_per_second": 8230949.992005167, "eta_seconds": 15212.979792809487, "data_wait_seconds": 0.279002845287323} {"step": 8400, "total_steps": 22439, "tokens": 74868326400, "source": "fineweb_hq", "phase": 1, "loss": 1.9723694920539856, "ce_loss": 1.9712784886360168, "logit_z_loss": 10.910116195678711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2824344038963318, "tokens_per_second": 8480058.405097608, "eta_seconds": 14755.576078200342, "data_wait_seconds": 1.4841556549072266e-05} {"step": 8410, "total_steps": 22439, "tokens": 74957455360, "source": "fineweb_hq", "phase": 1, "loss": 1.9891856908798218, "ce_loss": 1.9881036579608917, "logit_z_loss": 10.820555448532104, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22754204273223877, "tokens_per_second": 8529799.50548632, "eta_seconds": 14659.080545043946, "data_wait_seconds": 1.5795230865478516e-05} {"step": 8420, "total_steps": 22439, "tokens": 75046584320, "source": "fineweb_hq", "phase": 1, "loss": 1.9972561299800873, "ce_loss": 1.9960100650787354, "logit_z_loss": 12.460954904556274, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2569555342197418, "tokens_per_second": 9404786.280519444, "eta_seconds": 13285.776550054552, "data_wait_seconds": 0.3154679536819458} {"step": 8430, "total_steps": 22439, "tokens": 75135713280, "source": "fineweb_hq", "phase": 1, "loss": 1.9885797202587128, "ce_loss": 1.987569510936737, "logit_z_loss": 10.101909875869751, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22975672781467438, "tokens_per_second": 9365048.121249374, "eta_seconds": 13332.634114360808, "data_wait_seconds": 1.3113021850585938e-05} {"step": 8440, "total_steps": 22439, "tokens": 75224842240, "source": "fineweb_hq", "phase": 1, "loss": 2.0040208995342255, "ce_loss": 2.00303915143013, "logit_z_loss": 9.817911148071289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28192761540412903, "tokens_per_second": 9104748.716752298, "eta_seconds": 13704.016989994048, "data_wait_seconds": 1.3589859008789062e-05} {"step": 8450, "total_steps": 22439, "tokens": 75313971200, "source": "fineweb_hq", "phase": 1, "loss": 1.9928097426891327, "ce_loss": 1.9917741119861603, "logit_z_loss": 10.356776237487793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2385130226612091, "tokens_per_second": 8894213.990956228, "eta_seconds": 14018.383442401888, "data_wait_seconds": 0.29077011346817017} {"step": 8460, "total_steps": 22439, "tokens": 75403100160, "source": "fineweb_hq", "phase": 1, "loss": 2.0023021399974823, "ce_loss": 2.0012419521808624, "logit_z_loss": 10.602264642715454, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.329175740480423, "tokens_per_second": 8649249.923726467, "eta_seconds": 14405.107296323777, "data_wait_seconds": 0.22440677881240845} {"step": 8470, "total_steps": 22439, "tokens": 75492229120, "source": "fineweb_hq", "phase": 1, "loss": 1.9902257919311523, "ce_loss": 1.9891935288906097, "logit_z_loss": 10.32268238067627, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21053056418895721, "tokens_per_second": 8481426.703314537, "eta_seconds": 14679.63452131748, "data_wait_seconds": 0.24584364891052246} {"step": 8480, "total_steps": 22439, "tokens": 75581358080, "source": "fineweb_hq", "phase": 1, "loss": 1.985752671957016, "ce_loss": 1.9845346510410309, "logit_z_loss": 12.1798734664917, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20625120401382446, "tokens_per_second": 7527895.254800742, "eta_seconds": 16527.211265945436, "data_wait_seconds": 2.110004425048828e-05} {"step": 8490, "total_steps": 22439, "tokens": 75670487040, "source": "fineweb_hq", "phase": 1, "loss": 1.9688800275325775, "ce_loss": 1.9677128195762634, "logit_z_loss": 11.672186136245728, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25881949067115784, "tokens_per_second": 7659362.524447395, "eta_seconds": 16231.89735531807, "data_wait_seconds": 0.3151172995567322} {"step": 8500, "total_steps": 22439, "tokens": 75759616000, "source": "fineweb_hq", "phase": 1, "loss": 1.9569692611694336, "ce_loss": 1.9559881091117859, "logit_z_loss": 9.811585664749146, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3062780201435089, "tokens_per_second": 8616905.585682686, "eta_seconds": 14417.80417675972, "data_wait_seconds": 0.21823275089263916} {"step": 8510, "total_steps": 22439, "tokens": 75848744960, "source": "fineweb_hq", "phase": 1, "loss": 1.9153843820095062, "ce_loss": 1.9142571687698364, "logit_z_loss": 11.272044658660889, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22090831398963928, "tokens_per_second": 8930398.866717303, "eta_seconds": 13901.700275301933, "data_wait_seconds": 1.3470649719238281e-05} {"step": 8520, "total_steps": 22439, "tokens": 75937873920, "source": "fineweb_hq", "phase": 1, "loss": 1.936046302318573, "ce_loss": 1.9349381029605865, "logit_z_loss": 11.082020044326782, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2829980254173279, "tokens_per_second": 9599005.323288143, "eta_seconds": 12924.109868240357, "data_wait_seconds": 1.33514404296875e-05} {"step": 8530, "total_steps": 22439, "tokens": 76027002880, "source": "fineweb_hq", "phase": 1, "loss": 1.9388335347175598, "ce_loss": 1.9376882016658783, "logit_z_loss": 11.45334243774414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2576637268066406, "tokens_per_second": 9276818.176679691, "eta_seconds": 13363.361025619506, "data_wait_seconds": 1.5974044799804688e-05} {"step": 8540, "total_steps": 22439, "tokens": 76116131840, "source": "fineweb_hq", "phase": 1, "loss": 1.897178441286087, "ce_loss": 1.8960666358470917, "logit_z_loss": 11.118027925491333, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24499349296092987, "tokens_per_second": 7516851.679984206, "eta_seconds": 16480.349324154853, "data_wait_seconds": 1.5974044799804688e-05} {"step": 8550, "total_steps": 22439, "tokens": 76205260800, "source": "fineweb_hq", "phase": 1, "loss": 1.8327616453170776, "ce_loss": 1.8314450681209564, "logit_z_loss": 13.16602087020874, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23594918847084045, "tokens_per_second": 8111765.582062987, "eta_seconds": 15260.698955321313, "data_wait_seconds": 0.12533414363861084} {"step": 8560, "total_steps": 22439, "tokens": 76294389760, "source": "fineweb_hq", "phase": 1, "loss": 1.764465093612671, "ce_loss": 1.7629570066928864, "logit_z_loss": 15.081035614013672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1873917430639267, "tokens_per_second": 9385996.73317239, "eta_seconds": 13179.429644036292, "data_wait_seconds": 0.27072155475616455} {"step": 8570, "total_steps": 22439, "tokens": 76383518720, "source": "fineweb_hq", "phase": 1, "loss": 1.7774664759635925, "ce_loss": 1.775801032781601, "logit_z_loss": 16.654344081878662, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2495577484369278, "tokens_per_second": 9211512.74005146, "eta_seconds": 13419.397889614105, "data_wait_seconds": 1.811981201171875e-05} {"step": 8580, "total_steps": 22439, "tokens": 76472647680, "source": "fineweb_hq", "phase": 1, "loss": 1.8728169798851013, "ce_loss": 1.871679812669754, "logit_z_loss": 11.371561765670776, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27256783843040466, "tokens_per_second": 9529909.022460349, "eta_seconds": 12961.700407934188, "data_wait_seconds": 1.531839370727539e-05} {"step": 8590, "total_steps": 22439, "tokens": 76561776640, "source": "fineweb_hq", "phase": 1, "loss": 1.9620609283447266, "ce_loss": 1.9611113667488098, "logit_z_loss": 9.495867490768433, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26206958293914795, "tokens_per_second": 7396396.656503975, "eta_seconds": 16688.49068491459, "data_wait_seconds": 0.30612194538116455} {"step": 8600, "total_steps": 22439, "tokens": 76650905600, "source": "fineweb_hq", "phase": 1, "loss": 1.9750053882598877, "ce_loss": 1.9738965332508087, "logit_z_loss": 11.088648557662964, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2781836688518524, "tokens_per_second": 9016359.937536627, "eta_seconds": 13680.195622014999, "data_wait_seconds": 1.6927719116210938e-05} {"step": 8610, "total_steps": 22439, "tokens": 76740034560, "source": "fineweb_hq", "phase": 1, "loss": 1.9890535771846771, "ce_loss": 1.9881157577037811, "logit_z_loss": 9.37792444229126, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24745167791843414, "tokens_per_second": 9832244.308496863, "eta_seconds": 12535.941430735587, "data_wait_seconds": 1.5556812286376953e-05} {"step": 8620, "total_steps": 22439, "tokens": 76829163520, "source": "fineweb_hq", "phase": 1, "loss": 1.9687360525131226, "ce_loss": 1.967725694179535, "logit_z_loss": 10.10347604751587, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24194768071174622, "tokens_per_second": 8249606.4788404675, "eta_seconds": 14930.083045768737, "data_wait_seconds": 0.04329538345336914} {"step": 8630, "total_steps": 22439, "tokens": 76918292480, "source": "fineweb_hq", "phase": 1, "loss": 1.9030345976352692, "ce_loss": 1.9019888043403625, "logit_z_loss": 10.457853317260742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23026256263256073, "tokens_per_second": 7290458.309052019, "eta_seconds": 16882.09103550911, "data_wait_seconds": 1.5914440155029297e-05} {"step": 8640, "total_steps": 22439, "tokens": 77007421440, "source": "fineweb_hq", "phase": 1, "loss": 1.851554274559021, "ce_loss": 1.850174605846405, "logit_z_loss": 13.796844959259033, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2043287307024002, "tokens_per_second": 8794702.63145551, "eta_seconds": 13984.446894669534, "data_wait_seconds": 1.3113021850585938e-05} {"step": 8650, "total_steps": 22439, "tokens": 77096550400, "source": "fineweb_hq", "phase": 1, "loss": 1.7807807922363281, "ce_loss": 1.7792851626873016, "logit_z_loss": 14.956303596496582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21166172623634338, "tokens_per_second": 8401242.907939594, "eta_seconds": 14628.778657007218, "data_wait_seconds": 1.6748905181884766e-05} {"step": 8660, "total_steps": 22439, "tokens": 77185679360, "source": "fineweb_hq", "phase": 1, "loss": 1.7684021890163422, "ce_loss": 1.7670300006866455, "logit_z_loss": 13.721890211105347, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2549152970314026, "tokens_per_second": 7015758.733790457, "eta_seconds": 17504.991069960593, "data_wait_seconds": 0.395784854888916} {"step": 8670, "total_steps": 22439, "tokens": 77274808320, "source": "fineweb_hq", "phase": 1, "loss": 1.7683925926685333, "ce_loss": 1.766920417547226, "logit_z_loss": 14.721954822540283, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24734337627887726, "tokens_per_second": 7800506.649762792, "eta_seconds": 15732.524890255929, "data_wait_seconds": 1.9073486328125e-05} {"step": 8680, "total_steps": 22439, "tokens": 77363937280, "source": "fineweb_hq", "phase": 1, "loss": 1.7522331178188324, "ce_loss": 1.7509594559669495, "logit_z_loss": 12.736555337905884, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26259645819664, "tokens_per_second": 7726077.3079418, "eta_seconds": 15872.548406672477, "data_wait_seconds": 0.45048463344573975} {"step": 8690, "total_steps": 22439, "tokens": 77453066240, "source": "fineweb_hq", "phase": 1, "loss": 1.750197023153305, "ce_loss": 1.7489838898181915, "logit_z_loss": 12.131319761276245, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24717368185520172, "tokens_per_second": 9048441.275100518, "eta_seconds": 13543.040550112724, "data_wait_seconds": 1.71661376953125e-05} {"step": 8700, "total_steps": 22439, "tokens": 77542195200, "source": "fineweb_hq", "phase": 1, "loss": 1.7447417080402374, "ce_loss": 1.743362843990326, "logit_z_loss": 13.788600206375122, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22093604505062103, "tokens_per_second": 9076646.395967286, "eta_seconds": 13491.136792373656, "data_wait_seconds": 1.3947486877441406e-05} {"step": 8710, "total_steps": 22439, "tokens": 77631324160, "source": "fineweb_hq", "phase": 1, "loss": 1.7569804787635803, "ce_loss": 1.7557668387889862, "logit_z_loss": 12.13633680343628, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23730532824993134, "tokens_per_second": 8732915.209455995, "eta_seconds": 14011.94747104645, "data_wait_seconds": 1.3709068298339844e-05} {"step": 8720, "total_steps": 22439, "tokens": 77720453120, "source": "fineweb_hq", "phase": 1, "loss": 1.7382968664169312, "ce_loss": 1.737038105726242, "logit_z_loss": 12.587564706802368, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23772843182086945, "tokens_per_second": 9002261.54520886, "eta_seconds": 13582.811342453959, "data_wait_seconds": 2.8252601623535156e-05} {"step": 8730, "total_steps": 22439, "tokens": 77809582080, "source": "fineweb_hq", "phase": 1, "loss": 1.7567774951457977, "ce_loss": 1.755385160446167, "logit_z_loss": 13.923111915588379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28641119599342346, "tokens_per_second": 8771781.771035992, "eta_seconds": 13929.540708303453, "data_wait_seconds": 1.4066696166992188e-05} {"step": 8740, "total_steps": 22439, "tokens": 77898711040, "source": "fineweb_hq", "phase": 1, "loss": 1.7351737022399902, "ce_loss": 1.7339244484901428, "logit_z_loss": 12.492481470108032, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24615219235420227, "tokens_per_second": 8125087.719152922, "eta_seconds": 15027.254661655426, "data_wait_seconds": 0.3088817000389099} {"step": 8750, "total_steps": 22439, "tokens": 77987840000, "source": "fineweb_hq", "phase": 1, "loss": 1.7042592763900757, "ce_loss": 1.7030079364776611, "logit_z_loss": 12.51345181465149, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22823062539100647, "tokens_per_second": 9406368.706878403, "eta_seconds": 12970.853806185722, "data_wait_seconds": 1.806020736694336e-05} {"step": 8760, "total_steps": 22439, "tokens": 78076968960, "source": "fineweb_hq", "phase": 1, "loss": 1.709514319896698, "ce_loss": 1.7082136571407318, "logit_z_loss": 13.006876468658447, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2602774500846863, "tokens_per_second": 9269374.411591131, "eta_seconds": 13152.937724852562, "data_wait_seconds": 1.7464160919189453e-05} {"step": 8770, "total_steps": 22439, "tokens": 78166097920, "source": "fineweb_hq", "phase": 1, "loss": 1.7143073678016663, "ce_loss": 1.7129806578159332, "logit_z_loss": 13.267049312591553, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27319255471229553, "tokens_per_second": 10174514.178246088, "eta_seconds": 11974.07299156189, "data_wait_seconds": 1.8477439880371094e-05} {"step": 8780, "total_steps": 22439, "tokens": 78255226880, "source": "fineweb_hq", "phase": 1, "loss": 1.6970289945602417, "ce_loss": 1.6957040131092072, "logit_z_loss": 13.249715089797974, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23133236169815063, "tokens_per_second": 9089848.921219248, "eta_seconds": 13393.098996376992, "data_wait_seconds": 1.7642974853515625e-05} {"step": 8790, "total_steps": 22439, "tokens": 78344355840, "source": "fineweb_hq", "phase": 1, "loss": 1.7204597890377045, "ce_loss": 1.7186655402183533, "logit_z_loss": 17.94251298904419, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2870091199874878, "tokens_per_second": 10496276.124245193, "eta_seconds": 11590.026411652565, "data_wait_seconds": 1.4066696166992188e-05} {"step": 8800, "total_steps": 22439, "tokens": 78433484800, "source": "fineweb_hq", "phase": 1, "loss": 1.6929976642131805, "ce_loss": 1.6915777623653412, "logit_z_loss": 14.19906759262085, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23349207639694214, "tokens_per_second": 9379612.863009296, "eta_seconds": 12960.341788029671, "data_wait_seconds": 0.045757174491882324} {"step": 8810, "total_steps": 22439, "tokens": 78522613760, "source": "fineweb_hq", "phase": 1, "loss": 1.8262482285499573, "ce_loss": 1.825060099363327, "logit_z_loss": 11.88139533996582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25484806299209595, "tokens_per_second": 7256486.923502397, "eta_seconds": 16740.03699924946, "data_wait_seconds": 0.31717175245285034} {"step": 8820, "total_steps": 22439, "tokens": 78611742720, "source": "fineweb_hq", "phase": 1, "loss": 1.9382066428661346, "ce_loss": 1.937330424785614, "logit_z_loss": 8.762025356292725, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2619193494319916, "tokens_per_second": 8051902.819297981, "eta_seconds": 15075.285103178025, "data_wait_seconds": 1.6391277313232422e-05} {"step": 8830, "total_steps": 22439, "tokens": 78700871680, "source": "fineweb_hq", "phase": 1, "loss": 1.9735071063041687, "ce_loss": 1.9726454019546509, "logit_z_loss": 8.617294073104858, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25202837586402893, "tokens_per_second": 8885814.449713675, "eta_seconds": 13650.476537680624, "data_wait_seconds": 1.531839370727539e-05} {"step": 8840, "total_steps": 22439, "tokens": 78790000640, "source": "fineweb_hq", "phase": 1, "loss": 1.9663269519805908, "ce_loss": 1.9654973447322845, "logit_z_loss": 8.296035528182983, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24102044105529785, "tokens_per_second": 8347326.043532331, "eta_seconds": 14520.395162701607, "data_wait_seconds": 1.537799835205078e-05} {"step": 8850, "total_steps": 22439, "tokens": 78879129600, "source": "fineweb_hq", "phase": 1, "loss": 1.9634956419467926, "ce_loss": 1.9624490141868591, "logit_z_loss": 10.46629524230957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24597062170505524, "tokens_per_second": 8538494.869142206, "eta_seconds": 14184.858760261535, "data_wait_seconds": 1.537799835205078e-05} {"step": 8860, "total_steps": 22439, "tokens": 78968258560, "source": "fineweb_hq", "phase": 1, "loss": 1.9260091185569763, "ce_loss": 1.925011694431305, "logit_z_loss": 9.974319219589233, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2770249545574188, "tokens_per_second": 7078520.903831766, "eta_seconds": 17097.952584767343, "data_wait_seconds": 1.4662742614746094e-05} {"step": 8870, "total_steps": 22439, "tokens": 79057387520, "source": "fineweb_hq", "phase": 1, "loss": 1.8664973378181458, "ce_loss": 1.8652839958667755, "logit_z_loss": 12.133147716522217, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22097694873809814, "tokens_per_second": 6872014.625213076, "eta_seconds": 17598.78178668022, "data_wait_seconds": 1.9073486328125e-05} {"step": 8880, "total_steps": 22439, "tokens": 79146516480, "source": "fineweb_hq", "phase": 1, "loss": 1.8420802652835846, "ce_loss": 1.840427428483963, "logit_z_loss": 16.528380393981934, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29817521572113037, "tokens_per_second": 8647976.383680442, "eta_seconds": 13974.362498497963, "data_wait_seconds": 1.6510486602783203e-05} {"step": 8890, "total_steps": 22439, "tokens": 79235645440, "source": "fineweb_hq", "phase": 1, "loss": 1.8185142576694489, "ce_loss": 1.8171027302742004, "logit_z_loss": 14.115208864212036, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2564827501773834, "tokens_per_second": 10159843.288563784, "eta_seconds": 11886.091593551635, "data_wait_seconds": 1.5437602996826172e-05} {"step": 8900, "total_steps": 22439, "tokens": 79324774400, "source": "fineweb_hq", "phase": 1, "loss": 1.828657329082489, "ce_loss": 1.8272964656352997, "logit_z_loss": 13.608440399169922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25761646032333374, "tokens_per_second": 8554281.400682349, "eta_seconds": 14106.585146284104, "data_wait_seconds": 1.52587890625e-05} {"step": 8910, "total_steps": 22439, "tokens": 79413903360, "source": "fineweb_hq", "phase": 1, "loss": 1.7948593199253082, "ce_loss": 1.7935926020145416, "logit_z_loss": 12.667060375213623, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2625105082988739, "tokens_per_second": 9918253.039141545, "eta_seconds": 12157.642027091979, "data_wait_seconds": 0.05257272720336914} {"step": 8920, "total_steps": 22439, "tokens": 79503032320, "source": "fineweb_hq", "phase": 1, "loss": 1.8163466155529022, "ce_loss": 1.815088003873825, "logit_z_loss": 12.586488723754883, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31451162695884705, "tokens_per_second": 9392040.535054492, "eta_seconds": 12829.31441514492, "data_wait_seconds": 0.04945039749145508} {"step": 8930, "total_steps": 22439, "tokens": 79592161280, "source": "fineweb_hq", "phase": 1, "loss": 1.8104665577411652, "ce_loss": 1.8091472387313843, "logit_z_loss": 13.19307255744934, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2448744773864746, "tokens_per_second": 8530205.318176169, "eta_seconds": 14115.054394698142, "data_wait_seconds": 1.531839370727539e-05} {"step": 8940, "total_steps": 22439, "tokens": 79681290240, "source": "fineweb_hq", "phase": 1, "loss": 1.8138928711414337, "ce_loss": 1.8126161396503448, "logit_z_loss": 12.7676100730896, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29598382115364075, "tokens_per_second": 8938624.115949584, "eta_seconds": 13460.145716309546, "data_wait_seconds": 1.2099742889404297e-05} {"step": 8950, "total_steps": 22439, "tokens": 79770419200, "source": "fineweb_hq", "phase": 1, "loss": 1.8256580233573914, "ce_loss": 1.8245335519313812, "logit_z_loss": 11.244980573654175, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23972268402576447, "tokens_per_second": 9373913.630462082, "eta_seconds": 12825.598664927482, "data_wait_seconds": 1.3947486877441406e-05} {"step": 8960, "total_steps": 22439, "tokens": 79859548160, "source": "fineweb_hq", "phase": 1, "loss": 1.8245214223861694, "ce_loss": 1.8234554529190063, "logit_z_loss": 10.659906387329102, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2712342143058777, "tokens_per_second": 8335257.2422713, "eta_seconds": 14413.103482246399, "data_wait_seconds": 1.436471939086914e-05} {"step": 8970, "total_steps": 22439, "tokens": 79948677120, "source": "fineweb_hq", "phase": 1, "loss": 1.8554934859275818, "ce_loss": 1.8543352782726288, "logit_z_loss": 11.582093954086304, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18713514506816864, "tokens_per_second": 8465669.76442122, "eta_seconds": 14180.543248748778, "data_wait_seconds": 0.3515629172325134} {"step": 8980, "total_steps": 22439, "tokens": 80037806080, "source": "fineweb_hq", "phase": 1, "loss": 1.9105778932571411, "ce_loss": 1.9105778932571411, "logit_z_loss": 9.938977479934692, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2709043622016907, "tokens_per_second": 11246443.697455723, "eta_seconds": 10666.364451825619, "data_wait_seconds": 1.6510486602783203e-05} {"step": 8990, "total_steps": 22439, "tokens": 80126935040, "source": "fineweb_hq", "phase": 1, "loss": 1.911492258310318, "ce_loss": 1.911492258310318, "logit_z_loss": 13.467236995697021, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26620399951934814, "tokens_per_second": 10337554.75720871, "eta_seconds": 11595.540833330155, "data_wait_seconds": 1.7344951629638672e-05} {"step": 9000, "total_steps": 22439, "tokens": 80216064000, "source": "fineweb_hq", "phase": 1, "loss": 1.9088817536830902, "ce_loss": 1.9088817536830902, "logit_z_loss": 18.021133422851562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28515785932540894, "tokens_per_second": 9278581.900889125, "eta_seconds": 12909.344404506683, "data_wait_seconds": 1.5079975128173828e-05} {"step": 9010, "total_steps": 22439, "tokens": 80305192960, "source": "fineweb_hq", "phase": 1, "loss": 1.8973770439624786, "ce_loss": 1.8973770439624786, "logit_z_loss": 20.547932624816895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21939978003501892, "tokens_per_second": 8189895.639224968, "eta_seconds": 14614.506174015998, "data_wait_seconds": 2.1457672119140625e-05} {"step": 9020, "total_steps": 22439, "tokens": 80394321920, "source": "fineweb_hq", "phase": 1, "loss": 1.9116999208927155, "ce_loss": 1.9116999208927155, "logit_z_loss": 23.07257318496704, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23468439280986786, "tokens_per_second": 10679866.410486665, "eta_seconds": 11198.843396258355, "data_wait_seconds": 1.6391277313232422e-05} {"step": 9030, "total_steps": 22439, "tokens": 80483450880, "source": "fineweb_hq", "phase": 1, "loss": 1.9063617587089539, "ce_loss": 1.9063617587089539, "logit_z_loss": 25.153956413269043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2028626948595047, "tokens_per_second": 9297373.724104578, "eta_seconds": 12854.492678308487, "data_wait_seconds": 1.6808509826660156e-05} {"step": 9040, "total_steps": 22439, "tokens": 80572579840, "source": "fineweb_hq", "phase": 1, "loss": 1.89553564786911, "ce_loss": 1.89553564786911, "logit_z_loss": 25.032899379730225, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28641951084136963, "tokens_per_second": 9703855.35507836, "eta_seconds": 12306.850126481057, "data_wait_seconds": 1.7464160919189453e-05} {"step": 9050, "total_steps": 22439, "tokens": 80661708800, "source": "fineweb_hq", "phase": 1, "loss": 1.91450697183609, "ce_loss": 1.91450697183609, "logit_z_loss": 26.057410717010498, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24097351729869843, "tokens_per_second": 9032718.363139804, "eta_seconds": 13211.389943361282, "data_wait_seconds": 1.5914440155029297e-05} {"step": 9060, "total_steps": 22439, "tokens": 80750837760, "source": "fineweb_hq", "phase": 1, "loss": 1.9138667285442352, "ce_loss": 1.9138667285442352, "logit_z_loss": 26.32914161682129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2446470856666565, "tokens_per_second": 7735717.138254032, "eta_seconds": 15414.94259068966, "data_wait_seconds": 1.5020370483398438e-05} {"step": 9070, "total_steps": 22439, "tokens": 80839966720, "source": "fineweb_hq", "phase": 1, "loss": 1.9235478639602661, "ce_loss": 1.9235478639602661, "logit_z_loss": 28.814423084259033, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2701858878135681, "tokens_per_second": 8126174.62758394, "eta_seconds": 14663.296333742142, "data_wait_seconds": 0.24362856149673462} {"step": 9080, "total_steps": 22439, "tokens": 80929095680, "source": "fineweb_hq", "phase": 1, "loss": 1.9460509717464447, "ce_loss": 1.9460509717464447, "logit_z_loss": 28.277770519256592, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21900896728038788, "tokens_per_second": 9407571.678690597, "eta_seconds": 12656.547484374047, "data_wait_seconds": 0.0004183650016784668} {"step": 9090, "total_steps": 22439, "tokens": 81018224640, "source": "fineweb_hq", "phase": 1, "loss": 1.9383544027805328, "ce_loss": 1.9383544027805328, "logit_z_loss": 29.345985889434814, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2440715730190277, "tokens_per_second": 9961929.94899305, "eta_seconds": 11943.293047952651, "data_wait_seconds": 1.430511474609375e-05} {"step": 9100, "total_steps": 22439, "tokens": 81107353600, "source": "fineweb_hq", "phase": 1, "loss": 1.940564215183258, "ce_loss": 1.940564215183258, "logit_z_loss": 27.24939489364624, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2404661774635315, "tokens_per_second": 7509408.22386787, "eta_seconds": 15832.022470974924, "data_wait_seconds": 1.3887882232666016e-05} {"step": 9110, "total_steps": 22439, "tokens": 81196482560, "source": "fineweb_hq", "phase": 1, "loss": 1.9364704191684723, "ce_loss": 1.9364704191684723, "logit_z_loss": 31.062344551086426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21792298555374146, "tokens_per_second": 7616074.558302499, "eta_seconds": 15598.585580348969, "data_wait_seconds": 0.21691912412643433} {"step": 9120, "total_steps": 22439, "tokens": 81285611520, "source": "fineweb_hq", "phase": 1, "loss": 1.9313321709632874, "ce_loss": 1.9313321709632874, "logit_z_loss": 28.519657611846924, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.243795707821846, "tokens_per_second": 8960641.820997545, "eta_seconds": 13248.03113386631, "data_wait_seconds": 1.3709068298339844e-05} {"step": 9130, "total_steps": 22439, "tokens": 81374740480, "source": "fineweb_hq", "phase": 1, "loss": 1.9502461850643158, "ce_loss": 1.9502461850643158, "logit_z_loss": 31.169950485229492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2128874659538269, "tokens_per_second": 9362104.492178382, "eta_seconds": 12670.41325623989, "data_wait_seconds": 0.15525120496749878} {"step": 9140, "total_steps": 22439, "tokens": 81463869440, "source": "fineweb_hq", "phase": 1, "loss": 1.9466132819652557, "ce_loss": 1.9466132819652557, "logit_z_loss": 31.947139263153076, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23859749734401703, "tokens_per_second": 8489362.950567327, "eta_seconds": 13962.485123348237, "data_wait_seconds": 1.4901161193847656e-05} {"step": 9150, "total_steps": 22439, "tokens": 81552998400, "source": "fineweb_hq", "phase": 1, "loss": 1.943547248840332, "ce_loss": 1.943547248840332, "logit_z_loss": 33.67529773712158, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2745296359062195, "tokens_per_second": 8678486.66333952, "eta_seconds": 13647.941114473342, "data_wait_seconds": 1.3113021850585938e-05} {"step": 9160, "total_steps": 22439, "tokens": 81642127360, "source": "fineweb_hq", "phase": 1, "loss": 1.9436460733413696, "ce_loss": 1.9436460733413696, "logit_z_loss": 31.05198860168457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2370862066745758, "tokens_per_second": 9732829.798703631, "eta_seconds": 12160.322170615196, "data_wait_seconds": 1.3768672943115234e-05} {"step": 9170, "total_steps": 22439, "tokens": 81731256320, "source": "fineweb_hq", "phase": 1, "loss": 1.947835624217987, "ce_loss": 1.947835624217987, "logit_z_loss": 34.66003704071045, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22717319428920746, "tokens_per_second": 9070579.867107935, "eta_seconds": 13038.330377626418, "data_wait_seconds": 2.0563602447509766e-05} {"step": 9180, "total_steps": 22439, "tokens": 81820385280, "source": "fineweb_hq", "phase": 1, "loss": 1.9385451078414917, "ce_loss": 1.9385451078414917, "logit_z_loss": 34.2797155380249, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2053026258945465, "tokens_per_second": 8633370.24415554, "eta_seconds": 13688.291446089745, "data_wait_seconds": 0.1995641589164734} {"step": 9190, "total_steps": 22439, "tokens": 81909514240, "source": "fineweb_hq", "phase": 1, "loss": 1.9309524595737457, "ce_loss": 1.9309524595737457, "logit_z_loss": 37.49671649932861, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19649551808834076, "tokens_per_second": 7537252.196151169, "eta_seconds": 15667.109979987144, "data_wait_seconds": 1.3887882232666016e-05} {"step": 9200, "total_steps": 22439, "tokens": 81998643200, "source": "fineweb_hq", "phase": 1, "loss": 1.873956024646759, "ce_loss": 1.873956024646759, "logit_z_loss": 40.50106334686279, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21517282724380493, "tokens_per_second": 8389622.899243744, "eta_seconds": 14064.7358720541, "data_wait_seconds": 0.7013449668884277} {"step": 9210, "total_steps": 22439, "tokens": 82087772160, "source": "fineweb_hq", "phase": 1, "loss": 1.7659783363342285, "ce_loss": 1.7659783363342285, "logit_z_loss": 43.615241050720215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21707198023796082, "tokens_per_second": 8819084.271148954, "eta_seconds": 13369.721567320823, "data_wait_seconds": 1.5497207641601562e-05} {"step": 9220, "total_steps": 22439, "tokens": 82176901120, "source": "fineweb_hq", "phase": 1, "loss": 1.7509791254997253, "ce_loss": 1.7509791254997253, "logit_z_loss": 47.588887214660645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.1933802217245102, "tokens_per_second": 9082313.255854487, "eta_seconds": 12972.418909692764, "data_wait_seconds": 1.245737075805664e-05} {"step": 9230, "total_steps": 22439, "tokens": 82266030080, "source": "fineweb_hq", "phase": 1, "loss": 1.7605646252632141, "ce_loss": 1.7605646252632141, "logit_z_loss": 49.31062698364258, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2431672066450119, "tokens_per_second": 9502619.488942262, "eta_seconds": 12389.262076735495, "data_wait_seconds": 1.3172626495361328e-05} {"step": 9240, "total_steps": 22439, "tokens": 82355159040, "source": "fineweb_hq", "phase": 1, "loss": 1.7549114227294922, "ce_loss": 1.7549114227294922, "logit_z_loss": 48.1991491317749, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.206935316324234, "tokens_per_second": 9198019.87039253, "eta_seconds": 12789.852159667014, "data_wait_seconds": 1.537799835205078e-05} {"step": 9250, "total_steps": 22439, "tokens": 82444288000, "source": "fineweb_hq", "phase": 1, "loss": 1.7599486708641052, "ce_loss": 1.7599486708641052, "logit_z_loss": 44.84247589111328, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24358800053596497, "tokens_per_second": 9406249.894009143, "eta_seconds": 12497.242436528206, "data_wait_seconds": 0.04762148857116699} {"step": 9260, "total_steps": 22439, "tokens": 82533416960, "source": "fineweb_hq", "phase": 1, "loss": 1.7385940551757812, "ce_loss": 1.7385940551757812, "logit_z_loss": 46.17058563232422, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24440208077430725, "tokens_per_second": 9700371.716343299, "eta_seconds": 12109.12940440178, "data_wait_seconds": 1.6450881958007812e-05} {"step": 9270, "total_steps": 22439, "tokens": 82622545920, "source": "fineweb_hq", "phase": 1, "loss": 1.7320255935192108, "ce_loss": 1.7320255935192108, "logit_z_loss": 50.25489616394043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25158900022506714, "tokens_per_second": 10119248.859477459, "eta_seconds": 11599.075094795227, "data_wait_seconds": 1.8656253814697266e-05} {"step": 9280, "total_steps": 22439, "tokens": 82711674880, "source": "fineweb_hq", "phase": 1, "loss": 1.751942902803421, "ce_loss": 1.751942902803421, "logit_z_loss": 48.713385581970215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2317657470703125, "tokens_per_second": 8038412.1523353625, "eta_seconds": 14590.543037772179, "data_wait_seconds": 1.8477439880371094e-05} {"step": 9290, "total_steps": 22439, "tokens": 82800803840, "source": "fineweb_hq", "phase": 1, "loss": 1.736953616142273, "ce_loss": 1.736953616142273, "logit_z_loss": 53.498172760009766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3039352297782898, "tokens_per_second": 9270777.326081457, "eta_seconds": 12641.407012796402, "data_wait_seconds": 1.3649463653564453e-05} {"step": 9300, "total_steps": 22439, "tokens": 82889932800, "source": "fineweb_hq", "phase": 1, "loss": 1.8040026724338531, "ce_loss": 1.8040026724338531, "logit_z_loss": 46.40646839141846, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20922622084617615, "tokens_per_second": 7420689.668500378, "eta_seconds": 15781.085825634003, "data_wait_seconds": 1.430511474609375e-05} {"step": 9310, "total_steps": 22439, "tokens": 82979061760, "source": "fineweb_hq", "phase": 1, "loss": 1.8713557422161102, "ce_loss": 1.8713557422161102, "logit_z_loss": 46.69102382659912, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23063939809799194, "tokens_per_second": 7993635.46824358, "eta_seconds": 14638.8226044178, "data_wait_seconds": 1.7523765563964844e-05} {"step": 9320, "total_steps": 22439, "tokens": 83068190720, "source": "fineweb_hq", "phase": 1, "loss": 1.8864891529083252, "ce_loss": 1.8864891529083252, "logit_z_loss": 44.84260272979736, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2469257116317749, "tokens_per_second": 10269405.200073138, "eta_seconds": 11386.081311035156, "data_wait_seconds": 1.5735626220703125e-05} {"step": 9330, "total_steps": 22439, "tokens": 83157319680, "source": "fineweb_hq", "phase": 1, "loss": 1.9031448364257812, "ce_loss": 1.9031448364257812, "logit_z_loss": 39.167381286621094, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23012053966522217, "tokens_per_second": 10132709.180548342, "eta_seconds": 11530.889871811867, "data_wait_seconds": 1.424551010131836e-05} {"step": 9340, "total_steps": 22439, "tokens": 83246448640, "source": "fineweb_hq", "phase": 1, "loss": 1.8859448730945587, "ce_loss": 1.8859448730945587, "logit_z_loss": 45.37937068939209, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22773100435733795, "tokens_per_second": 9659723.686810073, "eta_seconds": 12086.269596242904, "data_wait_seconds": 1.5437602996826172e-05} {"step": 9350, "total_steps": 22439, "tokens": 83335577600, "source": "fineweb_hq", "phase": 1, "loss": 1.8774033784866333, "ce_loss": 1.8774033784866333, "logit_z_loss": 40.648444175720215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23789510130882263, "tokens_per_second": 9738407.956172496, "eta_seconds": 11979.462789916992, "data_wait_seconds": 0.2688010334968567} {"step": 9360, "total_steps": 22439, "tokens": 83424706560, "source": "fineweb_hq", "phase": 1, "loss": 1.8795176446437836, "ce_loss": 1.8795176446437836, "logit_z_loss": 47.45373725891113, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20036478340625763, "tokens_per_second": 8321133.861502388, "eta_seconds": 14009.12047855854, "data_wait_seconds": 1.7940998077392578e-05} {"step": 9370, "total_steps": 22439, "tokens": 83513835520, "source": "fineweb_hq", "phase": 1, "loss": 1.8242018818855286, "ce_loss": 1.8242018818855286, "logit_z_loss": 47.579548835754395, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21199385821819305, "tokens_per_second": 8505068.006012978, "eta_seconds": 13695.673890161515, "data_wait_seconds": 1.5139579772949219e-05} {"step": 9380, "total_steps": 22439, "tokens": 83602964480, "source": "fineweb_hq", "phase": 1, "loss": 1.7503722310066223, "ce_loss": 1.7503722310066223, "logit_z_loss": 54.685001373291016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26495301723480225, "tokens_per_second": 7690487.858996007, "eta_seconds": 15134.736703062057, "data_wait_seconds": 0.00010526180267333984} {"step": 9390, "total_steps": 22439, "tokens": 83692093440, "source": "fineweb_hq", "phase": 1, "loss": 1.7099515795707703, "ce_loss": 1.7099515795707703, "logit_z_loss": 57.70282459259033, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20774585008621216, "tokens_per_second": 10135557.230245551, "eta_seconds": 11474.887592458725, "data_wait_seconds": 1.633167266845703e-05} {"step": 9400, "total_steps": 22439, "tokens": 83781222400, "source": "fineweb_hq", "phase": 1, "loss": 1.7226167619228363, "ce_loss": 1.7226167619228363, "logit_z_loss": 51.65678691864014, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22216063737869263, "tokens_per_second": 9083785.48544961, "eta_seconds": 12793.702705788612, "data_wait_seconds": 0.3474475145339966} {"step": 9410, "total_steps": 22439, "tokens": 83870351360, "source": "fineweb_hq", "phase": 1, "loss": 1.6984308063983917, "ce_loss": 1.6984308063983917, "logit_z_loss": 61.20921802520752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25592291355133057, "tokens_per_second": 10127482.354067646, "eta_seconds": 11466.435380887986, "data_wait_seconds": 1.5735626220703125e-05} {"step": 9420, "total_steps": 22439, "tokens": 83959480320, "source": "fineweb_hq", "phase": 1, "loss": 1.7780433297157288, "ce_loss": 1.7780433297157288, "logit_z_loss": 53.18715000152588, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20666947960853577, "tokens_per_second": 7610020.632801446, "eta_seconds": 15247.920948314666, "data_wait_seconds": 0.37405991554260254} {"step": 9430, "total_steps": 22439, "tokens": 84048609280, "source": "fineweb_hq", "phase": 1, "loss": 1.8874724805355072, "ce_loss": 1.8874724805355072, "logit_z_loss": 44.105130195617676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21881923079490662, "tokens_per_second": 8226599.418685316, "eta_seconds": 14094.2640042305, "data_wait_seconds": 1.609325408935547e-05} {"step": 9440, "total_steps": 22439, "tokens": 84137738240, "source": "fineweb_hq", "phase": 1, "loss": 1.9953331649303436, "ce_loss": 1.9953331649303436, "logit_z_loss": 41.04299068450928, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27124375104904175, "tokens_per_second": 8882325.564732967, "eta_seconds": 13043.73885641098, "data_wait_seconds": 2.4080276489257812e-05} {"step": 9450, "total_steps": 22439, "tokens": 84226867200, "source": "fineweb_hq", "phase": 1, "loss": 1.9738336503505707, "ce_loss": 1.9738336503505707, "logit_z_loss": 43.00626754760742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21339119970798492, "tokens_per_second": 9766862.89042421, "eta_seconds": 11853.305144429207, "data_wait_seconds": 1.52587890625e-05} {"step": 9460, "total_steps": 22439, "tokens": 84315996160, "source": "fineweb_hq", "phase": 1, "loss": 1.987962692975998, "ce_loss": 1.987962692975998, "logit_z_loss": 41.976667404174805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25581860542297363, "tokens_per_second": 8775570.370098483, "eta_seconds": 13182.103533482552, "data_wait_seconds": 1.4424324035644531e-05} {"step": 9470, "total_steps": 22439, "tokens": 84405125120, "source": "fineweb_hq", "phase": 1, "loss": 1.9814948737621307, "ce_loss": 1.9814948737621307, "logit_z_loss": 44.53179931640625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2963275909423828, "tokens_per_second": 9508968.535036579, "eta_seconds": 12156.034358310699, "data_wait_seconds": 1.8596649169921875e-05} {"step": 9480, "total_steps": 22439, "tokens": 84494254080, "source": "fineweb_hq", "phase": 1, "loss": 1.9786895513534546, "ce_loss": 1.9786895513534546, "logit_z_loss": 44.90840816497803, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24318696558475494, "tokens_per_second": 9116280.384386288, "eta_seconds": 12669.884469747543, "data_wait_seconds": 1.722574234008789e-05} {"step": 9490, "total_steps": 22439, "tokens": 84583383040, "source": "fineweb_hq", "phase": 1, "loss": 1.98308065533638, "ce_loss": 1.98308065533638, "logit_z_loss": 45.88521194458008, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2674618065357208, "tokens_per_second": 9293275.614286529, "eta_seconds": 12418.98928797245, "data_wait_seconds": 1.6570091247558594e-05} {"step": 9500, "total_steps": 22439, "tokens": 84672512000, "source": "fineweb_hq", "phase": 1, "loss": 1.970241665840149, "ce_loss": 1.970241665840149, "logit_z_loss": 46.55625057220459, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21318048238754272, "tokens_per_second": 6338120.198904633, "eta_seconds": 18195.29414477348, "data_wait_seconds": 0.266121506690979} {"step": 9510, "total_steps": 22439, "tokens": 84761640960, "source": "fineweb_hq", "phase": 1, "loss": 1.9518376886844635, "ce_loss": 1.9518376886844635, "logit_z_loss": 48.98061466217041, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2233879417181015, "tokens_per_second": 7565652.351029281, "eta_seconds": 15231.31476802826, "data_wait_seconds": 0.2146661877632141} {"step": 9520, "total_steps": 22439, "tokens": 84850769920, "source": "fineweb_hq", "phase": 1, "loss": 1.9405188858509064, "ce_loss": 1.9405188858509064, "logit_z_loss": 49.313042640686035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24893788993358612, "tokens_per_second": 6526353.729551655, "eta_seconds": 17643.1906996727, "data_wait_seconds": 0.6616272926330566} {"step": 9530, "total_steps": 22439, "tokens": 84939898880, "source": "fineweb_hq", "phase": 1, "loss": 1.9415769577026367, "ce_loss": 1.9415769577026367, "logit_z_loss": 51.6072940826416, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21913206577301025, "tokens_per_second": 5641850.455521294, "eta_seconds": 20393.410880184176, "data_wait_seconds": 0.33822834491729736} {"step": 9540, "total_steps": 22439, "tokens": 85029027840, "source": "fineweb_hq", "phase": 1, "loss": 1.9470135271549225, "ce_loss": 1.9470135271549225, "logit_z_loss": 46.530381202697754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26500949263572693, "tokens_per_second": 5343040.014603554, "eta_seconds": 21517.23460609913, "data_wait_seconds": 1.7702579498291016e-05} {"step": 9550, "total_steps": 22439, "tokens": 85118156800, "source": "fineweb_hq", "phase": 1, "loss": 1.942518711090088, "ce_loss": 1.942518711090088, "logit_z_loss": 50.468618392944336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2570122182369232, "tokens_per_second": 1536515.599596399, "eta_seconds": 74765.4736301899, "data_wait_seconds": 1.875576674938202} {"step": 9560, "total_steps": 22439, "tokens": 85207285760, "source": "fineweb_hq", "phase": 1, "loss": 1.9341232180595398, "ce_loss": 1.9341232180595398, "logit_z_loss": 51.6296272277832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2048700749874115, "tokens_per_second": 7583313.6538152, "eta_seconds": 15137.075007605552, "data_wait_seconds": 0.12481027841567993} {"step": 9570, "total_steps": 22439, "tokens": 85296414720, "source": "fineweb_hq", "phase": 1, "loss": 1.9269722700119019, "ce_loss": 1.9269722700119019, "logit_z_loss": 54.683194160461426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2714824676513672, "tokens_per_second": 8775064.869698483, "eta_seconds": 13071.13512289524, "data_wait_seconds": 1.1861324310302734e-05} {"step": 9580, "total_steps": 22439, "tokens": 85385543680, "source": "fineweb_hq", "phase": 1, "loss": 1.9370276927947998, "ce_loss": 1.9370276927947998, "logit_z_loss": 53.24695587158203, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22044067084789276, "tokens_per_second": 8543986.321443567, "eta_seconds": 13414.222044849397, "data_wait_seconds": 1.704692840576172e-05} {"step": 9590, "total_steps": 22439, "tokens": 85474672640, "source": "fineweb_hq", "phase": 1, "loss": 1.9426605105400085, "ce_loss": 1.9426605105400085, "logit_z_loss": 52.70921039581299, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22545462846755981, "tokens_per_second": 7675786.672423463, "eta_seconds": 14919.877999663353, "data_wait_seconds": 0.6820500493049622} {"step": 9600, "total_steps": 22439, "tokens": 85563801600, "source": "fineweb_hq", "phase": 1, "loss": 1.8509272038936615, "ce_loss": 1.8509272038936615, "logit_z_loss": 52.92994976043701, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24846215546131134, "tokens_per_second": 6464317.776294052, "eta_seconds": 17702.20396089554, "data_wait_seconds": 0.5356127023696899} {"step": 9610, "total_steps": 22439, "tokens": 85652930560, "source": "fineweb_hq", "phase": 1, "loss": 1.7973390519618988, "ce_loss": 1.7973390519618988, "logit_z_loss": 59.48188781738281, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23480796813964844, "tokens_per_second": 7164947.534632658, "eta_seconds": 15958.741111683845, "data_wait_seconds": 1.621246337890625e-05} {"step": 9620, "total_steps": 22439, "tokens": 85742059520, "source": "fineweb_hq", "phase": 1, "loss": 1.7440567314624786, "ce_loss": 1.7440567314624786, "logit_z_loss": 63.03021240234375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20250816643238068, "tokens_per_second": 9598422.690619223, "eta_seconds": 11903.457214450837, "data_wait_seconds": 0.31932878494262695} {"step": 9630, "total_steps": 22439, "tokens": 85831188480, "source": "fineweb_hq", "phase": 1, "loss": 1.7541173994541168, "ce_loss": 1.7541173994541168, "logit_z_loss": 61.715664863586426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24220316112041473, "tokens_per_second": 8875994.305250011, "eta_seconds": 12862.253054451941, "data_wait_seconds": 1.6689300537109375e-05} {"step": 9640, "total_steps": 22439, "tokens": 85920317440, "source": "fineweb_hq", "phase": 1, "loss": 1.750697284936905, "ce_loss": 1.750697284936905, "logit_z_loss": 63.30853843688965, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26285210251808167, "tokens_per_second": 11117671.273057891, "eta_seconds": 10260.795907902717, "data_wait_seconds": 1.6033649444580078e-05} {"step": 9650, "total_steps": 22439, "tokens": 86009446400, "source": "fineweb_hq", "phase": 1, "loss": 1.7218170464038849, "ce_loss": 1.7218170464038849, "logit_z_loss": 68.39541625976562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.187678262591362, "tokens_per_second": 9610693.108767586, "eta_seconds": 11860.437707662582, "data_wait_seconds": 1.621246337890625e-05} {"step": 9660, "total_steps": 22439, "tokens": 86098575360, "source": "fineweb_hq", "phase": 1, "loss": 1.74608713388443, "ce_loss": 1.74608713388443, "logit_z_loss": 68.60484886169434, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2533438503742218, "tokens_per_second": 8451464.760238823, "eta_seconds": 13476.705070090295, "data_wait_seconds": 1.4901161193847656e-05} {"step": 9670, "total_steps": 22439, "tokens": 86187704320, "source": "fineweb_hq", "phase": 1, "loss": 1.720708191394806, "ce_loss": 1.720708191394806, "logit_z_loss": 65.23698806762695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23746739327907562, "tokens_per_second": 9761346.147644524, "eta_seconds": 11659.126446557046, "data_wait_seconds": 1.9848346710205078e-05} {"step": 9680, "total_steps": 22439, "tokens": 86276833280, "source": "fineweb_hq", "phase": 1, "loss": 1.7307626605033875, "ce_loss": 1.7307626605033875, "logit_z_loss": 65.84566688537598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24766966700553894, "tokens_per_second": 8604425.496363625, "eta_seconds": 13216.412892651559, "data_wait_seconds": 1.5676021575927734e-05} {"step": 9690, "total_steps": 22439, "tokens": 86365962240, "source": "fineweb_hq", "phase": 1, "loss": 1.7394394278526306, "ce_loss": 1.7394394278526306, "logit_z_loss": 63.6712703704834, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22100013494491577, "tokens_per_second": 10182165.311365241, "eta_seconds": 11159.759012866021, "data_wait_seconds": 1.3828277587890625e-05} {"step": 9700, "total_steps": 22439, "tokens": 86455091200, "source": "fineweb_hq", "phase": 1, "loss": 1.827106088399887, "ce_loss": 1.827106088399887, "logit_z_loss": 61.95872497558594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2440936416387558, "tokens_per_second": 8420877.731757639, "eta_seconds": 13483.319169425964, "data_wait_seconds": 1.531839370727539e-05} {"step": 9710, "total_steps": 22439, "tokens": 86544220160, "source": "fineweb_hq", "phase": 1, "loss": 1.881878912448883, "ce_loss": 1.881878912448883, "logit_z_loss": 59.6358585357666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2374853640794754, "tokens_per_second": 8444433.81517893, "eta_seconds": 13435.152156686781, "data_wait_seconds": 1.7940998077392578e-05} {"step": 9720, "total_steps": 22439, "tokens": 86633349120, "source": "fineweb_hq", "phase": 1, "loss": 1.9111838638782501, "ce_loss": 1.9111838638782501, "logit_z_loss": 61.031206130981445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22187890112400055, "tokens_per_second": 10186912.136157596, "eta_seconds": 11128.310788273811, "data_wait_seconds": 0.0369342565536499} {"step": 9730, "total_steps": 22439, "tokens": 86722478080, "source": "fineweb_hq", "phase": 1, "loss": 1.9273001849651337, "ce_loss": 1.9273001849651337, "logit_z_loss": 55.622554779052734, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2440791130065918, "tokens_per_second": 8912472.932582647, "eta_seconds": 12709.60328528881, "data_wait_seconds": 1.5616416931152344e-05} {"step": 9740, "total_steps": 22439, "tokens": 86811607040, "source": "fineweb_hq", "phase": 1, "loss": 1.922165721654892, "ce_loss": 1.922165721654892, "logit_z_loss": 51.9896936416626, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2411205768585205, "tokens_per_second": 9167365.501026183, "eta_seconds": 12346.498706889153, "data_wait_seconds": 0.5430099964141846} {"step": 9750, "total_steps": 22439, "tokens": 86900736000, "source": "fineweb_hq", "phase": 1, "loss": 1.9604479670524597, "ce_loss": 1.9604479670524597, "logit_z_loss": 56.431983947753906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24200980365276337, "tokens_per_second": 6763776.119005015, "eta_seconds": 16720.798464369775, "data_wait_seconds": 1.2695789337158203e-05} {"step": 9760, "total_steps": 22439, "tokens": 86989864960, "source": "fineweb_hq", "phase": 1, "loss": 1.9624070823192596, "ce_loss": 1.9624070823192596, "logit_z_loss": 49.66936206817627, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22094473242759705, "tokens_per_second": 8124107.384334996, "eta_seconds": 13910.033808994294, "data_wait_seconds": 0.589232861995697} {"step": 9770, "total_steps": 22439, "tokens": 87078993920, "source": "fineweb_hq", "phase": 1, "loss": 1.9737742841243744, "ce_loss": 1.9737742841243744, "logit_z_loss": 57.69807434082031, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2830978333950043, "tokens_per_second": 8093019.301696485, "eta_seconds": 13952.453987145425, "data_wait_seconds": 1.6391277313232422e-05} {"step": 9780, "total_steps": 22439, "tokens": 87168122880, "source": "fineweb_hq", "phase": 1, "loss": 1.954890877008438, "ce_loss": 1.954890877008438, "logit_z_loss": 54.34807777404785, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22053566575050354, "tokens_per_second": 8778574.29279461, "eta_seconds": 12852.69642891884, "data_wait_seconds": 1.5735626220703125e-05} {"step": 9790, "total_steps": 22439, "tokens": 87257251840, "source": "fineweb_hq", "phase": 1, "loss": 1.965626448392868, "ce_loss": 1.965626448392868, "logit_z_loss": 53.49591636657715, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2545514702796936, "tokens_per_second": 8465776.35631114, "eta_seconds": 13317.056435108185, "data_wait_seconds": 1.7821788787841797e-05} {"step": 9800, "total_steps": 22439, "tokens": 87346380800, "source": "fineweb_hq", "phase": 1, "loss": 1.9658661484718323, "ce_loss": 1.9658661484718323, "logit_z_loss": 55.84089469909668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2193651646375656, "tokens_per_second": 9201503.017952772, "eta_seconds": 12242.575188446044, "data_wait_seconds": 1.9669532775878906e-05} {"step": 9810, "total_steps": 22439, "tokens": 87435509760, "source": "fineweb_hq", "phase": 1, "loss": 1.971415489912033, "ce_loss": 1.971415489912033, "logit_z_loss": 59.98384666442871, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2139427363872528, "tokens_per_second": 10221318.570433717, "eta_seconds": 11012.372113084793, "data_wait_seconds": 1.704692840576172e-05} {"step": 9820, "total_steps": 22439, "tokens": 87524638720, "source": "fineweb_hq", "phase": 1, "loss": 1.9602888524532318, "ce_loss": 1.9602888524532318, "logit_z_loss": 55.98921012878418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23575229942798615, "tokens_per_second": 9138693.167834848, "eta_seconds": 12307.212044262888, "data_wait_seconds": 1.531839370727539e-05} {"step": 9830, "total_steps": 22439, "tokens": 87613767680, "source": "fineweb_hq", "phase": 1, "loss": 1.9587727189064026, "ce_loss": 1.9587727189064026, "logit_z_loss": 53.881205558776855, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2713847756385803, "tokens_per_second": 8784508.013040403, "eta_seconds": 12793.283983254432, "data_wait_seconds": 1.7881393432617188e-05} {"step": 9840, "total_steps": 22439, "tokens": 87702896640, "source": "fineweb_hq", "phase": 1, "loss": 1.9620111584663391, "ce_loss": 1.9620111584663391, "logit_z_loss": 57.3950309753418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20985153317451477, "tokens_per_second": 8306908.559083809, "eta_seconds": 13518.094716620446, "data_wait_seconds": 0.2620736360549927} {"step": 9850, "total_steps": 22439, "tokens": 87792025600, "source": "fineweb_hq", "phase": 1, "loss": 1.9485237300395966, "ce_loss": 1.9485237300395966, "logit_z_loss": 60.34073257446289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19788941740989685, "tokens_per_second": 8953629.714283962, "eta_seconds": 12531.727503204347, "data_wait_seconds": 1.6450881958007812e-05} {"step": 9860, "total_steps": 22439, "tokens": 87881154560, "source": "fineweb_hq", "phase": 1, "loss": 1.930121749639511, "ce_loss": 1.930121749639511, "logit_z_loss": 61.961058616638184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2588943541049957, "tokens_per_second": 8489173.640694955, "eta_seconds": 13206.858939313888, "data_wait_seconds": 0.24091660976409912} {"step": 9870, "total_steps": 22439, "tokens": 87970283520, "source": "fineweb_hq", "phase": 1, "loss": 1.956048458814621, "ce_loss": 1.956048458814621, "logit_z_loss": 59.53172016143799, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20070216059684753, "tokens_per_second": 8984764.623042842, "eta_seconds": 12468.461281299591, "data_wait_seconds": 1.5676021575927734e-05} {"step": 9880, "total_steps": 22439, "tokens": 88059412480, "source": "fineweb_hq", "phase": 1, "loss": 1.9259427785873413, "ce_loss": 1.9259427785873413, "logit_z_loss": 63.44951915740967, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2917712926864624, "tokens_per_second": 9639685.985291814, "eta_seconds": 11612.10655977726, "data_wait_seconds": 0.07674860954284668} {"step": 9890, "total_steps": 22439, "tokens": 88148541440, "source": "fineweb_hq", "phase": 1, "loss": 1.9275493025779724, "ce_loss": 1.9275493025779724, "logit_z_loss": 59.325316429138184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2552804946899414, "tokens_per_second": 8930031.518233346, "eta_seconds": 12524.920172524453, "data_wait_seconds": 0.24715858697891235} {"step": 9900, "total_steps": 22439, "tokens": 88237670400, "source": "fineweb_hq", "phase": 1, "loss": 1.9292663037776947, "ce_loss": 1.9292663037776947, "logit_z_loss": 65.30245018005371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2538163363933563, "tokens_per_second": 8419512.97031907, "eta_seconds": 13273.784759044647, "data_wait_seconds": 1.5735626220703125e-05} {"step": 9910, "total_steps": 22439, "tokens": 88326799360, "source": "fineweb_hq", "phase": 1, "loss": 1.9361361861228943, "ce_loss": 1.9361361861228943, "logit_z_loss": 62.076252937316895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2523325979709625, "tokens_per_second": 10101122.928953674, "eta_seconds": 11055.174238491058, "data_wait_seconds": 1.436471939086914e-05} {"step": 9920, "total_steps": 22439, "tokens": 88415928320, "source": "fineweb_hq", "phase": 1, "loss": 1.9268408417701721, "ce_loss": 1.9268408417701721, "logit_z_loss": 61.23367404937744, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22717487812042236, "tokens_per_second": 9473446.449487992, "eta_seconds": 11778.24201772213, "data_wait_seconds": 0.0005019903182983398} {"step": 9930, "total_steps": 22439, "tokens": 88505057280, "source": "fineweb_hq", "phase": 1, "loss": 1.9318345189094543, "ce_loss": 1.9318345189094543, "logit_z_loss": 62.73935890197754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2122001051902771, "tokens_per_second": 9233638.202050358, "eta_seconds": 12074.483927607536, "data_wait_seconds": 1.8417835235595703e-05} {"step": 9940, "total_steps": 22439, "tokens": 88594186240, "source": "fineweb_hq", "phase": 1, "loss": 1.9688722491264343, "ce_loss": 1.9688722491264343, "logit_z_loss": 64.40108489990234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23932452499866486, "tokens_per_second": 7076793.661689074, "eta_seconds": 15741.915396952629, "data_wait_seconds": 1.436471939086914e-05} {"step": 9950, "total_steps": 22439, "tokens": 88683315200, "source": "fineweb_hq", "phase": 1, "loss": 1.989538699388504, "ce_loss": 1.989538699388504, "logit_z_loss": 63.04613494873047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22350238263607025, "tokens_per_second": 7721221.105419402, "eta_seconds": 14416.522545361518, "data_wait_seconds": 1.615285873413086e-05} {"step": 9960, "total_steps": 22439, "tokens": 88772444160, "source": "fineweb_hq", "phase": 1, "loss": 2.013659566640854, "ce_loss": 2.013659566640854, "logit_z_loss": 57.51537227630615, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3114334046840668, "tokens_per_second": 6171122.145258323, "eta_seconds": 18023.30703654289, "data_wait_seconds": 0.6859644651412964} {"step": 9970, "total_steps": 22439, "tokens": 88861573120, "source": "fineweb_hq", "phase": 1, "loss": 2.013848602771759, "ce_loss": 2.013848602771759, "logit_z_loss": 57.549076080322266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.257997989654541, "tokens_per_second": 3023841.1082967822, "eta_seconds": 36752.890196204185, "data_wait_seconds": 0.3819285035133362} {"step": 9980, "total_steps": 22439, "tokens": 88950702080, "source": "fineweb_hq", "phase": 1, "loss": 1.9959567189216614, "ce_loss": 1.9959567189216614, "logit_z_loss": 61.8864221572876, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21450401842594147, "tokens_per_second": 8032560.359731478, "eta_seconds": 13824.455253481865, "data_wait_seconds": 1.4841556549072266e-05} {"step": 9990, "total_steps": 22439, "tokens": 89039831040, "source": "fineweb_hq", "phase": 1, "loss": 1.9928065240383148, "ce_loss": 1.9928065240383148, "logit_z_loss": 61.557905197143555, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2190602421760559, "tokens_per_second": 8811749.53144018, "eta_seconds": 12591.89697892666, "data_wait_seconds": 1.5616416931152344e-05} {"step": 10000, "total_steps": 22439, "tokens": 89128960000, "source": "fineweb_hq", "phase": 1, "loss": 1.9848710298538208, "ce_loss": 1.9848710298538208, "logit_z_loss": 64.61446952819824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22535477578639984, "tokens_per_second": 6639195.540468455, "eta_seconds": 16698.937795734404, "data_wait_seconds": 0.22736716270446777} {"step": 10010, "total_steps": 22439, "tokens": 89218088960, "source": "fineweb_hq", "phase": 1, "loss": 2.0035621523857117, "ce_loss": 2.0035621523857117, "logit_z_loss": 59.34299373626709, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.231859490275383, "tokens_per_second": 7904997.108189239, "eta_seconds": 14013.715991020203, "data_wait_seconds": 1.7821788787841797e-05} {"step": 10020, "total_steps": 22439, "tokens": 89307217920, "source": "fineweb_hq", "phase": 1, "loss": 1.9829587936401367, "ce_loss": 1.9829587936401367, "logit_z_loss": 64.13888931274414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23446416854858398, "tokens_per_second": 8309956.832469036, "eta_seconds": 13320.075862669946, "data_wait_seconds": 0.26732516288757324} {"step": 10030, "total_steps": 22439, "tokens": 89396346880, "source": "fineweb_hq", "phase": 1, "loss": 1.9810285568237305, "ce_loss": 1.9810285568237305, "logit_z_loss": 61.35946464538574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23448823392391205, "tokens_per_second": 8628567.257146819, "eta_seconds": 12817.901647853852, "data_wait_seconds": 1.4722347259521484e-05} {"step": 10040, "total_steps": 22439, "tokens": 89485475840, "source": "fineweb_hq", "phase": 1, "loss": 2.0007737278938293, "ce_loss": 2.0007737278938293, "logit_z_loss": 61.58579730987549, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2546621859073639, "tokens_per_second": 8800820.615964765, "eta_seconds": 12556.896944761276, "data_wait_seconds": 1.3887882232666016e-05} {"step": 10050, "total_steps": 22439, "tokens": 89574604800, "source": "fineweb_hq", "phase": 1, "loss": 1.9725029170513153, "ce_loss": 1.9725029170513153, "logit_z_loss": 63.27691459655762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20085012912750244, "tokens_per_second": 8394562.341116574, "eta_seconds": 13153.975640058516, "data_wait_seconds": 1.71661376953125e-05} {"step": 10060, "total_steps": 22439, "tokens": 89663733760, "source": "fineweb_hq", "phase": 1, "loss": 1.9490131437778473, "ce_loss": 1.9490131437778473, "logit_z_loss": 63.32782745361328, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2511979937553406, "tokens_per_second": 6798869.574058045, "eta_seconds": 16228.100624990464, "data_wait_seconds": 0.3122580051422119} {"step": 10070, "total_steps": 22439, "tokens": 89752862720, "source": "fineweb_hq", "phase": 1, "loss": 1.931158423423767, "ce_loss": 1.931158423423767, "logit_z_loss": 61.20680522918701, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24479205906391144, "tokens_per_second": 8194261.172272201, "eta_seconds": 13453.758466601372, "data_wait_seconds": 0.6429576873779297} {"step": 10080, "total_steps": 22439, "tokens": 89841991680, "source": "fineweb_hq", "phase": 1, "loss": 1.9135977625846863, "ce_loss": 1.9135977625846863, "logit_z_loss": 67.25369071960449, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19773094356060028, "tokens_per_second": 9845812.03291363, "eta_seconds": 11187.952938342094, "data_wait_seconds": 1.996755599975586e-05} {"step": 10090, "total_steps": 22439, "tokens": 89931120640, "source": "fineweb_hq", "phase": 1, "loss": 1.910376787185669, "ce_loss": 1.910376787185669, "logit_z_loss": 67.4998722076416, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.257967084646225, "tokens_per_second": 10299789.599310104, "eta_seconds": 10686.174862384796, "data_wait_seconds": 1.3887882232666016e-05} {"step": 10100, "total_steps": 22439, "tokens": 90020249600, "source": "fineweb_hq", "phase": 1, "loss": 1.9126804172992706, "ce_loss": 1.9126804172992706, "logit_z_loss": 68.14409828186035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29396286606788635, "tokens_per_second": 13810202.087701594, "eta_seconds": 7963.404376387596, "data_wait_seconds": 1.6689300537109375e-05} {"step": 10110, "total_steps": 22439, "tokens": 90109378560, "source": "fineweb_hq", "phase": 1, "loss": 1.904731035232544, "ce_loss": 1.904731035232544, "logit_z_loss": 68.4383716583252, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27432793378829956, "tokens_per_second": 9229700.667696096, "eta_seconds": 11905.813497138022, "data_wait_seconds": 1.33514404296875e-05} {"step": 10120, "total_steps": 22439, "tokens": 90198507520, "source": "fineweb_hq", "phase": 1, "loss": 1.8972892463207245, "ce_loss": 1.8972892463207245, "logit_z_loss": 69.09909248352051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23172985017299652, "tokens_per_second": 9275723.66947549, "eta_seconds": 11837.132038044929, "data_wait_seconds": 1.6987323760986328e-05} {"step": 10130, "total_steps": 22439, "tokens": 90287636480, "source": "fineweb_hq", "phase": 1, "loss": 1.905683845281601, "ce_loss": 1.905683845281601, "logit_z_loss": 67.17062377929688, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.250712126493454, "tokens_per_second": 9033556.528516067, "eta_seconds": 12144.589621782303, "data_wait_seconds": 1.8835067749023438e-05} {"step": 10140, "total_steps": 22439, "tokens": 90376765440, "source": "fineweb_hq", "phase": 1, "loss": 1.8982174694538116, "ce_loss": 1.8982174694538116, "logit_z_loss": 70.12163925170898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18897745013237, "tokens_per_second": 8422478.229574732, "eta_seconds": 13015.136984157562, "data_wait_seconds": 1.436471939086914e-05} {"step": 10150, "total_steps": 22439, "tokens": 90465894400, "source": "fineweb_hq", "phase": 1, "loss": 1.902219533920288, "ce_loss": 1.902219533920288, "logit_z_loss": 68.8799991607666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27745309472084045, "tokens_per_second": 7510529.475856253, "eta_seconds": 14583.602833342551, "data_wait_seconds": 1.7702579498291016e-05} {"step": 10160, "total_steps": 22439, "tokens": 90555023360, "source": "fineweb_hq", "phase": 1, "loss": 1.9282495081424713, "ce_loss": 1.9282495081424713, "logit_z_loss": 68.89831733703613, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24223549664020538, "tokens_per_second": 9718236.346678473, "eta_seconds": 11261.451777863502, "data_wait_seconds": 1.3232231140136719e-05} {"step": 10170, "total_steps": 22439, "tokens": 90644152320, "source": "fineweb_hq", "phase": 1, "loss": 1.938812255859375, "ce_loss": 1.938812255859375, "logit_z_loss": 62.93348217010498, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20956474542617798, "tokens_per_second": 7992578.255453466, "eta_seconds": 13681.732918834687, "data_wait_seconds": 1.424551010131836e-05} {"step": 10180, "total_steps": 22439, "tokens": 90733281280, "source": "fineweb_hq", "phase": 1, "loss": 1.9422836005687714, "ce_loss": 1.9422836005687714, "logit_z_loss": 66.35282897949219, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2538853585720062, "tokens_per_second": 8813849.507117385, "eta_seconds": 12396.761707329752, "data_wait_seconds": 0.20754408836364746} {"step": 10190, "total_steps": 22439, "tokens": 90822410240, "source": "fineweb_hq", "phase": 1, "loss": 1.9379872679710388, "ce_loss": 1.9379872679710388, "logit_z_loss": 66.72313499450684, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21917866170406342, "tokens_per_second": 9084378.17547918, "eta_seconds": 12017.780523347854, "data_wait_seconds": 1.5854835510253906e-05} {"step": 10200, "total_steps": 22439, "tokens": 90911539200, "source": "fineweb_hq", "phase": 1, "loss": 1.9352053999900818, "ce_loss": 1.9352053999900818, "logit_z_loss": 67.23934555053711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2691737115383148, "tokens_per_second": 9829487.900582366, "eta_seconds": 11097.723019480707, "data_wait_seconds": 1.7404556274414062e-05} {"step": 10210, "total_steps": 22439, "tokens": 91000668160, "source": "fineweb_hq", "phase": 1, "loss": 1.9328056871891022, "ce_loss": 1.9328056871891022, "logit_z_loss": 70.04197120666504, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2623480260372162, "tokens_per_second": 8355052.973306019, "eta_seconds": 13045.495406460763, "data_wait_seconds": 1.5914440155029297e-05} {"step": 10220, "total_steps": 22439, "tokens": 91089797120, "source": "fineweb_hq", "phase": 1, "loss": 1.9322841167449951, "ce_loss": 1.9322841167449951, "logit_z_loss": 66.73787117004395, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23485903441905975, "tokens_per_second": 9831611.557849098, "eta_seconds": 11077.194779634476, "data_wait_seconds": 1.4483928680419922e-05} {"step": 10230, "total_steps": 22439, "tokens": 91178926080, "source": "fineweb_hq", "phase": 1, "loss": 1.9379306137561798, "ce_loss": 1.9379306137561798, "logit_z_loss": 66.06467056274414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19894279539585114, "tokens_per_second": 8921378.778240561, "eta_seconds": 12197.39122941494, "data_wait_seconds": 0.05352330207824707} {"step": 10240, "total_steps": 22439, "tokens": 91268055040, "source": "fineweb_hq", "phase": 1, "loss": 1.9372605383396149, "ce_loss": 1.9372605383396149, "logit_z_loss": 69.7763557434082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2567315399646759, "tokens_per_second": 9310003.92448614, "eta_seconds": 11678.665141916275, "data_wait_seconds": 1.4126300811767578e-05} {"step": 10250, "total_steps": 22439, "tokens": 91357184000, "source": "fineweb_hq", "phase": 1, "loss": 1.9506708085536957, "ce_loss": 1.9506708085536957, "logit_z_loss": 66.74792289733887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2166617512702942, "tokens_per_second": 7086569.914716005, "eta_seconds": 15330.306573057174, "data_wait_seconds": 1.704692840576172e-05} {"step": 10260, "total_steps": 22439, "tokens": 91446312960, "source": "fineweb_hq", "phase": 1, "loss": 1.9701649248600006, "ce_loss": 1.9701649248600006, "logit_z_loss": 70.86153221130371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2177714705467224, "tokens_per_second": 7292951.106410509, "eta_seconds": 14884.257250618935, "data_wait_seconds": 1.4901161193847656e-05} {"step": 10270, "total_steps": 22439, "tokens": 91535441920, "source": "fineweb_hq", "phase": 1, "loss": 1.9805365800857544, "ce_loss": 1.9805365800857544, "logit_z_loss": 65.3884220123291, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24453842639923096, "tokens_per_second": 8276133.907104385, "eta_seconds": 13105.27749326229, "data_wait_seconds": 0.5910347700119019} {"step": 10280, "total_steps": 22439, "tokens": 91624570880, "source": "fineweb_hq", "phase": 1, "loss": 1.9729127287864685, "ce_loss": 1.9729127287864685, "logit_z_loss": 67.08537673950195, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2649990916252136, "tokens_per_second": 6228207.164873877, "eta_seconds": 17400.17626183033, "data_wait_seconds": 0.31739532947540283} {"step": 10290, "total_steps": 22439, "tokens": 91713699840, "source": "fineweb_hq", "phase": 1, "loss": 1.981035590171814, "ce_loss": 1.981035590171814, "logit_z_loss": 64.54805374145508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2237197905778885, "tokens_per_second": 6600242.852819972, "eta_seconds": 16405.87716522217, "data_wait_seconds": 0.3867683410644531} {"step": 10300, "total_steps": 22439, "tokens": 91802828800, "source": "fineweb_hq", "phase": 1, "loss": 1.9749411046504974, "ce_loss": 1.9749411046504974, "logit_z_loss": 68.13088989257812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2561257481575012, "tokens_per_second": 6332984.07016038, "eta_seconds": 17084.1491697073, "data_wait_seconds": 1.5914440155029297e-05} {"step": 10310, "total_steps": 22439, "tokens": 91891957760, "source": "fineweb_hq", "phase": 1, "loss": 1.9878762364387512, "ce_loss": 1.9878762364387512, "logit_z_loss": 68.11370849609375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23517853021621704, "tokens_per_second": 6362277.22362437, "eta_seconds": 16991.481474995613, "data_wait_seconds": 0.3112486004829407} {"step": 10320, "total_steps": 22439, "tokens": 91981086720, "source": "fineweb_hq", "phase": 1, "loss": 1.9872187972068787, "ce_loss": 1.9872187972068787, "logit_z_loss": 67.33786582946777, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2679179608821869, "tokens_per_second": 8552977.944697872, "eta_seconds": 12628.979908800124, "data_wait_seconds": 0.13057267665863037} {"step": 10330, "total_steps": 22439, "tokens": 92070215680, "source": "fineweb_hq", "phase": 1, "loss": 1.9974149465560913, "ce_loss": 1.9974149465560913, "logit_z_loss": 66.87938690185547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29182931780815125, "tokens_per_second": 7517474.750503336, "eta_seconds": 14356.717015480996, "data_wait_seconds": 1.7642974853515625e-05} {"step": 10340, "total_steps": 22439, "tokens": 92159344640, "source": "fineweb_hq", "phase": 1, "loss": 1.9850939810276031, "ce_loss": 1.9850939810276031, "logit_z_loss": 70.3608570098877, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24795499444007874, "tokens_per_second": 8905732.225043755, "eta_seconds": 12108.73244097233, "data_wait_seconds": 1.4781951904296875e-05} {"step": 10350, "total_steps": 22439, "tokens": 92248473600, "source": "fineweb_hq", "phase": 1, "loss": 1.9855325818061829, "ce_loss": 1.9855325818061829, "logit_z_loss": 72.74356842041016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2005610167980194, "tokens_per_second": 7067667.630328914, "eta_seconds": 15245.199035906791, "data_wait_seconds": 1.7344951629638672e-05} {"step": 10360, "total_steps": 22439, "tokens": 92337602560, "source": "fineweb_hq", "phase": 1, "loss": 1.991353988647461, "ce_loss": 1.991353988647461, "logit_z_loss": 65.18115234375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2798220217227936, "tokens_per_second": 8668326.98151632, "eta_seconds": 12419.798077940943, "data_wait_seconds": 1.6927719116210938e-05} {"step": 10370, "total_steps": 22439, "tokens": 92426731520, "source": "fineweb_hq", "phase": 1, "loss": 1.9878953099250793, "ce_loss": 1.9878953099250793, "logit_z_loss": 67.92120742797852, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2750779390335083, "tokens_per_second": 7938426.371015951, "eta_seconds": 13550.512002825737, "data_wait_seconds": 1.6808509826660156e-05} {"step": 10380, "total_steps": 22439, "tokens": 92515860480, "source": "fineweb_hq", "phase": 1, "loss": 1.9929405748844147, "ce_loss": 1.9929405748844147, "logit_z_loss": 68.71237373352051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2917802929878235, "tokens_per_second": 9321936.670246318, "eta_seconds": 11529.858726358414, "data_wait_seconds": 1.4603137969970703e-05} {"step": 10390, "total_steps": 22439, "tokens": 92604989440, "source": "fineweb_hq", "phase": 1, "loss": 1.977658599615097, "ce_loss": 1.977658599615097, "logit_z_loss": 71.5905704498291, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24214228987693787, "tokens_per_second": 9711404.05066035, "eta_seconds": 11058.286046361924, "data_wait_seconds": 1.4424324035644531e-05} {"step": 10400, "total_steps": 22439, "tokens": 92694118400, "source": "fineweb_hq", "phase": 1, "loss": 1.9725300967693329, "ce_loss": 1.9725300967693329, "logit_z_loss": 73.60511779785156, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22574278712272644, "tokens_per_second": 9138826.318100104, "eta_seconds": 11741.371507573129, "data_wait_seconds": 1.5497207641601562e-05} {"step": 10410, "total_steps": 22439, "tokens": 92783247360, "source": "fineweb_hq", "phase": 1, "loss": 1.9828105866909027, "ce_loss": 1.9828105866909027, "logit_z_loss": 69.98666763305664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2080925703048706, "tokens_per_second": 9383916.806000823, "eta_seconds": 11425.210623717308, "data_wait_seconds": 1.4543533325195312e-05} {"step": 10420, "total_steps": 22439, "tokens": 92872376320, "source": "fineweb_hq", "phase": 1, "loss": 1.9810510277748108, "ce_loss": 1.9810510277748108, "logit_z_loss": 66.79701805114746, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3161216378211975, "tokens_per_second": 9351593.519995334, "eta_seconds": 11455.170372295379, "data_wait_seconds": 1.5616416931152344e-05} {"step": 10430, "total_steps": 22439, "tokens": 92961505280, "source": "fineweb_hq", "phase": 1, "loss": 1.9916149973869324, "ce_loss": 1.9916149973869324, "logit_z_loss": 71.32961082458496, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23034080862998962, "tokens_per_second": 8898631.852352876, "eta_seconds": 12028.249942231178, "data_wait_seconds": 1.7940998077392578e-05} {"step": 10440, "total_steps": 22439, "tokens": 93050634240, "source": "fineweb_hq", "phase": 1, "loss": 1.9944967329502106, "ce_loss": 1.9944967329502106, "logit_z_loss": 71.56532669067383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24875852465629578, "tokens_per_second": 9786662.374081533, "eta_seconds": 10927.713148379326, "data_wait_seconds": 1.3828277587890625e-05} {"step": 10450, "total_steps": 22439, "tokens": 93139763200, "source": "fineweb_hq", "phase": 1, "loss": 1.9664903581142426, "ce_loss": 1.9664903581142426, "logit_z_loss": 72.72096824645996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2671225070953369, "tokens_per_second": 6884635.398549378, "eta_seconds": 15521.041269159317, "data_wait_seconds": 1.2814998626708984e-05} {"step": 10460, "total_steps": 22439, "tokens": 93228892160, "source": "fineweb_hq", "phase": 1, "loss": 1.9606167376041412, "ce_loss": 1.9606167376041412, "logit_z_loss": 74.8320083618164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2226303666830063, "tokens_per_second": 8110922.553254012, "eta_seconds": 13163.432455801965, "data_wait_seconds": 1.5616416931152344e-05} {"step": 10470, "total_steps": 22439, "tokens": 93318021120, "source": "fineweb_hq", "phase": 1, "loss": 1.9484582543373108, "ce_loss": 1.9484582543373108, "logit_z_loss": 72.26547241210938, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29036474227905273, "tokens_per_second": 9822717.973624377, "eta_seconds": 10860.380244088174, "data_wait_seconds": 1.5437602996826172e-05} {"step": 10480, "total_steps": 22439, "tokens": 93407150080, "source": "fineweb_hq", "phase": 1, "loss": 1.9301509261131287, "ce_loss": 1.9301509261131287, "logit_z_loss": 74.02713584899902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24315978586673737, "tokens_per_second": 9693815.618068274, "eta_seconds": 10995.600438833237, "data_wait_seconds": 0.043537437915802} {"step": 10490, "total_steps": 22439, "tokens": 93496279040, "source": "fineweb_hq", "phase": 1, "loss": 1.929635226726532, "ce_loss": 1.929635226726532, "logit_z_loss": 74.95917129516602, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23877324163913727, "tokens_per_second": 7914726.241058209, "eta_seconds": 13455.954263019561, "data_wait_seconds": 1.4901161193847656e-05} {"step": 10500, "total_steps": 22439, "tokens": 93585408000, "source": "fineweb_hq", "phase": 1, "loss": 1.95041161775589, "ce_loss": 1.95041161775589, "logit_z_loss": 73.86993598937988, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21192969381809235, "tokens_per_second": 8988165.681612788, "eta_seconds": 11839.019118404387, "data_wait_seconds": 1.537799835205078e-05} {"step": 10510, "total_steps": 22439, "tokens": 93674536960, "source": "fineweb_hq", "phase": 1, "loss": 1.9641863107681274, "ce_loss": 1.9641863107681274, "logit_z_loss": 73.87916946411133, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2760126292705536, "tokens_per_second": 8229674.5378733175, "eta_seconds": 12919.336711883545, "data_wait_seconds": 4.9114227294921875e-05} {"step": 10520, "total_steps": 22439, "tokens": 93763665920, "source": "fineweb_hq", "phase": 1, "loss": 1.9877322018146515, "ce_loss": 1.9877322018146515, "logit_z_loss": 72.76935386657715, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2038183957338333, "tokens_per_second": 8562261.881002516, "eta_seconds": 12407.096267366409, "data_wait_seconds": 0.00032007694244384766} {"step": 10530, "total_steps": 22439, "tokens": 93852794880, "source": "fineweb_hq", "phase": 1, "loss": 1.9830965101718903, "ce_loss": 1.9830965101718903, "logit_z_loss": 70.11295318603516, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2704654932022095, "tokens_per_second": 8286756.411103449, "eta_seconds": 12808.832937550545, "data_wait_seconds": 1.6868114471435547e-05} {"step": 10540, "total_steps": 22439, "tokens": 93941923840, "source": "fineweb_hq", "phase": 1, "loss": 1.9896162450313568, "ce_loss": 1.9896162450313568, "logit_z_loss": 71.21489524841309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29328909516334534, "tokens_per_second": 8929672.092088519, "eta_seconds": 11876.645459127425, "data_wait_seconds": 1.4424324035644531e-05} {"step": 10550, "total_steps": 22439, "tokens": 94031052800, "source": "fineweb_hq", "phase": 1, "loss": 1.9700946509838104, "ce_loss": 1.9700946509838104, "logit_z_loss": 73.78257751464844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19125981628894806, "tokens_per_second": 8700838.089336364, "eta_seconds": 12178.760190224648, "data_wait_seconds": 1.519918441772461e-05} {"step": 10560, "total_steps": 22439, "tokens": 94120181760, "source": "fineweb_hq", "phase": 1, "loss": 1.9657149612903595, "ce_loss": 1.9657149612903595, "logit_z_loss": 75.40043067932129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2736842930316925, "tokens_per_second": 7209780.771286989, "eta_seconds": 14685.091675138474, "data_wait_seconds": 1.519918441772461e-05} {"step": 10570, "total_steps": 22439, "tokens": 94209310720, "source": "fineweb_hq", "phase": 1, "loss": 1.9646224975585938, "ce_loss": 1.9646224975585938, "logit_z_loss": 73.80830001831055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28793248534202576, "tokens_per_second": 7273104.156233411, "eta_seconds": 14544.981118321419, "data_wait_seconds": 0.4500620365142822} {"step": 10580, "total_steps": 22439, "tokens": 94298439680, "source": "fineweb_hq", "phase": 1, "loss": 1.9428363144397736, "ce_loss": 1.9428363144397736, "logit_z_loss": 75.11288452148438, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2056121528148651, "tokens_per_second": 8373971.371186743, "eta_seconds": 12622.211013007163, "data_wait_seconds": 0.3036460280418396} {"step": 10590, "total_steps": 22439, "tokens": 94387568640, "source": "fineweb_hq", "phase": 1, "loss": 1.9483427703380585, "ce_loss": 1.9483427703380585, "logit_z_loss": 77.86996841430664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2196483314037323, "tokens_per_second": 10126682.37714332, "eta_seconds": 10428.776253747941, "data_wait_seconds": 1.4007091522216797e-05} {"step": 10600, "total_steps": 22439, "tokens": 94476697600, "source": "fineweb_hq", "phase": 1, "loss": 1.9465028941631317, "ce_loss": 1.9465028941631317, "logit_z_loss": 69.92579650878906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2615128457546234, "tokens_per_second": 9346298.393048706, "eta_seconds": 11290.007156467438, "data_wait_seconds": 0.22468936443328857} {"step": 10610, "total_steps": 22439, "tokens": 94565826560, "source": "fineweb_hq", "phase": 1, "loss": 1.9386052787303925, "ce_loss": 1.9386052787303925, "logit_z_loss": 75.40484237670898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23656047880649567, "tokens_per_second": 8909485.617929557, "eta_seconds": 11833.527916789055, "data_wait_seconds": 1.519918441772461e-05} {"step": 10620, "total_steps": 22439, "tokens": 94654955520, "source": "fineweb_hq", "phase": 1, "loss": 1.937229722738266, "ce_loss": 1.937229722738266, "logit_z_loss": 73.1838436126709, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28859344124794006, "tokens_per_second": 8916442.548152706, "eta_seconds": 11814.298948836326, "data_wait_seconds": 0.13036423921585083} {"step": 10630, "total_steps": 22439, "tokens": 94744084480, "source": "fineweb_hq", "phase": 1, "loss": 1.939992219209671, "ce_loss": 1.939992219209671, "logit_z_loss": 75.61719703674316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25644055008888245, "tokens_per_second": 8624228.782265915, "eta_seconds": 12204.266783881187, "data_wait_seconds": 1.5616416931152344e-05} {"step": 10640, "total_steps": 22439, "tokens": 94833213440, "source": "fineweb_hq", "phase": 1, "loss": 1.937236249446869, "ce_loss": 1.937236249446869, "logit_z_loss": 80.26948547363281, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2573147714138031, "tokens_per_second": 8427044.773611255, "eta_seconds": 12479.257287597657, "data_wait_seconds": 0.14832478761672974} {"step": 10650, "total_steps": 22439, "tokens": 94922342400, "source": "fineweb_hq", "phase": 1, "loss": 1.949059158563614, "ce_loss": 1.949059158563614, "logit_z_loss": 76.53649711608887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25867196917533875, "tokens_per_second": 7669353.475268725, "eta_seconds": 13700.52003507614, "data_wait_seconds": 1.4185905456542969e-05} {"step": 10660, "total_steps": 22439, "tokens": 95011471360, "source": "fineweb_hq", "phase": 1, "loss": 1.9635476469993591, "ce_loss": 1.9635476469993591, "logit_z_loss": 75.05374526977539, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22407345473766327, "tokens_per_second": 8825906.727464983, "eta_seconds": 11895.095339870453, "data_wait_seconds": 0.6614091992378235} {"step": 10670, "total_steps": 22439, "tokens": 95100600320, "source": "fineweb_hq", "phase": 1, "loss": 1.9734184443950653, "ce_loss": 1.9734184443950653, "logit_z_loss": 74.09757041931152, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2559424936771393, "tokens_per_second": 8728145.53871383, "eta_seconds": 12018.11685640812, "data_wait_seconds": 1.436471939086914e-05} {"step": 10680, "total_steps": 22439, "tokens": 95189729280, "source": "fineweb_hq", "phase": 1, "loss": 1.9725508987903595, "ce_loss": 1.9725508987903595, "logit_z_loss": 75.7772159576416, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19889883697032928, "tokens_per_second": 8373605.045439369, "eta_seconds": 12516.322837686539, "data_wait_seconds": 1.531839370727539e-05} {"step": 10690, "total_steps": 22439, "tokens": 95278858240, "source": "fineweb_hq", "phase": 1, "loss": 1.972013682126999, "ce_loss": 1.972013682126999, "logit_z_loss": 72.56189727783203, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26138919591903687, "tokens_per_second": 8968255.676856603, "eta_seconds": 11676.475211811066, "data_wait_seconds": 0.3287277817726135} {"step": 10700, "total_steps": 22439, "tokens": 95367987200, "source": "fineweb_hq", "phase": 1, "loss": 1.984026461839676, "ce_loss": 1.984026461839676, "logit_z_loss": 73.22743225097656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2531823217868805, "tokens_per_second": 9015652.153705657, "eta_seconds": 11605.20441119671, "data_wait_seconds": 0.33141028881073} {"step": 10710, "total_steps": 22439, "tokens": 95457116160, "source": "fineweb_hq", "phase": 1, "loss": 1.9776151776313782, "ce_loss": 1.9776151776313782, "logit_z_loss": 77.43704605102539, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.208831787109375, "tokens_per_second": 8559855.707492195, "eta_seconds": 12212.747592520715, "data_wait_seconds": 1.2934207916259766e-05} {"step": 10720, "total_steps": 22439, "tokens": 95546245120, "source": "fineweb_hq", "phase": 1, "loss": 1.9818782210350037, "ce_loss": 1.9818782210350037, "logit_z_loss": 75.32609748840332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2626383900642395, "tokens_per_second": 9441530.247780027, "eta_seconds": 11062.849504566193, "data_wait_seconds": 1.3470649719238281e-05} {"step": 10730, "total_steps": 22439, "tokens": 95635374080, "source": "fineweb_hq", "phase": 1, "loss": 1.9807040393352509, "ce_loss": 1.9807040393352509, "logit_z_loss": 76.82274055480957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22405673563480377, "tokens_per_second": 9461344.652942551, "eta_seconds": 11030.260823607445, "data_wait_seconds": 1.9431114196777344e-05} {"step": 10740, "total_steps": 22439, "tokens": 95724503040, "source": "fineweb_hq", "phase": 1, "loss": 1.9803939163684845, "ce_loss": 1.9803939163684845, "logit_z_loss": 76.75339317321777, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.21259234845638275, "tokens_per_second": 8888238.541409425, "eta_seconds": 11731.454980444909, "data_wait_seconds": 0.277151882648468} {"step": 10750, "total_steps": 22439, "tokens": 95813632000, "source": "fineweb_hq", "phase": 1, "loss": 1.9409427642822266, "ce_loss": 1.9409427642822266, "logit_z_loss": 73.48834228515625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.18583159148693085, "tokens_per_second": 7407040.591628114, "eta_seconds": 14065.380100893974, "data_wait_seconds": 0.5377686619758606} {"step": 10760, "total_steps": 22439, "tokens": 95902760960, "source": "fineweb_hq", "phase": 1, "loss": 1.954895257949829, "ce_loss": 1.954895257949829, "logit_z_loss": 76.05136108398438, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20513056218624115, "tokens_per_second": 8530686.699070595, "eta_seconds": 12202.266482877732, "data_wait_seconds": 1.4185905456542969e-05} {"step": 10770, "total_steps": 22439, "tokens": 95991889920, "source": "fineweb_hq", "phase": 1, "loss": 1.9394203126430511, "ce_loss": 1.9394203126430511, "logit_z_loss": 77.57577323913574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25453534722328186, "tokens_per_second": 8052049.88861998, "eta_seconds": 12916.534902620317, "data_wait_seconds": 0.3352903127670288} {"step": 10780, "total_steps": 22439, "tokens": 96081018880, "source": "fineweb_hq", "phase": 1, "loss": 1.956962674856186, "ce_loss": 1.956962674856186, "logit_z_loss": 76.53137969970703, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22859540581703186, "tokens_per_second": 9421908.606609143, "eta_seconds": 11029.12995686531, "data_wait_seconds": 0.27585911750793457} {"step": 10790, "total_steps": 22439, "tokens": 96170147840, "source": "fineweb_hq", "phase": 1, "loss": 1.9708074033260345, "ce_loss": 1.9708074033260345, "logit_z_loss": 77.48688507080078, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22672221064567566, "tokens_per_second": 8853714.873509124, "eta_seconds": 11726.865726685524, "data_wait_seconds": 0.3110312223434448} {"step": 10800, "total_steps": 22439, "tokens": 96259276800, "source": "fineweb_hq", "phase": 1, "loss": 1.9581051468849182, "ce_loss": 1.9581051468849182, "logit_z_loss": 72.53314399719238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2415817379951477, "tokens_per_second": 9765343.072882183, "eta_seconds": 10622.995604944228, "data_wait_seconds": 0.00043189525604248047} {"step": 10810, "total_steps": 22439, "tokens": 96348405760, "source": "fineweb_hq", "phase": 1, "loss": 1.930848240852356, "ce_loss": 1.930848240852356, "logit_z_loss": 78.64097595214844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23991790413856506, "tokens_per_second": 7446779.801168321, "eta_seconds": 13918.508449482919, "data_wait_seconds": 1.4722347259521484e-05} {"step": 10820, "total_steps": 22439, "tokens": 96437534720, "source": "fineweb_hq", "phase": 1, "loss": 1.868318885564804, "ce_loss": 1.868318885564804, "logit_z_loss": 81.83304595947266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2457689344882965, "tokens_per_second": 7426140.322389969, "eta_seconds": 13945.190116024018, "data_wait_seconds": 0.8866625428199768} {"step": 10830, "total_steps": 22439, "tokens": 96526663680, "source": "fineweb_hq", "phase": 1, "loss": 1.7418203353881836, "ce_loss": 1.7418203353881836, "logit_z_loss": 88.29984283447266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2389916628599167, "tokens_per_second": 8195029.454571458, "eta_seconds": 12625.92285208702, "data_wait_seconds": 0.38394176959991455} {"step": 10840, "total_steps": 22439, "tokens": 96615792640, "source": "fineweb_hq", "phase": 1, "loss": 1.7416929304599762, "ce_loss": 1.7416929304599762, "logit_z_loss": 85.06139945983887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2760450839996338, "tokens_per_second": 8873630.80821014, "eta_seconds": 11650.324758648872, "data_wait_seconds": 1.9788742065429688e-05} {"step": 10850, "total_steps": 22439, "tokens": 96704921600, "source": "fineweb_hq", "phase": 1, "loss": 1.7394448518753052, "ce_loss": 1.7394448518753052, "logit_z_loss": 91.29654884338379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22135823965072632, "tokens_per_second": 10069018.317965155, "eta_seconds": 10258.353742361069, "data_wait_seconds": 0.0009558796882629395} {"step": 10860, "total_steps": 22439, "tokens": 96794050560, "source": "fineweb_hq", "phase": 1, "loss": 1.7222632765769958, "ce_loss": 1.7222632765769958, "logit_z_loss": 87.76584815979004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2618759274482727, "tokens_per_second": 6453471.150543183, "eta_seconds": 15991.769448804856, "data_wait_seconds": 0.7476730942726135} {"step": 10870, "total_steps": 22439, "tokens": 96883179520, "source": "fineweb_hq", "phase": 1, "loss": 1.7368917763233185, "ce_loss": 1.7368917763233185, "logit_z_loss": 91.06254005432129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26574376225471497, "tokens_per_second": 4404826.5237323055, "eta_seconds": 23409.161125516894, "data_wait_seconds": 1.6927719116210938e-05} {"step": 10880, "total_steps": 22439, "tokens": 96972308480, "source": "fineweb_hq", "phase": 1, "loss": 1.8736624717712402, "ce_loss": 1.8736624717712402, "logit_z_loss": 78.87374496459961, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22960975766181946, "tokens_per_second": 5015757.997674446, "eta_seconds": 20540.09880695343, "data_wait_seconds": 0.13581842184066772} {"step": 10890, "total_steps": 22439, "tokens": 97061437440, "source": "fineweb_hq", "phase": 1, "loss": 1.984308123588562, "ce_loss": 1.984308123588562, "logit_z_loss": 76.27145004272461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2730380594730377, "tokens_per_second": 5551423.684529574, "eta_seconds": 18542.096902251244, "data_wait_seconds": 0.6376739144325256} {"step": 10900, "total_steps": 22439, "tokens": 97150566400, "source": "fineweb_hq", "phase": 1, "loss": 1.9923482537269592, "ce_loss": 1.9923482537269592, "logit_z_loss": 78.81719589233398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2814468443393707, "tokens_per_second": 7208874.291000644, "eta_seconds": 14266.569618558884, "data_wait_seconds": 1.341104507446289e-05} {"step": 10910, "total_steps": 22439, "tokens": 97239695360, "source": "fineweb_hq", "phase": 1, "loss": 1.98691126704216, "ce_loss": 1.98691126704216, "logit_z_loss": 73.549560546875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27350857853889465, "tokens_per_second": 6734637.089243636, "eta_seconds": 15257.953267908097, "data_wait_seconds": 1.6033649444580078e-05} {"step": 10920, "total_steps": 22439, "tokens": 97328824320, "source": "fineweb_hq", "phase": 1, "loss": 1.9825204610824585, "ce_loss": 1.9825204610824585, "logit_z_loss": 77.01945686340332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22168676555156708, "tokens_per_second": 7346740.502180554, "eta_seconds": 13974.584918785094, "data_wait_seconds": 0.03525263071060181} {"step": 10930, "total_steps": 22439, "tokens": 97417953280, "source": "fineweb_hq", "phase": 1, "loss": 2.005900412797928, "ce_loss": 2.005900412797928, "logit_z_loss": 73.38150215148926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2256026417016983, "tokens_per_second": 5372608.721007704, "eta_seconds": 19092.870035910608, "data_wait_seconds": 1.8656253814697266e-05} {"step": 10940, "total_steps": 22439, "tokens": 97507082240, "source": "fineweb_hq", "phase": 1, "loss": 1.987178385257721, "ce_loss": 1.987178385257721, "logit_z_loss": 78.26622772216797, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22168950736522675, "tokens_per_second": 3960272.617904898, "eta_seconds": 25879.377758145332, "data_wait_seconds": 0.3000657558441162} {"step": 10950, "total_steps": 22439, "tokens": 97596211200, "source": "fineweb_hq", "phase": 1, "loss": 1.9887645840644836, "ce_loss": 1.9887645840644836, "logit_z_loss": 79.85288619995117, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2456049919128418, "tokens_per_second": 6705618.023420033, "eta_seconds": 15270.816468572617, "data_wait_seconds": 1.627206802368164e-05} {"step": 10960, "total_steps": 22439, "tokens": 97685340160, "source": "fineweb_hq", "phase": 1, "loss": 1.9945951402187347, "ce_loss": 1.9945951402187347, "logit_z_loss": 76.77300262451172, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26148271560668945, "tokens_per_second": 5888982.3405466555, "eta_seconds": 17373.312954187393, "data_wait_seconds": 0.3657509684562683} {"step": 10970, "total_steps": 22439, "tokens": 97774469120, "source": "fineweb_hq", "phase": 1, "loss": 1.989620327949524, "ce_loss": 1.989620327949524, "logit_z_loss": 79.32081413269043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2501806318759918, "tokens_per_second": 8329728.942168366, "eta_seconds": 12271.948455190659, "data_wait_seconds": 1.8894672393798828e-05} {"step": 10980, "total_steps": 22439, "tokens": 97863598080, "source": "fineweb_hq", "phase": 1, "loss": 1.993188500404358, "ce_loss": 1.993188500404358, "logit_z_loss": 77.16767501831055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22476966679096222, "tokens_per_second": 6771102.92432806, "eta_seconds": 15083.639461016655, "data_wait_seconds": 1.5079975128173828e-05} {"step": 10990, "total_steps": 22439, "tokens": 97952727040, "source": "fineweb_hq", "phase": 1, "loss": 1.991950660943985, "ce_loss": 1.991950660943985, "logit_z_loss": 77.89020919799805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22354651987552643, "tokens_per_second": 7573239.232271321, "eta_seconds": 13474.253641581536, "data_wait_seconds": 0.20030277967453003} {"step": 11000, "total_steps": 22439, "tokens": 98041856000, "source": "fineweb_hq", "phase": 1, "loss": 1.9821999073028564, "ce_loss": 1.9821999073028564, "logit_z_loss": 74.65436363220215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.19900749623775482, "tokens_per_second": 6831553.726173397, "eta_seconds": 14924.074585461616, "data_wait_seconds": 0.41954517364501953} {"step": 11010, "total_steps": 22439, "tokens": 98130984960, "source": "fineweb_hq", "phase": 1, "loss": 1.9923936128616333, "ce_loss": 1.9923936128616333, "logit_z_loss": 78.9135627746582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.20723432302474976, "tokens_per_second": 8426727.355319323, "eta_seconds": 12088.380706858636, "data_wait_seconds": 1.4603137969970703e-05} {"step": 11020, "total_steps": 22439, "tokens": 98220113920, "source": "fineweb_hq", "phase": 1, "loss": 1.983690470457077, "ce_loss": 1.983690470457077, "logit_z_loss": 78.41397857666016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22272196412086487, "tokens_per_second": 7174255.777790069, "eta_seconds": 14186.32992415428, "data_wait_seconds": 0.2287137508392334} {"step": 11030, "total_steps": 22439, "tokens": 98309242880, "source": "fineweb_hq", "phase": 1, "loss": 1.9802798330783844, "ce_loss": 1.9802798330783844, "logit_z_loss": 78.68134117126465, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27858129143714905, "tokens_per_second": 5577941.442870453, "eta_seconds": 18230.24345190525, "data_wait_seconds": 0.34491926431655884} {"step": 11040, "total_steps": 22439, "tokens": 98398371840, "source": "fineweb_hq", "phase": 1, "loss": 1.9765567779541016, "ce_loss": 1.9765567779541016, "logit_z_loss": 78.19682312011719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.246942400932312, "tokens_per_second": 7332425.907619903, "eta_seconds": 13856.001108503342, "data_wait_seconds": 0.40012097358703613} {"step": 11050, "total_steps": 22439, "tokens": 98487500800, "source": "fineweb_hq", "phase": 1, "loss": 1.9871589541435242, "ce_loss": 1.9871589541435242, "logit_z_loss": 77.39751815795898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28808432817459106, "tokens_per_second": 7014733.607764519, "eta_seconds": 14470.823586463928, "data_wait_seconds": 2.3543834686279297e-05} {"step": 11060, "total_steps": 22439, "tokens": 98576629760, "source": "fineweb_hq", "phase": 1, "loss": 1.9731517732143402, "ce_loss": 1.9731517732143402, "logit_z_loss": 77.69059562683105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2441232055425644, "tokens_per_second": 8640905.810218794, "eta_seconds": 11737.177306580545, "data_wait_seconds": 1.537799835205078e-05} {"step": 11070, "total_steps": 22439, "tokens": 98665758720, "source": "fineweb_hq", "phase": 1, "loss": 1.9701114296913147, "ce_loss": 1.9701114296913147, "logit_z_loss": 77.87674331665039, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2749950885772705, "tokens_per_second": 9057831.971103245, "eta_seconds": 11187.082620573045, "data_wait_seconds": 1.4662742614746094e-05} {"step": 11080, "total_steps": 22439, "tokens": 98754887680, "source": "fineweb_hq", "phase": 1, "loss": 1.9894963502883911, "ce_loss": 1.9894963502883911, "logit_z_loss": 80.65342140197754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32713261246681213, "tokens_per_second": 6979087.572664736, "eta_seconds": 14506.421449780464, "data_wait_seconds": 0.3127790689468384} {"step": 11090, "total_steps": 22439, "tokens": 98844016640, "source": "fineweb_hq", "phase": 1, "loss": 1.960910975933075, "ce_loss": 1.960910975933075, "logit_z_loss": 80.39234161376953, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2815703749656677, "tokens_per_second": 6823874.107705526, "eta_seconds": 14823.318119215965, "data_wait_seconds": 2.9921531677246094e-05} {"step": 11100, "total_steps": 22439, "tokens": 98933145600, "source": "fineweb_hq", "phase": 1, "loss": 1.9749257862567902, "ce_loss": 1.9749257862567902, "logit_z_loss": 78.04056358337402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24512532353401184, "tokens_per_second": 7927951.884795648, "eta_seconds": 12747.722137141227, "data_wait_seconds": 1.6689300537109375e-05} {"step": 11110, "total_steps": 22439, "tokens": 99022274560, "source": "fineweb_hq", "phase": 1, "loss": 1.9305013120174408, "ce_loss": 1.9305013120174408, "logit_z_loss": 82.67217254638672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2505144476890564, "tokens_per_second": 6641434.352796376, "eta_seconds": 15203.67339646816, "data_wait_seconds": 1.7702579498291016e-05} {"step": 11120, "total_steps": 22439, "tokens": 99111403520, "source": "fineweb_hq", "phase": 1, "loss": 1.8676758706569672, "ce_loss": 1.8676758706569672, "logit_z_loss": 83.40247535705566, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2305218130350113, "tokens_per_second": 8350601.032164742, "eta_seconds": 12081.174688553809, "data_wait_seconds": 1.722574234008789e-05} {"step": 11130, "total_steps": 22439, "tokens": 99200532480, "source": "fineweb_hq", "phase": 1, "loss": 1.7493431270122528, "ce_loss": 1.7493431270122528, "logit_z_loss": 91.71643447875977, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22999721765518188, "tokens_per_second": 9363537.025714425, "eta_seconds": 10764.729245710374, "data_wait_seconds": 1.4007091522216797e-05} {"step": 11140, "total_steps": 22439, "tokens": 99289661440, "source": "fineweb_hq", "phase": 1, "loss": 1.7526644170284271, "ce_loss": 1.7526644170284271, "logit_z_loss": 91.26131629943848, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.281170517206192, "tokens_per_second": 9147430.547965499, "eta_seconds": 11009.300521707533, "data_wait_seconds": 1.5497207641601562e-05} {"step": 11150, "total_steps": 22439, "tokens": 99378790400, "source": "fineweb_hq", "phase": 1, "loss": 1.7354093790054321, "ce_loss": 1.7354093790054321, "logit_z_loss": 93.99369239807129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22007456421852112, "tokens_per_second": 9214969.772291368, "eta_seconds": 10918.937927126884, "data_wait_seconds": 1.71661376953125e-05} {"step": 11160, "total_steps": 22439, "tokens": 99467919360, "source": "fineweb_hq", "phase": 1, "loss": 1.7268171906471252, "ce_loss": 1.7268171906471252, "logit_z_loss": 92.46858787536621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2695290446281433, "tokens_per_second": 10460479.040378232, "eta_seconds": 9610.320291829108, "data_wait_seconds": 1.2576580047607422e-05} {"step": 11170, "total_steps": 22439, "tokens": 99557048320, "source": "fineweb_hq", "phase": 1, "loss": 1.8456245362758636, "ce_loss": 1.8456245362758636, "logit_z_loss": 87.16385078430176, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2982593774795532, "tokens_per_second": 6916911.540233905, "eta_seconds": 14520.848566555977, "data_wait_seconds": 1.7523765563964844e-05} {"step": 11180, "total_steps": 22439, "tokens": 99646177280, "source": "fineweb_hq", "phase": 1, "loss": 1.9230758249759674, "ce_loss": 1.9230758249759674, "logit_z_loss": 83.16119766235352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22589099407196045, "tokens_per_second": 8214661.413507593, "eta_seconds": 12215.999054932594, "data_wait_seconds": 1.7404556274414062e-05} {"step": 11190, "total_steps": 22439, "tokens": 99735306240, "source": "fineweb_hq", "phase": 1, "loss": 1.98896524310112, "ce_loss": 1.98896524310112, "logit_z_loss": 83.57501220703125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24024082720279694, "tokens_per_second": 8350566.710150747, "eta_seconds": 12006.510526061058, "data_wait_seconds": 0.036624908447265625} {"step": 11200, "total_steps": 22439, "tokens": 99824435200, "source": "fineweb_hq", "phase": 1, "loss": 1.9776065647602081, "ce_loss": 1.9776065647602081, "logit_z_loss": 79.81919479370117, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28973305225372314, "tokens_per_second": 7189884.636562801, "eta_seconds": 13932.356805086136, "data_wait_seconds": 1.4722347259521484e-05} {"step": 11210, "total_steps": 22439, "tokens": 99913564160, "source": "fineweb_hq", "phase": 1, "loss": 1.9933946430683136, "ce_loss": 1.9933946430683136, "logit_z_loss": 77.37292289733887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.257527619600296, "tokens_per_second": 6774787.138574057, "eta_seconds": 14772.849262547492, "data_wait_seconds": 1.5735626220703125e-05} {"step": 11220, "total_steps": 22439, "tokens": 100002693120, "source": "fineweb_hq", "phase": 1, "loss": 1.9798974394798279, "ce_loss": 1.9798974394798279, "logit_z_loss": 80.42536926269531, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2520350515842438, "tokens_per_second": 6971010.213762519, "eta_seconds": 14344.230915999413, "data_wait_seconds": 1.7642974853515625e-05} {"step": 11230, "total_steps": 22439, "tokens": 100091822080, "source": "fineweb_hq", "phase": 2, "loss": 2.007095694541931, "ce_loss": 2.007095694541931, "logit_z_loss": 83.33421897888184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3613852262496948, "tokens_per_second": 8964250.120911427, "eta_seconds": 11144.786224889756, "data_wait_seconds": 1.6987323760986328e-05} {"step": 11240, "total_steps": 22439, "tokens": 100180951040, "source": "fineweb_hq", "phase": 2, "loss": 2.026885449886322, "ce_loss": 2.026885449886322, "logit_z_loss": 87.96148681640625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29578807950019836, "tokens_per_second": 8338200.450196056, "eta_seconds": 11970.871041083336, "data_wait_seconds": 2.1457672119140625e-05} {"step": 11250, "total_steps": 22439, "tokens": 100270080000, "source": "fineweb_hq", "phase": 2, "loss": 2.025086462497711, "ce_loss": 2.025086462497711, "logit_z_loss": 81.2085189819336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33175545930862427, "tokens_per_second": 10192330.551913375, "eta_seconds": 9784.45438323021, "data_wait_seconds": 2.0742416381835938e-05} {"step": 11260, "total_steps": 22439, "tokens": 100359208960, "source": "fineweb_hq", "phase": 2, "loss": 1.9966791868209839, "ce_loss": 1.9966791868209839, "logit_z_loss": 79.79134750366211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2711360454559326, "tokens_per_second": 9312095.052357344, "eta_seconds": 10699.7688300848, "data_wait_seconds": 1.7940998077392578e-05} {"step": 11270, "total_steps": 22439, "tokens": 100448337920, "source": "fineweb_hq", "phase": 2, "loss": 2.0092742145061493, "ce_loss": 2.0092742145061493, "logit_z_loss": 80.39978218078613, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3143165409564972, "tokens_per_second": 2173122.347184953, "eta_seconds": 45808.80388669968, "data_wait_seconds": 1.6665745973587036} {"step": 11280, "total_steps": 22439, "tokens": 100537466880, "source": "fineweb_hq", "phase": 2, "loss": 2.0060060620307922, "ce_loss": 2.0060060620307922, "logit_z_loss": 87.8721866607666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3321945369243622, "tokens_per_second": 4528387.24088379, "eta_seconds": 21963.44993777275, "data_wait_seconds": 0.9149692058563232} {"step": 11290, "total_steps": 22439, "tokens": 100626595840, "source": "fineweb_hq", "phase": 2, "loss": 2.010584533214569, "ce_loss": 2.010584533214569, "logit_z_loss": 86.94362449645996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3067040741443634, "tokens_per_second": 4926452.535902808, "eta_seconds": 20170.675913310053, "data_wait_seconds": 0.871416449546814} {"step": 11300, "total_steps": 22439, "tokens": 100715724800, "source": "fineweb_hq", "phase": 2, "loss": 1.994544357061386, "ce_loss": 1.994544357061386, "logit_z_loss": 84.77689933776855, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31482377648353577, "tokens_per_second": 1740542.1935470738, "eta_seconds": 57040.12744538784, "data_wait_seconds": 2.5391578674316406e-05} {"step": 11310, "total_steps": 22439, "tokens": 100804853760, "source": "fineweb_hq", "phase": 2, "loss": 1.9886932373046875, "ce_loss": 1.9886932373046875, "logit_z_loss": 87.05093955993652, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2671757936477661, "tokens_per_second": 1935379.6167850138, "eta_seconds": 51251.76411063671, "data_wait_seconds": 0.523735523223877} {"step": 11320, "total_steps": 22439, "tokens": 100893982720, "source": "fineweb_hq", "phase": 2, "loss": 1.9875732362270355, "ce_loss": 1.9875732362270355, "logit_z_loss": 88.97580528259277, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2727348804473877, "tokens_per_second": 9470650.463474793, "eta_seconds": 10464.169383740425, "data_wait_seconds": 1.722574234008789e-05} {"step": 11330, "total_steps": 22439, "tokens": 100983111680, "source": "fineweb_hq", "phase": 2, "loss": 1.9852905571460724, "ce_loss": 1.9852905571460724, "logit_z_loss": 88.4370346069336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2626589238643646, "tokens_per_second": 1536895.6673063363, "eta_seconds": 64424.25713746547, "data_wait_seconds": 2.4318695068359375e-05} {"step": 11340, "total_steps": 22439, "tokens": 101072240640, "source": "fineweb_hq", "phase": 2, "loss": 1.9717274904251099, "ce_loss": 1.9717274904251099, "logit_z_loss": 84.56743049621582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2644370198249817, "tokens_per_second": 7998161.947209951, "eta_seconds": 12368.370802807809, "data_wait_seconds": 1.6570091247558594e-05} {"step": 11350, "total_steps": 22439, "tokens": 101161369600, "source": "fineweb_hq", "phase": 2, "loss": 1.9899662137031555, "ce_loss": 1.9899662137031555, "logit_z_loss": 87.86278915405273, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28376442193984985, "tokens_per_second": 9689639.422992649, "eta_seconds": 10200.080666518212, "data_wait_seconds": 1.9073486328125e-05} {"step": 11360, "total_steps": 22439, "tokens": 101250498560, "source": "fineweb_hq", "phase": 2, "loss": 1.989107459783554, "ce_loss": 1.989107459783554, "logit_z_loss": 87.01530838012695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3425188660621643, "tokens_per_second": 9552463.120731119, "eta_seconds": 10337.226486611367, "data_wait_seconds": 1.895427703857422e-05} {"step": 11370, "total_steps": 22439, "tokens": 101339627520, "source": "fineweb_hq", "phase": 2, "loss": 1.9939748048782349, "ce_loss": 1.9939748048782349, "logit_z_loss": 86.41028022766113, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3396170139312744, "tokens_per_second": 8189374.807526425, "eta_seconds": 12046.932536697388, "data_wait_seconds": 1.704692840576172e-05} {"step": 11380, "total_steps": 22439, "tokens": 101428756480, "source": "fineweb_hq", "phase": 2, "loss": 1.9323919415473938, "ce_loss": 1.9323919415473938, "logit_z_loss": 86.52509880065918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30955618619918823, "tokens_per_second": 8716101.360866936, "eta_seconds": 11308.693277311324, "data_wait_seconds": 1.728534698486328e-05} {"step": 11390, "total_steps": 22439, "tokens": 101517885440, "source": "fineweb_hq", "phase": 2, "loss": 1.8984166085720062, "ce_loss": 1.8984166085720062, "logit_z_loss": 90.16188621520996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2752220630645752, "tokens_per_second": 7748897.368498303, "eta_seconds": 12708.722702193261, "data_wait_seconds": 0.553290069103241} {"step": 11400, "total_steps": 22439, "tokens": 101607014400, "source": "fineweb_hq", "phase": 2, "loss": 1.8221127688884735, "ce_loss": 1.8221127688884735, "logit_z_loss": 96.56663703918457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.318105012178421, "tokens_per_second": 10345390.46078468, "eta_seconds": 9510.463555431366, "data_wait_seconds": 1.537799835205078e-05} {"step": 11410, "total_steps": 22439, "tokens": 101696143360, "source": "fineweb_hq", "phase": 2, "loss": 1.7784276604652405, "ce_loss": 1.7784276604652405, "logit_z_loss": 97.22239112854004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2883704602718353, "tokens_per_second": 8708886.941421304, "eta_seconds": 11287.358607959748, "data_wait_seconds": 2.002716064453125e-05} {"step": 11420, "total_steps": 22439, "tokens": 101785272320, "source": "fineweb_hq", "phase": 2, "loss": 1.7791753113269806, "ce_loss": 1.7791753113269806, "logit_z_loss": 98.80198287963867, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27955517172813416, "tokens_per_second": 9254842.957471224, "eta_seconds": 10611.87115495205, "data_wait_seconds": 2.485513687133789e-05} {"step": 11430, "total_steps": 22439, "tokens": 101874401280, "source": "fineweb_hq", "phase": 2, "loss": 1.7764109075069427, "ce_loss": 1.7764109075069427, "logit_z_loss": 99.25929641723633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.263653963804245, "tokens_per_second": 10789978.787807785, "eta_seconds": 9093.815103220939, "data_wait_seconds": 2.1576881408691406e-05} {"step": 11440, "total_steps": 22439, "tokens": 101963530240, "source": "fineweb_hq", "phase": 2, "loss": 1.7680573165416718, "ce_loss": 1.7680573165416718, "logit_z_loss": 98.7275276184082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2739444971084595, "tokens_per_second": 9294306.561983528, "eta_seconds": 10547.633914399148, "data_wait_seconds": 1.8417835235595703e-05} {"step": 11450, "total_steps": 22439, "tokens": 102052659200, "source": "fineweb_hq", "phase": 2, "loss": 1.7821145951747894, "ce_loss": 1.7821145951747894, "logit_z_loss": 99.39507484436035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25685742497444153, "tokens_per_second": 9876353.19756175, "eta_seconds": 9917.001972770691, "data_wait_seconds": 1.6510486602783203e-05} {"step": 11460, "total_steps": 22439, "tokens": 102141788160, "source": "fineweb_hq", "phase": 2, "loss": 1.8917135000228882, "ce_loss": 1.8917135000228882, "logit_z_loss": 91.9603271484375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3050455152988434, "tokens_per_second": 9882653.57780343, "eta_seconds": 9901.660967230797, "data_wait_seconds": 1.7881393432617188e-05} {"step": 11470, "total_steps": 22439, "tokens": 102230917120, "source": "fineweb_hq", "phase": 2, "loss": 1.9743521213531494, "ce_loss": 1.9743521213531494, "logit_z_loss": 87.45655632019043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2671789526939392, "tokens_per_second": 8277230.266152772, "eta_seconds": 11811.385340309143, "data_wait_seconds": 2.002716064453125e-05} {"step": 11480, "total_steps": 22439, "tokens": 102320046080, "source": "fineweb_hq", "phase": 2, "loss": 2.0309504866600037, "ce_loss": 2.0309504866600037, "logit_z_loss": 84.2296085357666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32120776176452637, "tokens_per_second": 9217224.768754227, "eta_seconds": 10597.162347078323, "data_wait_seconds": 1.7702579498291016e-05} {"step": 11490, "total_steps": 22439, "tokens": 102409175040, "source": "fineweb_hq", "phase": 2, "loss": 2.026476204395294, "ce_loss": 2.026476204395294, "logit_z_loss": 83.69842529296875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2603900730609894, "tokens_per_second": 9864433.706770532, "eta_seconds": 9892.843441891671, "data_wait_seconds": 1.6629695892333984e-05} {"step": 11500, "total_steps": 22439, "tokens": 102498304000, "source": "fineweb_hq", "phase": 2, "loss": 2.0336082577705383, "ce_loss": 2.0336082577705383, "logit_z_loss": 86.71281623840332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34427034854888916, "tokens_per_second": 10598097.217394292, "eta_seconds": 9199.591902589798, "data_wait_seconds": 1.811981201171875e-05} {"step": 11510, "total_steps": 22439, "tokens": 102587432960, "source": "fineweb_hq", "phase": 2, "loss": 2.025566428899765, "ce_loss": 2.025566428899765, "logit_z_loss": 86.3588638305664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30159643292427063, "tokens_per_second": 7763583.8632603595, "eta_seconds": 12546.916746139526, "data_wait_seconds": 0.49191415309906006} {"step": 11520, "total_steps": 22439, "tokens": 102676561920, "source": "fineweb_hq", "phase": 2, "loss": 1.9861728250980377, "ce_loss": 1.9861728250980377, "logit_z_loss": 89.54952239990234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2790950536727905, "tokens_per_second": 8726894.905766383, "eta_seconds": 11151.722631573677, "data_wait_seconds": 0.44182634353637695} {"step": 11530, "total_steps": 22439, "tokens": 102765690880, "source": "fineweb_hq", "phase": 2, "loss": 1.9268009662628174, "ce_loss": 1.9268009662628174, "logit_z_loss": 88.12101364135742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24265190958976746, "tokens_per_second": 8553727.481207762, "eta_seconds": 11367.065723991394, "data_wait_seconds": 1.5974044799804688e-05} {"step": 11540, "total_steps": 22439, "tokens": 102854819840, "source": "fineweb_hq", "phase": 2, "loss": 1.9120774865150452, "ce_loss": 1.9120774865150452, "logit_z_loss": 88.53826713562012, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26542484760284424, "tokens_per_second": 8249435.902680945, "eta_seconds": 11775.551037669182, "data_wait_seconds": 1.7702579498291016e-05} {"step": 11550, "total_steps": 22439, "tokens": 102943948800, "source": "fineweb_hq", "phase": 2, "loss": 1.9266210794448853, "ce_loss": 1.9266210794448853, "logit_z_loss": 91.15355491638184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2676176428794861, "tokens_per_second": 10187168.914893635, "eta_seconds": 9526.93779349327, "data_wait_seconds": 1.5616416931152344e-05} {"step": 11560, "total_steps": 22439, "tokens": 103033077760, "source": "fineweb_hq", "phase": 2, "loss": 1.9145832657814026, "ce_loss": 1.9145832657814026, "logit_z_loss": 93.9596996307373, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.284423828125, "tokens_per_second": 9255523.488210294, "eta_seconds": 10476.273514676093, "data_wait_seconds": 1.7464160919189453e-05} {"step": 11570, "total_steps": 22439, "tokens": 103122206720, "source": "fineweb_hq", "phase": 2, "loss": 1.9341462552547455, "ce_loss": 1.9341462552547455, "logit_z_loss": 89.11798477172852, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31010565161705017, "tokens_per_second": 8564355.271528864, "eta_seconds": 11311.332091283797, "data_wait_seconds": 1.7762184143066406e-05} {"step": 11580, "total_steps": 22439, "tokens": 103211335680, "source": "fineweb_hq", "phase": 2, "loss": 1.9166158437728882, "ce_loss": 1.9166158437728882, "logit_z_loss": 91.69429969787598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27060702443122864, "tokens_per_second": 9007799.844814861, "eta_seconds": 10744.592390084266, "data_wait_seconds": 2.2530555725097656e-05} {"step": 11590, "total_steps": 22439, "tokens": 103300464640, "source": "fineweb_hq", "phase": 2, "loss": 1.9128190279006958, "ce_loss": 1.9128190279006958, "logit_z_loss": 82.70561790466309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26424771547317505, "tokens_per_second": 8142682.063109856, "eta_seconds": 11875.203766345978, "data_wait_seconds": 1.823902130126953e-05} {"step": 11600, "total_steps": 22439, "tokens": 103389593600, "source": "fineweb_hq", "phase": 2, "loss": 1.9396682977676392, "ce_loss": 1.9396682977676392, "logit_z_loss": 86.02753257751465, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28225335478782654, "tokens_per_second": 9927497.172628887, "eta_seconds": 9731.242231965065, "data_wait_seconds": 2.0742416381835938e-05} {"step": 11610, "total_steps": 22439, "tokens": 103478722560, "source": "fineweb_hq", "phase": 2, "loss": 1.9674861133098602, "ce_loss": 1.9674861133098602, "logit_z_loss": 90.1103401184082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28445592522621155, "tokens_per_second": 8556376.569601506, "eta_seconds": 11280.21306669712, "data_wait_seconds": 1.7344951629638672e-05} {"step": 11620, "total_steps": 22439, "tokens": 103567851520, "source": "fineweb_hq", "phase": 2, "loss": 1.9739316999912262, "ce_loss": 1.9739316999912262, "logit_z_loss": 88.5443115234375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3305550515651703, "tokens_per_second": 9314703.959070852, "eta_seconds": 10352.30129134655, "data_wait_seconds": 1.5556812286376953e-05} {"step": 11630, "total_steps": 22439, "tokens": 103656980480, "source": "fineweb_hq", "phase": 2, "loss": 1.986697793006897, "ce_loss": 1.986697793006897, "logit_z_loss": 89.58600997924805, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2925976514816284, "tokens_per_second": 10712426.373267215, "eta_seconds": 8993.246675133705, "data_wait_seconds": 1.6987323760986328e-05} {"step": 11640, "total_steps": 22439, "tokens": 103746109440, "source": "fineweb_hq", "phase": 2, "loss": 1.9793646037578583, "ce_loss": 1.9793646037578583, "logit_z_loss": 86.15671730041504, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29536008834838867, "tokens_per_second": 9529372.641454615, "eta_seconds": 10100.388296842575, "data_wait_seconds": 1.7881393432617188e-05} {"step": 11650, "total_steps": 22439, "tokens": 103835238400, "source": "fineweb_hq", "phase": 2, "loss": 1.9768106639385223, "ce_loss": 1.9768106639385223, "logit_z_loss": 87.89888954162598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2938261926174164, "tokens_per_second": 9184133.014749022, "eta_seconds": 10470.366096568107, "data_wait_seconds": 1.996755599975586e-05} {"step": 11660, "total_steps": 22439, "tokens": 103924367360, "source": "fineweb_hq", "phase": 2, "loss": 1.9882102310657501, "ce_loss": 1.9882102310657501, "logit_z_loss": 89.88988494873047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29119953513145447, "tokens_per_second": 10291171.96590964, "eta_seconds": 9335.390206503867, "data_wait_seconds": 1.7344951629638672e-05} {"step": 11670, "total_steps": 22439, "tokens": 104013496320, "source": "fineweb_hq", "phase": 2, "loss": 2.007952630519867, "ce_loss": 2.007952630519867, "logit_z_loss": 84.55302810668945, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3770376145839691, "tokens_per_second": 9883894.967054296, "eta_seconds": 9711.047855520248, "data_wait_seconds": 1.8298625946044922e-05} {"step": 11680, "total_steps": 22439, "tokens": 104102625280, "source": "fineweb_hq", "phase": 2, "loss": 1.9816209971904755, "ce_loss": 1.9816209971904755, "logit_z_loss": 87.55094718933105, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31126999855041504, "tokens_per_second": 8636424.83201369, "eta_seconds": 11103.419520139694, "data_wait_seconds": 1.7404556274414062e-05} {"step": 11690, "total_steps": 22439, "tokens": 104191754240, "source": "fineweb_hq", "phase": 2, "loss": 1.9777179062366486, "ce_loss": 1.9777179062366486, "logit_z_loss": 87.23644256591797, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28470587730407715, "tokens_per_second": 9568050.299413104, "eta_seconds": 10012.982384705543, "data_wait_seconds": 1.4901161193847656e-05} {"step": 11700, "total_steps": 22439, "tokens": 104280883200, "source": "fineweb_hq", "phase": 2, "loss": 1.9828080236911774, "ce_loss": 1.9828080236911774, "logit_z_loss": 89.09629249572754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2951897978782654, "tokens_per_second": 9196307.676960938, "eta_seconds": 10408.0456533432, "data_wait_seconds": 1.823902130126953e-05} {"step": 11710, "total_steps": 22439, "tokens": 104370012160, "source": "fineweb_hq", "phase": 2, "loss": 1.9852083027362823, "ce_loss": 1.9852083027362823, "logit_z_loss": 87.80098152160645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.290797621011734, "tokens_per_second": 9753369.738706224, "eta_seconds": 9804.45361406803, "data_wait_seconds": 0.23694729804992676} {"step": 11720, "total_steps": 22439, "tokens": 104459141120, "source": "fineweb_hq", "phase": 2, "loss": 1.9727589786052704, "ce_loss": 1.9727589786052704, "logit_z_loss": 87.72119331359863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28546953201293945, "tokens_per_second": 8320856.041805989, "eta_seconds": 11481.671085762977, "data_wait_seconds": 2.8967857360839844e-05} {"step": 11730, "total_steps": 22439, "tokens": 104548270080, "source": "fineweb_hq", "phase": 2, "loss": 1.995935469865799, "ce_loss": 1.995935469865799, "logit_z_loss": 90.23315620422363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2877208888530731, "tokens_per_second": 8653479.405764125, "eta_seconds": 11030.03760550022, "data_wait_seconds": 1.5795230865478516e-05} {"step": 11740, "total_steps": 22439, "tokens": 104637399040, "source": "fineweb_hq", "phase": 2, "loss": 1.9899486303329468, "ce_loss": 1.9899486303329468, "logit_z_loss": 88.55814170837402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28477662801742554, "tokens_per_second": 8967316.009063412, "eta_seconds": 10634.070909023285, "data_wait_seconds": 1.6808509826660156e-05} {"step": 11750, "total_steps": 22439, "tokens": 104726528000, "source": "fineweb_hq", "phase": 2, "loss": 1.9890830516815186, "ce_loss": 1.9890830516815186, "logit_z_loss": 85.1898078918457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2750703990459442, "tokens_per_second": 7897550.763590629, "eta_seconds": 12063.22671368122, "data_wait_seconds": 2.0682811737060547e-05} {"step": 11760, "total_steps": 22439, "tokens": 104815656960, "source": "fineweb_hq", "phase": 2, "loss": 1.9990010857582092, "ce_loss": 1.9990010857582092, "logit_z_loss": 82.90326881408691, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34857529401779175, "tokens_per_second": 7741775.580508261, "eta_seconds": 12294.442714619638, "data_wait_seconds": 1.6808509826660156e-05} {"step": 11770, "total_steps": 22439, "tokens": 104904785920, "source": "fineweb_hq", "phase": 2, "loss": 2.0041482150554657, "ce_loss": 2.0041482150554657, "logit_z_loss": 89.8294849395752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2648491859436035, "tokens_per_second": 5602773.8652006015, "eta_seconds": 16972.25155107975, "data_wait_seconds": 0.5923044085502625} {"step": 11780, "total_steps": 22439, "tokens": 104993914880, "source": "fineweb_hq", "phase": 2, "loss": 1.9998307526111603, "ce_loss": 1.9998307526111603, "logit_z_loss": 89.1892318725586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27419382333755493, "tokens_per_second": 8259022.946109003, "eta_seconds": 11502.881041002274, "data_wait_seconds": 1.6748905181884766e-05} {"step": 11790, "total_steps": 22439, "tokens": 105083043840, "source": "fineweb_hq", "phase": 2, "loss": 1.998089224100113, "ce_loss": 1.998089224100113, "logit_z_loss": 83.37014198303223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29211875796318054, "tokens_per_second": 8695419.501204118, "eta_seconds": 10915.336458563805, "data_wait_seconds": 1.627206802368164e-05} {"step": 11800, "total_steps": 22439, "tokens": 105172172800, "source": "fineweb_hq", "phase": 2, "loss": 2.0023903846740723, "ce_loss": 2.0023903846740723, "logit_z_loss": 87.46390342712402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2917543351650238, "tokens_per_second": 9368293.862947542, "eta_seconds": 10121.83242020607, "data_wait_seconds": 1.9431114196777344e-05} {"step": 11810, "total_steps": 22439, "tokens": 105261301760, "source": "fineweb_hq", "phase": 2, "loss": 2.0051476657390594, "ce_loss": 2.0051476657390594, "logit_z_loss": 86.5491943359375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2803167700767517, "tokens_per_second": 8871613.835257798, "eta_seconds": 10678.459786820411, "data_wait_seconds": 1.8835067749023438e-05} {"step": 11820, "total_steps": 22439, "tokens": 105350430720, "source": "fineweb_hq", "phase": 2, "loss": 1.9941387474536896, "ce_loss": 1.9941387474536896, "logit_z_loss": 90.71007919311523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29255375266075134, "tokens_per_second": 6340508.834468286, "eta_seconds": 14927.199865961074, "data_wait_seconds": 0.3884841799736023} {"step": 11830, "total_steps": 22439, "tokens": 105439559680, "source": "fineweb_hq", "phase": 2, "loss": 1.9938556849956512, "ce_loss": 1.9938556849956512, "logit_z_loss": 87.66766929626465, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30835357308387756, "tokens_per_second": 8660082.453821143, "eta_seconds": 10918.70824189186, "data_wait_seconds": 2.104043960571289e-05} {"step": 11840, "total_steps": 22439, "tokens": 105528688640, "source": "fineweb_hq", "phase": 2, "loss": 1.9820576310157776, "ce_loss": 1.9820576310157776, "logit_z_loss": 84.81253814697266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31508156657218933, "tokens_per_second": 6236546.94713787, "eta_seconds": 15147.450264501573, "data_wait_seconds": 1.6450881958007812e-05} {"step": 11850, "total_steps": 22439, "tokens": 105617817600, "source": "fineweb_hq", "phase": 2, "loss": 1.9859417080879211, "ce_loss": 1.9859417080879211, "logit_z_loss": 90.24914741516113, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2996169924736023, "tokens_per_second": 8576473.35198956, "eta_seconds": 11004.366465163232, "data_wait_seconds": 1.3470649719238281e-05} {"step": 11860, "total_steps": 22439, "tokens": 105706946560, "source": "fineweb_hq", "phase": 2, "loss": 1.9619532525539398, "ce_loss": 1.9619532525539398, "logit_z_loss": 89.4011402130127, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3243568241596222, "tokens_per_second": 7053895.9167433595, "eta_seconds": 13367.014185762406, "data_wait_seconds": 1.6450881958007812e-05} {"step": 11870, "total_steps": 22439, "tokens": 105796075520, "source": "fineweb_hq", "phase": 2, "loss": 1.9591815173625946, "ce_loss": 1.9591815173625946, "logit_z_loss": 92.8994312286377, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28200486302375793, "tokens_per_second": 8949611.71343284, "eta_seconds": 10525.640758538246, "data_wait_seconds": 1.8477439880371094e-05} {"step": 11880, "total_steps": 22439, "tokens": 105885204480, "source": "fineweb_hq", "phase": 2, "loss": 1.959662765264511, "ce_loss": 1.959662765264511, "logit_z_loss": 91.55897903442383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.22586704790592194, "tokens_per_second": 8867489.246746268, "eta_seconds": 10613.068281817435, "data_wait_seconds": 1.6808509826660156e-05} {"step": 11890, "total_steps": 22439, "tokens": 105974333440, "source": "fineweb_hq", "phase": 2, "loss": 1.9745009243488312, "ce_loss": 1.9745009243488312, "logit_z_loss": 91.6092758178711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32067233324050903, "tokens_per_second": 9030723.762322599, "eta_seconds": 10411.362630343438, "data_wait_seconds": 2.485513687133789e-05} {"step": 11900, "total_steps": 22439, "tokens": 106063462400, "source": "fineweb_hq", "phase": 2, "loss": 1.9656766057014465, "ce_loss": 1.9656766057014465, "logit_z_loss": 89.89871215820312, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2867639362812042, "tokens_per_second": 8984817.528845362, "eta_seconds": 10454.637575268745, "data_wait_seconds": 1.627206802368164e-05} {"step": 11910, "total_steps": 22439, "tokens": 106152591360, "source": "fineweb_hq", "phase": 2, "loss": 1.9675632417201996, "ce_loss": 1.9675632417201996, "logit_z_loss": 91.25911903381348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3136102557182312, "tokens_per_second": 8827041.251922505, "eta_seconds": 10631.40856666565, "data_wait_seconds": 1.6927719116210938e-05} {"step": 11920, "total_steps": 22439, "tokens": 106241720320, "source": "fineweb_hq", "phase": 2, "loss": 1.9603319764137268, "ce_loss": 1.9603319764137268, "logit_z_loss": 90.28743553161621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3394509255886078, "tokens_per_second": 8083475.6792587405, "eta_seconds": 11598.32190310955, "data_wait_seconds": 1.8298625946044922e-05} {"step": 11930, "total_steps": 22439, "tokens": 106330849280, "source": "fineweb_hq", "phase": 2, "loss": 1.977161318063736, "ce_loss": 1.977161318063736, "logit_z_loss": 92.43840980529785, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28996577858924866, "tokens_per_second": 10343094.305341693, "eta_seconds": 9055.860973405837, "data_wait_seconds": 1.817941665649414e-05} {"step": 11940, "total_steps": 22439, "tokens": 106419978240, "source": "fineweb_hq", "phase": 2, "loss": 1.955942839384079, "ce_loss": 1.955942839384079, "logit_z_loss": 90.18493270874023, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2846057713031769, "tokens_per_second": 9881947.188613774, "eta_seconds": 9469.438898825645, "data_wait_seconds": 1.8477439880371094e-05} {"step": 11950, "total_steps": 22439, "tokens": 106509107200, "source": "fineweb_hq", "phase": 2, "loss": 1.959159940481186, "ce_loss": 1.959159940481186, "logit_z_loss": 85.21982765197754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29854077100753784, "tokens_per_second": 9855598.63010236, "eta_seconds": 9485.711589193343, "data_wait_seconds": 1.7404556274414062e-05} {"step": 11960, "total_steps": 22439, "tokens": 106598236160, "source": "fineweb_hq", "phase": 2, "loss": 1.9594144225120544, "ce_loss": 1.9594144225120544, "logit_z_loss": 89.94922637939453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3071954846382141, "tokens_per_second": 9045958.355441207, "eta_seconds": 10324.858186841011, "data_wait_seconds": 1.6033649444580078e-05} {"step": 11970, "total_steps": 22439, "tokens": 106687365120, "source": "fineweb_hq", "phase": 2, "loss": 1.9641022980213165, "ce_loss": 1.9641022980213165, "logit_z_loss": 91.7935562133789, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2978150248527527, "tokens_per_second": 9067697.223757247, "eta_seconds": 10290.2761220932, "data_wait_seconds": 1.722574234008789e-05} {"step": 11980, "total_steps": 22439, "tokens": 106776494080, "source": "fineweb_hq", "phase": 2, "loss": 1.9893257021903992, "ce_loss": 1.9893257021903992, "logit_z_loss": 87.97000694274902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3614341914653778, "tokens_per_second": 9507926.658675782, "eta_seconds": 9804.44871006012, "data_wait_seconds": 1.6987323760986328e-05} {"step": 11990, "total_steps": 22439, "tokens": 106865623040, "source": "fineweb_hq", "phase": 2, "loss": 1.988320231437683, "ce_loss": 1.988320231437683, "logit_z_loss": 86.25286102294922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3145853579044342, "tokens_per_second": 8249668.557934214, "eta_seconds": 11289.041450572015, "data_wait_seconds": 2.2351741790771484e-05} {"step": 12000, "total_steps": 22439, "tokens": 106954752000, "source": "fineweb_hq", "phase": 2, "loss": 2.00538969039917, "ce_loss": 2.00538969039917, "logit_z_loss": 89.94039154052734, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27977845072746277, "tokens_per_second": 9440631.35884409, "eta_seconds": 9855.455404138565, "data_wait_seconds": 2.0384788513183594e-05} {"step": 12010, "total_steps": 22439, "tokens": 107043880960, "source": "fineweb_hq", "phase": 2, "loss": 2.0124439895153046, "ce_loss": 2.0124439895153046, "logit_z_loss": 81.9410457611084, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28093644976615906, "tokens_per_second": 10701358.019941935, "eta_seconds": 8686.055752062797, "data_wait_seconds": 2.0682811737060547e-05} {"step": 12020, "total_steps": 22439, "tokens": 107133009920, "source": "fineweb_hq", "phase": 2, "loss": 2.007291078567505, "ce_loss": 2.007291078567505, "logit_z_loss": 89.88783073425293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31299591064453125, "tokens_per_second": 9318706.937302738, "eta_seconds": 9965.273513674736, "data_wait_seconds": 2.2470951080322266e-05} {"step": 12030, "total_steps": 22439, "tokens": 107222138880, "source": "fineweb_hq", "phase": 2, "loss": 2.0018216967582703, "ce_loss": 2.0018216967582703, "logit_z_loss": 88.60936164855957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2941744327545166, "tokens_per_second": 7540670.100227744, "eta_seconds": 12303.194972181322, "data_wait_seconds": 1.7583370208740234e-05} {"step": 12040, "total_steps": 22439, "tokens": 107311267840, "source": "fineweb_hq", "phase": 2, "loss": 1.985336571931839, "ce_loss": 1.985336571931839, "logit_z_loss": 91.9074535369873, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2749665379524231, "tokens_per_second": 9940895.956721408, "eta_seconds": 9323.626955509186, "data_wait_seconds": 1.8596649169921875e-05} {"step": 12050, "total_steps": 22439, "tokens": 107400396800, "source": "fineweb_hq", "phase": 2, "loss": 2.0196496546268463, "ce_loss": 2.0196496546268463, "logit_z_loss": 87.50079154968262, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.23757191002368927, "tokens_per_second": 8132789.768962511, "eta_seconds": 11385.524423289298, "data_wait_seconds": 1.7583370208740234e-05} {"step": 12060, "total_steps": 22439, "tokens": 107489525760, "source": "fineweb_hq", "phase": 2, "loss": 2.018471121788025, "ce_loss": 2.018471121788025, "logit_z_loss": 89.14454078674316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.341047465801239, "tokens_per_second": 9848761.564692767, "eta_seconds": 9392.749228048324, "data_wait_seconds": 1.811981201171875e-05} {"step": 12070, "total_steps": 22439, "tokens": 107578654720, "source": "fineweb_hq", "phase": 2, "loss": 2.027525007724762, "ce_loss": 2.027525007724762, "logit_z_loss": 85.77375411987305, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3455471098423004, "tokens_per_second": 9172456.389491607, "eta_seconds": 10075.580051803589, "data_wait_seconds": 1.9490718841552734e-05} {"step": 12080, "total_steps": 22439, "tokens": 107667783680, "source": "fineweb_hq", "phase": 2, "loss": 2.0388684272766113, "ce_loss": 2.0388684272766113, "logit_z_loss": 90.61846542358398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3468382656574249, "tokens_per_second": 9318033.34181651, "eta_seconds": 9908.602628588676, "data_wait_seconds": 1.5854835510253906e-05} {"step": 12090, "total_steps": 22439, "tokens": 107756912640, "source": "fineweb_hq", "phase": 2, "loss": 2.0270901024341583, "ce_loss": 2.0270901024341583, "logit_z_loss": 88.43439292907715, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33330124616622925, "tokens_per_second": 9445447.299692336, "eta_seconds": 9765.504774665831, "data_wait_seconds": 2.2292137145996094e-05} {"step": 12100, "total_steps": 22439, "tokens": 107846041600, "source": "fineweb_hq", "phase": 2, "loss": 2.0362863540649414, "ce_loss": 2.0362863540649414, "logit_z_loss": 89.52450752258301, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31053847074508667, "tokens_per_second": 9215011.794879355, "eta_seconds": 10000.034052610397, "data_wait_seconds": 1.817941665649414e-05} {"step": 12110, "total_steps": 22439, "tokens": 107935170560, "source": "fineweb_hq", "phase": 2, "loss": 1.9747468531131744, "ce_loss": 1.9747468531131744, "logit_z_loss": 88.05874824523926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2503243386745453, "tokens_per_second": 9049641.622533256, "eta_seconds": 10172.922489523888, "data_wait_seconds": 1.8894672393798828e-05} {"step": 12120, "total_steps": 22439, "tokens": 108024299520, "source": "fineweb_hq", "phase": 2, "loss": 1.9274264872074127, "ce_loss": 1.9274264872074127, "logit_z_loss": 95.2321662902832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24544811248779297, "tokens_per_second": 8595339.26706993, "eta_seconds": 10700.23776447773, "data_wait_seconds": 1.710653305053711e-05} {"step": 12130, "total_steps": 22439, "tokens": 108113428480, "source": "fineweb_hq", "phase": 2, "loss": 1.8481464982032776, "ce_loss": 1.8481464982032776, "logit_z_loss": 97.64448547363281, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27216896414756775, "tokens_per_second": 8732937.650008455, "eta_seconds": 10521.436032915115, "data_wait_seconds": 0.3298823833465576} {"step": 12140, "total_steps": 22439, "tokens": 108202557440, "source": "fineweb_hq", "phase": 2, "loss": 1.764317810535431, "ce_loss": 1.764317810535431, "logit_z_loss": 99.94951820373535, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29389920830726624, "tokens_per_second": 8363279.531632664, "eta_seconds": 10975.827790617943, "data_wait_seconds": 2.276897430419922e-05} {"step": 12150, "total_steps": 22439, "tokens": 108291686400, "source": "fineweb_hq", "phase": 2, "loss": 1.755744457244873, "ce_loss": 1.755744457244873, "logit_z_loss": 102.49237823486328, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2833862006664276, "tokens_per_second": 9311131.35173791, "eta_seconds": 9848.941388511657, "data_wait_seconds": 2.1457672119140625e-05} {"step": 12160, "total_steps": 22439, "tokens": 108380815360, "source": "fineweb_hq", "phase": 2, "loss": 1.7764952480793, "ce_loss": 1.7764952480793, "logit_z_loss": 101.82875442504883, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3133607804775238, "tokens_per_second": 10109825.61036355, "eta_seconds": 9062.041375875473, "data_wait_seconds": 2.3186206817626953e-05} {"step": 12170, "total_steps": 22439, "tokens": 108469944320, "source": "fineweb_hq", "phase": 2, "loss": 1.7717209160327911, "ce_loss": 1.7717209160327911, "logit_z_loss": 102.50449180603027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27582406997680664, "tokens_per_second": 10702343.902293326, "eta_seconds": 8552.007846093178, "data_wait_seconds": 1.8656253814697266e-05} {"step": 12180, "total_steps": 22439, "tokens": 108559073280, "source": "fineweb_hq", "phase": 2, "loss": 1.7572548687458038, "ce_loss": 1.7572548687458038, "logit_z_loss": 103.63172149658203, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27923068404197693, "tokens_per_second": 8751103.905890308, "eta_seconds": 10448.670367455483, "data_wait_seconds": 1.7940998077392578e-05} {"step": 12190, "total_steps": 22439, "tokens": 108648202240, "source": "fineweb_hq", "phase": 2, "loss": 1.817094326019287, "ce_loss": 1.817094326019287, "logit_z_loss": 99.8811092376709, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2854546308517456, "tokens_per_second": 8979968.117134653, "eta_seconds": 10172.449379825593, "data_wait_seconds": 1.8715858459472656e-05} {"step": 12200, "total_steps": 22439, "tokens": 108737331200, "source": "fineweb_hq", "phase": 2, "loss": 1.8821417093276978, "ce_loss": 1.8821417093276978, "logit_z_loss": 98.43452835083008, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32357078790664673, "tokens_per_second": 8485580.860589009, "eta_seconds": 10754.613460564613, "data_wait_seconds": 1.4603137969970703e-05} {"step": 12210, "total_steps": 22439, "tokens": 108826460160, "source": "fineweb_hq", "phase": 2, "loss": 1.9616829454898834, "ce_loss": 1.9616829454898834, "logit_z_loss": 94.71175575256348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2817050516605377, "tokens_per_second": 9368169.436595634, "eta_seconds": 9731.891998863219, "data_wait_seconds": 1.6570091247558594e-05} {"step": 12220, "total_steps": 22439, "tokens": 108915589120, "source": "fineweb_hq", "phase": 2, "loss": 1.9810991883277893, "ce_loss": 1.9810991883277893, "logit_z_loss": 92.94331932067871, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31408876180648804, "tokens_per_second": 10374368.386388311, "eta_seconds": 8779.41488404274, "data_wait_seconds": 1.9073486328125e-05} {"step": 12230, "total_steps": 22439, "tokens": 109004718080, "source": "fineweb_hq", "phase": 2, "loss": 1.9812399744987488, "ce_loss": 1.9812399744987488, "logit_z_loss": 91.66604614257812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36991286277770996, "tokens_per_second": 9502768.044820115, "eta_seconds": 9575.289519309998, "data_wait_seconds": 1.7344951629638672e-05} {"step": 12240, "total_steps": 22439, "tokens": 109093847040, "source": "fineweb_hq", "phase": 2, "loss": 1.9653317332267761, "ce_loss": 1.9653317332267761, "logit_z_loss": 90.68951797485352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33855095505714417, "tokens_per_second": 10436352.725054385, "eta_seconds": 8710.191069507599, "data_wait_seconds": 1.4424324035644531e-05} {"step": 12250, "total_steps": 22439, "tokens": 109182976000, "source": "fineweb_hq", "phase": 2, "loss": 1.9566285908222198, "ce_loss": 1.9566285908222198, "logit_z_loss": 93.69841384887695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27324697375297546, "tokens_per_second": 9894650.165465979, "eta_seconds": 9178.0402364254, "data_wait_seconds": 1.7464160919189453e-05} {"step": 12260, "total_steps": 22439, "tokens": 109272104960, "source": "fineweb_hq", "phase": 2, "loss": 1.9635685682296753, "ce_loss": 1.9635685682296753, "logit_z_loss": 92.9713020324707, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26761841773986816, "tokens_per_second": 9501963.966117417, "eta_seconds": 9547.959633135795, "data_wait_seconds": 1.728534698486328e-05} {"step": 12270, "total_steps": 22439, "tokens": 109361233920, "source": "fineweb_hq", "phase": 2, "loss": 1.9690411686897278, "ce_loss": 1.9690411686897278, "logit_z_loss": 93.17056274414062, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2945537567138672, "tokens_per_second": 10144278.356831523, "eta_seconds": 8934.616759896278, "data_wait_seconds": 1.5139579772949219e-05} {"step": 12280, "total_steps": 22439, "tokens": 109450362880, "source": "fineweb_hq", "phase": 2, "loss": 1.9737441539764404, "ce_loss": 1.9737441539764404, "logit_z_loss": 92.14329719543457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34992530941963196, "tokens_per_second": 9708351.648080377, "eta_seconds": 9326.620393061638, "data_wait_seconds": 1.5556812286376953e-05} {"step": 12290, "total_steps": 22439, "tokens": 109539491840, "source": "fineweb_hq", "phase": 2, "loss": 1.9714197516441345, "ce_loss": 1.9714197516441345, "logit_z_loss": 92.23954200744629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31489118933677673, "tokens_per_second": 8305821.670960877, "eta_seconds": 10890.792637681961, "data_wait_seconds": 1.990795135498047e-05} {"step": 12300, "total_steps": 22439, "tokens": 109628620800, "source": "fineweb_hq", "phase": 2, "loss": 1.9639228582382202, "ce_loss": 1.9639228582382202, "logit_z_loss": 94.16019630432129, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2718166410923004, "tokens_per_second": 11202458.295050208, "eta_seconds": 8066.787678551674, "data_wait_seconds": 1.722574234008789e-05} {"step": 12310, "total_steps": 22439, "tokens": 109717749760, "source": "fineweb_hq", "phase": 2, "loss": 1.9770644307136536, "ce_loss": 1.9770644307136536, "logit_z_loss": 90.47713661193848, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34738844633102417, "tokens_per_second": 7591275.907193161, "eta_seconds": 11892.4308229208, "data_wait_seconds": 1.7404556274414062e-05} {"step": 12320, "total_steps": 22439, "tokens": 109806878720, "source": "fineweb_hq", "phase": 2, "loss": 1.9648755490779877, "ce_loss": 1.9648755490779877, "logit_z_loss": 92.35566711425781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3216192126274109, "tokens_per_second": 9122600.555306539, "eta_seconds": 9886.390846252441, "data_wait_seconds": 1.7762184143066406e-05} {"step": 12330, "total_steps": 22439, "tokens": 109896007680, "source": "fineweb_hq", "phase": 2, "loss": 1.9593712985515594, "ce_loss": 1.9593712985515594, "logit_z_loss": 91.66794013977051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29699647426605225, "tokens_per_second": 8068799.356744152, "eta_seconds": 11166.526973891258, "data_wait_seconds": 1.7702579498291016e-05} {"step": 12340, "total_steps": 22439, "tokens": 109985136640, "source": "fineweb_hq", "phase": 2, "loss": 1.9687045812606812, "ce_loss": 1.9687045812606812, "logit_z_loss": 93.90682601928711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2546696364879608, "tokens_per_second": 10007667.657281525, "eta_seconds": 8994.237197566032, "data_wait_seconds": 1.7821788787841797e-05} {"step": 12350, "total_steps": 22439, "tokens": 110074265600, "source": "fineweb_hq", "phase": 2, "loss": 1.9801693558692932, "ce_loss": 1.9801693558692932, "logit_z_loss": 91.50530624389648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3194796144962311, "tokens_per_second": 10459498.437165787, "eta_seconds": 8597.181622445583, "data_wait_seconds": 2.9981136322021484e-05} {"step": 12360, "total_steps": 22439, "tokens": 110163394560, "source": "fineweb_hq", "phase": 2, "loss": 1.9707400798797607, "ce_loss": 1.9707400798797607, "logit_z_loss": 92.77789115905762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30054181814193726, "tokens_per_second": 10436650.20443954, "eta_seconds": 8607.462837624551, "data_wait_seconds": 2.014636993408203e-05} {"step": 12370, "total_steps": 22439, "tokens": 110252523520, "source": "fineweb_hq", "phase": 2, "loss": 1.969960480928421, "ce_loss": 1.969960480928421, "logit_z_loss": 88.28626823425293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2889792025089264, "tokens_per_second": 9806071.039393453, "eta_seconds": 9151.876369595528, "data_wait_seconds": 2.390146255493164e-05} {"step": 12380, "total_steps": 22439, "tokens": 110341652480, "source": "fineweb_hq", "phase": 2, "loss": 1.9890615046024323, "ce_loss": 1.9890615046024323, "logit_z_loss": 94.55788230895996, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26151251792907715, "tokens_per_second": 8344240.985413123, "eta_seconds": 10744.514812159538, "data_wait_seconds": 1.5556812286376953e-05} {"step": 12390, "total_steps": 22439, "tokens": 110430781440, "source": "fineweb_hq", "phase": 2, "loss": 1.9797775745391846, "ce_loss": 1.9797775745391846, "logit_z_loss": 93.47603797912598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27731502056121826, "tokens_per_second": 10301269.995512825, "eta_seconds": 8694.626191043853, "data_wait_seconds": 1.621246337890625e-05} {"step": 12400, "total_steps": 22439, "tokens": 110519910400, "source": "fineweb_hq", "phase": 2, "loss": 2.00194451212883, "ce_loss": 2.00194451212883, "logit_z_loss": 89.21120643615723, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.284213125705719, "tokens_per_second": 8064807.059224436, "eta_seconds": 11094.693560171128, "data_wait_seconds": 0.1374211311340332} {"step": 12410, "total_steps": 22439, "tokens": 110609039360, "source": "fineweb_hq", "phase": 2, "loss": 2.005029320716858, "ce_loss": 2.005029320716858, "logit_z_loss": 90.70866966247559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26346662640571594, "tokens_per_second": 7919857.8403166095, "eta_seconds": 11286.494756126403, "data_wait_seconds": 1.9311904907226562e-05} {"step": 12420, "total_steps": 22439, "tokens": 110698168320, "source": "fineweb_hq", "phase": 2, "loss": 1.987764835357666, "ce_loss": 1.987764835357666, "logit_z_loss": 91.34702110290527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2825997769832611, "tokens_per_second": 9466146.758992296, "eta_seconds": 9433.437627530097, "data_wait_seconds": 1.9431114196777344e-05} {"step": 12430, "total_steps": 22439, "tokens": 110787297280, "source": "fineweb_hq", "phase": 2, "loss": 2.02532160282135, "ce_loss": 2.02532160282135, "logit_z_loss": 93.01531028747559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31104105710983276, "tokens_per_second": 8289843.5875166645, "eta_seconds": 10761.261671853066, "data_wait_seconds": 2.181529998779297e-05} {"step": 12440, "total_steps": 22439, "tokens": 110876426240, "source": "fineweb_hq", "phase": 2, "loss": 2.00425586104393, "ce_loss": 2.00425586104393, "logit_z_loss": 88.7358455657959, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3240472972393036, "tokens_per_second": 9646828.68522132, "eta_seconds": 9238.274049639702, "data_wait_seconds": 2.0802021026611328e-05} {"step": 12450, "total_steps": 22439, "tokens": 110965555200, "source": "fineweb_hq", "phase": 2, "loss": 1.9946790039539337, "ce_loss": 1.9946790039539337, "logit_z_loss": 91.03823471069336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30235007405281067, "tokens_per_second": 11093691.558094772, "eta_seconds": 8025.364476537705, "data_wait_seconds": 1.9252300262451172e-05} {"step": 12460, "total_steps": 22439, "tokens": 111054684160, "source": "fineweb_hq", "phase": 2, "loss": 2.010979861021042, "ce_loss": 2.010979861021042, "logit_z_loss": 89.0999755859375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2963249683380127, "tokens_per_second": 8862019.35660566, "eta_seconds": 10036.289202833177, "data_wait_seconds": 1.806020736694336e-05} {"step": 12470, "total_steps": 22439, "tokens": 111143813120, "source": "fineweb_hq", "phase": 2, "loss": 2.011718988418579, "ce_loss": 2.011718988418579, "logit_z_loss": 91.60624313354492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3258401155471802, "tokens_per_second": 8254315.672045506, "eta_seconds": 10764.388442873955, "data_wait_seconds": 1.811981201171875e-05} {"step": 12480, "total_steps": 22439, "tokens": 111232942080, "source": "fineweb_hq", "phase": 2, "loss": 2.024017810821533, "ce_loss": 2.024017810821533, "logit_z_loss": 93.45393371582031, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2839369773864746, "tokens_per_second": 8998881.655759383, "eta_seconds": 9863.840270328521, "data_wait_seconds": 1.9252300262451172e-05} {"step": 12490, "total_steps": 22439, "tokens": 111322071040, "source": "fineweb_hq", "phase": 2, "loss": 2.0109723806381226, "ce_loss": 2.0109723806381226, "logit_z_loss": 90.5047664642334, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2638719379901886, "tokens_per_second": 8968353.35509117, "eta_seconds": 9887.478647756578, "data_wait_seconds": 1.7464160919189453e-05} {"step": 12500, "total_steps": 22439, "tokens": 111411200000, "source": "fineweb_hq", "phase": 2, "loss": 2.0188300013542175, "ce_loss": 2.0188300013542175, "logit_z_loss": 88.76823997497559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2604437470436096, "tokens_per_second": 7571642.150428951, "eta_seconds": 11699.611733365058, "data_wait_seconds": 1.7762184143066406e-05} {"step": 12510, "total_steps": 22439, "tokens": 111500328960, "source": "fineweb_hq", "phase": 2, "loss": 2.003489136695862, "ce_loss": 2.003489136695862, "logit_z_loss": 90.73970413208008, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3112252950668335, "tokens_per_second": 6633725.705766438, "eta_seconds": 13340.338191413879, "data_wait_seconds": 1.9431114196777344e-05} {"step": 12520, "total_steps": 22439, "tokens": 111589457920, "source": "fineweb_hq", "phase": 2, "loss": 2.032390981912613, "ce_loss": 2.032390981912613, "logit_z_loss": 95.15365219116211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.284941703081131, "tokens_per_second": 9421616.059201691, "eta_seconds": 9383.42370018959, "data_wait_seconds": 1.7464160919189453e-05} {"step": 12530, "total_steps": 22439, "tokens": 111678586880, "source": "fineweb_hq", "phase": 2, "loss": 2.010019838809967, "ce_loss": 2.010019838809967, "logit_z_loss": 92.01875877380371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34945032000541687, "tokens_per_second": 10078937.861734817, "eta_seconds": 8762.618410348892, "data_wait_seconds": 1.8775463104248047e-05} {"step": 12540, "total_steps": 22439, "tokens": 111767715840, "source": "fineweb_hq", "phase": 2, "loss": 1.9888455867767334, "ce_loss": 1.9888455867767334, "logit_z_loss": 89.18417930603027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28353580832481384, "tokens_per_second": 9472991.29929382, "eta_seconds": 9313.71672542095, "data_wait_seconds": 2.2232532501220703e-05} {"step": 12550, "total_steps": 22439, "tokens": 111856844800, "source": "fineweb_hq", "phase": 2, "loss": 2.0051765143871307, "ce_loss": 2.0051765143871307, "logit_z_loss": 91.18258666992188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3059903681278229, "tokens_per_second": 8859049.177732857, "eta_seconds": 9949.10704023838, "data_wait_seconds": 2.2232532501220703e-05} {"step": 12560, "total_steps": 22439, "tokens": 111945973760, "source": "fineweb_hq", "phase": 2, "loss": 1.9960270524024963, "ce_loss": 1.9960270524024963, "logit_z_loss": 90.40532302856445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3348039984703064, "tokens_per_second": 9238457.541215334, "eta_seconds": 9530.8658605814, "data_wait_seconds": 1.9848346710205078e-05} {"step": 12570, "total_steps": 22439, "tokens": 112035102720, "source": "fineweb_hq", "phase": 2, "loss": 1.9922836124897003, "ce_loss": 1.9922836124897003, "logit_z_loss": 89.317138671875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3079288899898529, "tokens_per_second": 9094943.005428053, "eta_seconds": 9671.459246253968, "data_wait_seconds": 1.8894672393798828e-05} {"step": 12580, "total_steps": 22439, "tokens": 112124231680, "source": "fineweb_hq", "phase": 2, "loss": 1.9923078417778015, "ce_loss": 1.9923078417778015, "logit_z_loss": 89.48576354980469, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2969641387462616, "tokens_per_second": 9526364.391264286, "eta_seconds": 9224.110904741288, "data_wait_seconds": 1.8298625946044922e-05} {"step": 12590, "total_steps": 22439, "tokens": 112213360640, "source": "fineweb_hq", "phase": 2, "loss": 1.9910354614257812, "ce_loss": 1.9910354614257812, "logit_z_loss": 91.24554443359375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2736748158931732, "tokens_per_second": 9918828.30284203, "eta_seconds": 8850.149435377121, "data_wait_seconds": 1.901388168334961e-05} {"step": 12600, "total_steps": 22439, "tokens": 112302489600, "source": "fineweb_hq", "phase": 2, "loss": 1.9888554215431213, "ce_loss": 1.9888554215431213, "logit_z_loss": 90.6775016784668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31791597604751587, "tokens_per_second": 9144786.977221323, "eta_seconds": 9589.50536108017, "data_wait_seconds": 1.919269561767578e-05} {"step": 12610, "total_steps": 22439, "tokens": 112391618560, "source": "fineweb_hq", "phase": 2, "loss": 1.9958678781986237, "ce_loss": 1.9958678781986237, "logit_z_loss": 89.51614952087402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3591960668563843, "tokens_per_second": 9281512.639011795, "eta_seconds": 9438.639819955824, "data_wait_seconds": 1.9848346710205078e-05} {"step": 12620, "total_steps": 22439, "tokens": 112480747520, "source": "fineweb_hq", "phase": 2, "loss": 1.9896863996982574, "ce_loss": 1.9896863996982574, "logit_z_loss": 88.49018287658691, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3089413344860077, "tokens_per_second": 8796804.217956068, "eta_seconds": 9948.58174123764, "data_wait_seconds": 2.104043960571289e-05} {"step": 12630, "total_steps": 22439, "tokens": 112569876480, "source": "fineweb_hq", "phase": 2, "loss": 2.0056316554546356, "ce_loss": 2.0056316554546356, "logit_z_loss": 94.3552017211914, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2551313638687134, "tokens_per_second": 8136482.726101851, "eta_seconds": 10745.011057853699, "data_wait_seconds": 1.6808509826660156e-05} {"step": 12640, "total_steps": 22439, "tokens": 112659005440, "source": "fineweb_hq", "phase": 2, "loss": 2.007692575454712, "ce_loss": 2.007692575454712, "logit_z_loss": 90.76851463317871, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30876243114471436, "tokens_per_second": 8698746.0712915, "eta_seconds": 10040.236510896682, "data_wait_seconds": 1.919269561767578e-05} {"step": 12650, "total_steps": 22439, "tokens": 112748134400, "source": "fineweb_hq", "phase": 2, "loss": 2.0096820890903473, "ce_loss": 2.0096820890903473, "logit_z_loss": 91.06680488586426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29157668352127075, "tokens_per_second": 9162157.653516416, "eta_seconds": 9522.684747791289, "data_wait_seconds": 2.2292137145996094e-05} {"step": 12660, "total_steps": 22439, "tokens": 112837263360, "source": "fineweb_hq", "phase": 2, "loss": 2.0078529715538025, "ce_loss": 2.0078529715538025, "logit_z_loss": 93.17115592956543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26565662026405334, "tokens_per_second": 10749536.477511657, "eta_seconds": 8108.183098530769, "data_wait_seconds": 1.5795230865478516e-05} {"step": 12670, "total_steps": 22439, "tokens": 112926392320, "source": "fineweb_hq", "phase": 2, "loss": 2.003551810979843, "ce_loss": 2.003551810979843, "logit_z_loss": 91.39596176147461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35496118664741516, "tokens_per_second": 9593123.834154213, "eta_seconds": 9076.30116417408, "data_wait_seconds": 2.300739288330078e-05} {"step": 12680, "total_steps": 22439, "tokens": 113015521280, "source": "fineweb_hq", "phase": 2, "loss": 2.0056200325489044, "ce_loss": 2.0056200325489044, "logit_z_loss": 87.41016960144043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32426565885543823, "tokens_per_second": 8822998.184271052, "eta_seconds": 9858.4347687006, "data_wait_seconds": 1.722574234008789e-05} {"step": 12690, "total_steps": 22439, "tokens": 113104650240, "source": "fineweb_hq", "phase": 2, "loss": 2.0227630138397217, "ce_loss": 2.0227630138397217, "logit_z_loss": 92.0023307800293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33880940079689026, "tokens_per_second": 8771450.612052038, "eta_seconds": 9906.209012293815, "data_wait_seconds": 1.901388168334961e-05} {"step": 12700, "total_steps": 22439, "tokens": 113193779200, "source": "fineweb_hq", "phase": 2, "loss": 2.013378292322159, "ce_loss": 2.013378292322159, "logit_z_loss": 92.83686447143555, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27199384570121765, "tokens_per_second": 9047335.178450344, "eta_seconds": 9594.283005094527, "data_wait_seconds": 1.7762184143066406e-05} {"step": 12710, "total_steps": 22439, "tokens": 113282908160, "source": "fineweb_hq", "phase": 2, "loss": 2.0049667954444885, "ce_loss": 2.0049667954444885, "logit_z_loss": 90.09311103820801, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33876198530197144, "tokens_per_second": 6399700.59112661, "eta_seconds": 13549.628447341918, "data_wait_seconds": 0.4831056594848633} {"step": 12720, "total_steps": 22439, "tokens": 113372037120, "source": "fineweb_hq", "phase": 2, "loss": 1.990437239408493, "ce_loss": 1.990437239408493, "logit_z_loss": 92.17292785644531, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29127970337867737, "tokens_per_second": 8093753.996038275, "eta_seconds": 10702.627762889862, "data_wait_seconds": 1.811981201171875e-05} {"step": 12730, "total_steps": 22439, "tokens": 113461166080, "source": "fineweb_hq", "phase": 2, "loss": 1.9685807824134827, "ce_loss": 1.9685807824134827, "logit_z_loss": 93.11046028137207, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32244014739990234, "tokens_per_second": 8406316.456967235, "eta_seconds": 10294.081564378737, "data_wait_seconds": 1.913309097290039e-05} {"step": 12740, "total_steps": 22439, "tokens": 113550295040, "source": "fineweb_hq", "phase": 2, "loss": 1.9247665703296661, "ce_loss": 1.9247665703296661, "logit_z_loss": 95.46317672729492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3498583734035492, "tokens_per_second": 8114242.706773171, "eta_seconds": 10653.634778738022, "data_wait_seconds": 0.03504818677902222} {"step": 12750, "total_steps": 22439, "tokens": 113639424000, "source": "fineweb_hq", "phase": 2, "loss": 1.8419983088970184, "ce_loss": 1.8419983088970184, "logit_z_loss": 97.47027587890625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30593734979629517, "tokens_per_second": 8846673.513748063, "eta_seconds": 9761.52778892517, "data_wait_seconds": 1.52587890625e-05} {"step": 12760, "total_steps": 22439, "tokens": 113728552960, "source": "fineweb_hq", "phase": 2, "loss": 1.7911263406276703, "ce_loss": 1.7911263406276703, "logit_z_loss": 103.90796852111816, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3228342533111572, "tokens_per_second": 9549702.759770282, "eta_seconds": 9033.571259140968, "data_wait_seconds": 1.7523765563964844e-05} {"step": 12770, "total_steps": 22439, "tokens": 113817681920, "source": "fineweb_hq", "phase": 2, "loss": 1.7579778730869293, "ce_loss": 1.7579778730869293, "logit_z_loss": 103.07150840759277, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2642746865749359, "tokens_per_second": 8743979.726003814, "eta_seconds": 9855.785823440552, "data_wait_seconds": 2.6047229766845703e-05} {"step": 12780, "total_steps": 22439, "tokens": 113906810880, "source": "fineweb_hq", "phase": 2, "loss": 1.7761237025260925, "ce_loss": 1.7761237025260925, "logit_z_loss": 108.02809524536133, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2755260467529297, "tokens_per_second": 9318376.863346325, "eta_seconds": 9238.697224473954, "data_wait_seconds": 2.008676528930664e-05} {"step": 12790, "total_steps": 22439, "tokens": 113995939840, "source": "fineweb_hq", "phase": 2, "loss": 1.779138207435608, "ce_loss": 1.779138207435608, "logit_z_loss": 103.56320381164551, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2475239485502243, "tokens_per_second": 10157687.813855458, "eta_seconds": 8466.54623374939, "data_wait_seconds": 2.3186206817626953e-05} {"step": 12800, "total_steps": 22439, "tokens": 114085068800, "source": "fineweb_hq", "phase": 2, "loss": 1.7600104808807373, "ce_loss": 1.7600104808807373, "logit_z_loss": 100.08356285095215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3265810012817383, "tokens_per_second": 9668445.212201804, "eta_seconds": 8885.751809978485, "data_wait_seconds": 1.823902130126953e-05} {"step": 12810, "total_steps": 22439, "tokens": 114174197760, "source": "fineweb_hq", "phase": 2, "loss": 1.7557417154312134, "ce_loss": 1.7557417154312134, "logit_z_loss": 102.82611083984375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.325715035200119, "tokens_per_second": 9776383.91965536, "eta_seconds": 8778.529596352577, "data_wait_seconds": 1.7404556274414062e-05} {"step": 12820, "total_steps": 22439, "tokens": 114263326720, "source": "fineweb_hq", "phase": 2, "loss": 1.767145037651062, "ce_loss": 1.767145037651062, "logit_z_loss": 103.91471862792969, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27794304490089417, "tokens_per_second": 9324823.224688971, "eta_seconds": 9194.077416610719, "data_wait_seconds": 1.6510486602783203e-05} {"step": 12830, "total_steps": 22439, "tokens": 114352455680, "source": "fineweb_hq", "phase": 2, "loss": 1.7508113384246826, "ce_loss": 1.7508113384246826, "logit_z_loss": 104.69724655151367, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3000669777393341, "tokens_per_second": 10032128.164384436, "eta_seconds": 8536.97403588295, "data_wait_seconds": 1.9311904907226562e-05} {"step": 12840, "total_steps": 22439, "tokens": 114441584640, "source": "fineweb_hq", "phase": 2, "loss": 1.744690179824829, "ce_loss": 1.744690179824829, "logit_z_loss": 106.1417407989502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24553658068180084, "tokens_per_second": 9522667.14810203, "eta_seconds": 8984.340980672836, "data_wait_seconds": 1.9252300262451172e-05} {"step": 12850, "total_steps": 22439, "tokens": 114530713600, "source": "fineweb_hq", "phase": 2, "loss": 1.7703010439872742, "ce_loss": 1.7703010439872742, "logit_z_loss": 106.63121604919434, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.258473664522171, "tokens_per_second": 10393877.829195831, "eta_seconds": 8222.70197403431, "data_wait_seconds": 3.3020973205566406e-05} {"step": 12860, "total_steps": 22439, "tokens": 114619842560, "source": "fineweb_hq", "phase": 2, "loss": 1.7629116773605347, "ce_loss": 1.7629116773605347, "logit_z_loss": 107.81910705566406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26570335030555725, "tokens_per_second": 8410131.128848672, "eta_seconds": 10151.640857434273, "data_wait_seconds": 0.3386688828468323} {"step": 12870, "total_steps": 22439, "tokens": 114708971520, "source": "fineweb_hq", "phase": 2, "loss": 1.816901296377182, "ce_loss": 1.816901296377182, "logit_z_loss": 99.30322456359863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32175955176353455, "tokens_per_second": 10127714.195417926, "eta_seconds": 8421.199510407449, "data_wait_seconds": 1.823902130126953e-05} {"step": 12880, "total_steps": 22439, "tokens": 114798100480, "source": "fineweb_hq", "phase": 2, "loss": 1.8318754434585571, "ce_loss": 1.8318754434585571, "logit_z_loss": 97.69525718688965, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3440026640892029, "tokens_per_second": 8853464.513841756, "eta_seconds": 9623.167600750923, "data_wait_seconds": 1.9788742065429688e-05} {"step": 12890, "total_steps": 22439, "tokens": 114887229440, "source": "fineweb_hq", "phase": 2, "loss": 1.9405734241008759, "ce_loss": 1.9405734241008759, "logit_z_loss": 99.52269744873047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30728113651275635, "tokens_per_second": 8977560.788784552, "eta_seconds": 9480.219171595574, "data_wait_seconds": 1.7583370208740234e-05} {"step": 12900, "total_steps": 22439, "tokens": 114976358400, "source": "fineweb_hq", "phase": 2, "loss": 1.9719631373882294, "ce_loss": 1.9719631373882294, "logit_z_loss": 95.65886497497559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30726951360702515, "tokens_per_second": 8984468.146135902, "eta_seconds": 9463.010337519645, "data_wait_seconds": 1.621246337890625e-05} {"step": 12910, "total_steps": 22439, "tokens": 115065487360, "source": "fineweb_hq", "phase": 2, "loss": 1.9513772130012512, "ce_loss": 1.9513772130012512, "logit_z_loss": 93.08441162109375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33158862590789795, "tokens_per_second": 9746706.762122877, "eta_seconds": 8713.81360461712, "data_wait_seconds": 1.901388168334961e-05} {"step": 12920, "total_steps": 22439, "tokens": 115154616320, "source": "fineweb_hq", "phase": 2, "loss": 1.9476059973239899, "ce_loss": 1.9476059973239899, "logit_z_loss": 98.62985420227051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26240435242652893, "tokens_per_second": 9186326.214458529, "eta_seconds": 9235.667778754234, "data_wait_seconds": 1.7464160919189453e-05} {"step": 12930, "total_steps": 22439, "tokens": 115243745280, "source": "fineweb_hq", "phase": 2, "loss": 1.955357849597931, "ce_loss": 1.955357849597931, "logit_z_loss": 97.40411376953125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2269044816493988, "tokens_per_second": 9794670.769360725, "eta_seconds": 8652.94301970005, "data_wait_seconds": 1.996755599975586e-05} {"step": 12940, "total_steps": 22439, "tokens": 115332874240, "source": "fineweb_hq", "phase": 2, "loss": 1.9469572305679321, "ce_loss": 1.9469572305679321, "logit_z_loss": 93.89006805419922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3485148549079895, "tokens_per_second": 8188289.401218587, "eta_seconds": 10339.595360589026, "data_wait_seconds": 2.0384788513183594e-05} {"step": 12950, "total_steps": 22439, "tokens": 115422003200, "source": "fineweb_hq", "phase": 2, "loss": 1.951456755399704, "ce_loss": 1.951456755399704, "logit_z_loss": 96.6485538482666, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31729352474212646, "tokens_per_second": 10301240.19039526, "eta_seconds": 8210.125051045417, "data_wait_seconds": 1.6570091247558594e-05} {"step": 12960, "total_steps": 22439, "tokens": 115511132160, "source": "fineweb_hq", "phase": 2, "loss": 1.9425728023052216, "ce_loss": 1.9425728023052216, "logit_z_loss": 93.46582221984863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.43617114424705505, "tokens_per_second": 9319302.337422734, "eta_seconds": 9065.629392099381, "data_wait_seconds": 1.9311904907226562e-05} {"step": 12970, "total_steps": 22439, "tokens": 115600261120, "source": "fineweb_hq", "phase": 2, "loss": 1.9643314480781555, "ce_loss": 1.9643314480781555, "logit_z_loss": 96.88921165466309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2976202070713043, "tokens_per_second": 7826261.418229685, "eta_seconds": 10783.720056605338, "data_wait_seconds": 0.49321943521499634} {"step": 12980, "total_steps": 22439, "tokens": 115689390080, "source": "fineweb_hq", "phase": 2, "loss": 1.968631774187088, "ce_loss": 1.968631774187088, "logit_z_loss": 97.70304107666016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29157155752182007, "tokens_per_second": 9328424.5051734, "eta_seconds": 9037.65509569645, "data_wait_seconds": 2.0503997802734375e-05} {"step": 12990, "total_steps": 22439, "tokens": 115778519040, "source": "fineweb_hq", "phase": 2, "loss": 1.9808609783649445, "ce_loss": 1.9808609783649445, "logit_z_loss": 96.32892799377441, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2696954309940338, "tokens_per_second": 8541984.070208823, "eta_seconds": 9859.296576976776, "data_wait_seconds": 2.2709369659423828e-05} {"step": 13000, "total_steps": 22439, "tokens": 115867648000, "source": "fineweb_hq", "phase": 2, "loss": 1.983223557472229, "ce_loss": 1.983223557472229, "logit_z_loss": 91.77549171447754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2962226867675781, "tokens_per_second": 9530512.037331332, "eta_seconds": 8827.314315795898, "data_wait_seconds": 2.0682811737060547e-05} {"step": 13010, "total_steps": 22439, "tokens": 115956776960, "source": "fineweb_hq", "phase": 2, "loss": 1.9738962054252625, "ce_loss": 1.9738962054252625, "logit_z_loss": 96.37679290771484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28723445534706116, "tokens_per_second": 5443386.516861812, "eta_seconds": 15438.862576389312, "data_wait_seconds": 1.0270463824272156} {"step": 13020, "total_steps": 22439, "tokens": 116045905920, "source": "fineweb_hq", "phase": 2, "loss": 1.9739839732646942, "ce_loss": 1.9739839732646942, "logit_z_loss": 93.34645080566406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3002482056617737, "tokens_per_second": 7307770.3346258, "eta_seconds": 11487.849724316597, "data_wait_seconds": 0.20409387350082397} {"step": 13030, "total_steps": 22439, "tokens": 116135034880, "source": "fineweb_hq", "phase": 2, "loss": 1.9714138805866241, "ce_loss": 1.9714138805866241, "logit_z_loss": 94.1760025024414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28354305028915405, "tokens_per_second": 7919661.703200962, "eta_seconds": 10589.017764496803, "data_wait_seconds": 2.002716064453125e-05} {"step": 13040, "total_steps": 22439, "tokens": 116224163840, "source": "fineweb_hq", "phase": 2, "loss": 2.0089001953601837, "ce_loss": 2.0089001953601837, "logit_z_loss": 94.55704689025879, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33542850613594055, "tokens_per_second": 8707380.58972355, "eta_seconds": 9620.83931450844, "data_wait_seconds": 0.27077245712280273} {"step": 13050, "total_steps": 22439, "tokens": 116313292800, "source": "fineweb_hq", "phase": 2, "loss": 1.9973955154418945, "ce_loss": 1.9973955154418945, "logit_z_loss": 92.5914421081543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27617740631103516, "tokens_per_second": 8811037.16319234, "eta_seconds": 9497.540300202369, "data_wait_seconds": 1.7344951629638672e-05} {"step": 13060, "total_steps": 22439, "tokens": 116402421760, "source": "fineweb_hq", "phase": 2, "loss": 2.015120804309845, "ce_loss": 2.015120804309845, "logit_z_loss": 94.91195106506348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2619588375091553, "tokens_per_second": 9840704.92016986, "eta_seconds": 8494.721898698806, "data_wait_seconds": 2.1636486053466797e-05} {"step": 13070, "total_steps": 22439, "tokens": 116491550720, "source": "fineweb_hq", "phase": 2, "loss": 2.03615540266037, "ce_loss": 2.03615540266037, "logit_z_loss": 94.76774978637695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2916007936000824, "tokens_per_second": 8590069.996136429, "eta_seconds": 9721.099206590652, "data_wait_seconds": 1.8715858459472656e-05} {"step": 13080, "total_steps": 22439, "tokens": 116580679680, "source": "fineweb_hq", "phase": 2, "loss": 2.0125732421875, "ce_loss": 2.0125732421875, "logit_z_loss": 93.73718070983887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3924613893032074, "tokens_per_second": 9473549.200414091, "eta_seconds": 8805.125924754144, "data_wait_seconds": 2.7239322662353516e-05} {"step": 13090, "total_steps": 22439, "tokens": 116669808640, "source": "fineweb_hq", "phase": 2, "loss": 1.9992603063583374, "ce_loss": 1.9992603063583374, "logit_z_loss": 91.3711109161377, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.273440420627594, "tokens_per_second": 9113993.845366491, "eta_seconds": 9142.716806459428, "data_wait_seconds": 2.0444393157958984e-05} {"step": 13100, "total_steps": 22439, "tokens": 116758937600, "source": "fineweb_hq", "phase": 2, "loss": 2.0160231590270996, "ce_loss": 2.0160231590270996, "logit_z_loss": 92.62715721130371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3400525450706482, "tokens_per_second": 9625666.975061024, "eta_seconds": 8647.456426620483, "data_wait_seconds": 1.615285873413086e-05} {"step": 13110, "total_steps": 22439, "tokens": 116848066560, "source": "fineweb_hq", "phase": 2, "loss": 2.0140273571014404, "ce_loss": 2.0140273571014404, "logit_z_loss": 95.47670555114746, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3069874346256256, "tokens_per_second": 9696864.419094758, "eta_seconds": 8574.772544026375, "data_wait_seconds": 1.5437602996826172e-05} {"step": 13120, "total_steps": 22439, "tokens": 116937195520, "source": "fineweb_hq", "phase": 2, "loss": 2.003050774335861, "ce_loss": 2.003050774335861, "logit_z_loss": 90.15055465698242, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35141095519065857, "tokens_per_second": 9629884.940638492, "eta_seconds": 8625.157863879203, "data_wait_seconds": 1.5437602996826172e-05} {"step": 13130, "total_steps": 22439, "tokens": 117026324480, "source": "fineweb_hq", "phase": 2, "loss": 2.0092077255249023, "ce_loss": 2.0092077255249023, "logit_z_loss": 94.01493072509766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2899346351623535, "tokens_per_second": 8434165.51622298, "eta_seconds": 9837.386840987205, "data_wait_seconds": 1.621246337890625e-05} {"step": 13140, "total_steps": 22439, "tokens": 117115453440, "source": "fineweb_hq", "phase": 2, "loss": 2.010484755039215, "ce_loss": 2.010484755039215, "logit_z_loss": 89.42593002319336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2629948854446411, "tokens_per_second": 9940439.18827439, "eta_seconds": 8337.762379932403, "data_wait_seconds": 1.6868114471435547e-05} {"step": 13150, "total_steps": 22439, "tokens": 117204582400, "source": "fineweb_hq", "phase": 2, "loss": 2.006840616464615, "ce_loss": 2.006840616464615, "logit_z_loss": 93.05060958862305, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3006197512149811, "tokens_per_second": 8187593.930995452, "eta_seconds": 10111.870671868324, "data_wait_seconds": 1.996755599975586e-05} {"step": 13160, "total_steps": 22439, "tokens": 117293711360, "source": "fineweb_hq", "phase": 2, "loss": 2.014511227607727, "ce_loss": 2.014511227607727, "logit_z_loss": 88.77019500732422, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3285844027996063, "tokens_per_second": 8690587.046139454, "eta_seconds": 9516.360810256005, "data_wait_seconds": 1.9490718841552734e-05} {"step": 13170, "total_steps": 22439, "tokens": 117382840320, "source": "fineweb_hq", "phase": 2, "loss": 1.9481889605522156, "ce_loss": 1.9481889605522156, "logit_z_loss": 95.11965370178223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34837865829467773, "tokens_per_second": 9009883.784594161, "eta_seconds": 9169.222933292389, "data_wait_seconds": 1.913309097290039e-05} {"step": 13180, "total_steps": 22439, "tokens": 117471969280, "source": "fineweb_hq", "phase": 2, "loss": 1.9725828170776367, "ce_loss": 1.9725828170776367, "logit_z_loss": 93.85699844360352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2647183835506439, "tokens_per_second": 9612823.623712039, "eta_seconds": 8584.83493449688, "data_wait_seconds": 1.9550323486328125e-05} {"step": 13190, "total_steps": 22439, "tokens": 117561098240, "source": "fineweb_hq", "phase": 2, "loss": 1.9598955512046814, "ce_loss": 1.9598955512046814, "logit_z_loss": 95.36152648925781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2665894329547882, "tokens_per_second": 9209180.000301525, "eta_seconds": 8951.434883594513, "data_wait_seconds": 3.4332275390625e-05} {"step": 13200, "total_steps": 22439, "tokens": 117650227200, "source": "fineweb_hq", "phase": 2, "loss": 1.9745086133480072, "ce_loss": 1.9745086133480072, "logit_z_loss": 93.36581993103027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26046308875083923, "tokens_per_second": 9967354.504808119, "eta_seconds": 8261.595000386238, "data_wait_seconds": 2.199411392211914e-05} {"step": 13210, "total_steps": 22439, "tokens": 117739356160, "source": "fineweb_hq", "phase": 2, "loss": 1.9578334093093872, "ce_loss": 1.9578334093093872, "logit_z_loss": 94.58608055114746, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2830658257007599, "tokens_per_second": 9291061.998532703, "eta_seconds": 8853.360056900978, "data_wait_seconds": 1.8596649169921875e-05} {"step": 13220, "total_steps": 22439, "tokens": 117828485120, "source": "fineweb_hq", "phase": 2, "loss": 1.9504069089889526, "ce_loss": 1.9504069089889526, "logit_z_loss": 91.14476013183594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.263915091753006, "tokens_per_second": 9148557.450116992, "eta_seconds": 8981.523991298676, "data_wait_seconds": 1.901388168334961e-05} {"step": 13230, "total_steps": 22439, "tokens": 117917614080, "source": "fineweb_hq", "phase": 2, "loss": 1.9695312678813934, "ce_loss": 1.9695312678813934, "logit_z_loss": 97.63335990905762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3029535412788391, "tokens_per_second": 9363593.313604947, "eta_seconds": 8765.743717718124, "data_wait_seconds": 2.1636486053466797e-05} {"step": 13240, "total_steps": 22439, "tokens": 118006743040, "source": "fineweb_hq", "phase": 2, "loss": 1.9804404973983765, "ce_loss": 1.9804404973983765, "logit_z_loss": 96.1181697845459, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3194182813167572, "tokens_per_second": 10128357.096248638, "eta_seconds": 8095.067099714279, "data_wait_seconds": 1.817941665649414e-05} {"step": 13250, "total_steps": 22439, "tokens": 118095872000, "source": "fineweb_hq", "phase": 2, "loss": 1.9587458074092865, "ce_loss": 1.9587458074092865, "logit_z_loss": 95.0111141204834, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26389315724372864, "tokens_per_second": 9762799.451343942, "eta_seconds": 8389.04883298874, "data_wait_seconds": 1.919269561767578e-05} {"step": 13260, "total_steps": 22439, "tokens": 118185000960, "source": "fineweb_hq", "phase": 2, "loss": 1.9865385293960571, "ce_loss": 1.9865385293960571, "logit_z_loss": 94.9403076171875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3263327181339264, "tokens_per_second": 9758108.42502564, "eta_seconds": 8383.947873973848, "data_wait_seconds": 1.823902130126953e-05} {"step": 13270, "total_steps": 22439, "tokens": 118274129920, "source": "fineweb_hq", "phase": 2, "loss": 1.9636656641960144, "ce_loss": 1.9636656641960144, "logit_z_loss": 95.98472785949707, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3190658688545227, "tokens_per_second": 9349334.034090558, "eta_seconds": 8740.980173134803, "data_wait_seconds": 1.996755599975586e-05} {"step": 13280, "total_steps": 22439, "tokens": 118363258880, "source": "fineweb_hq", "phase": 2, "loss": 1.9826564490795135, "ce_loss": 1.9826564490795135, "logit_z_loss": 93.65717887878418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2990199327468872, "tokens_per_second": 9108006.010344274, "eta_seconds": 8962.797605895996, "data_wait_seconds": 1.5974044799804688e-05} {"step": 13290, "total_steps": 22439, "tokens": 118452387840, "source": "fineweb_hq", "phase": 2, "loss": 1.9893596172332764, "ce_loss": 1.9893596172332764, "logit_z_loss": 96.69644355773926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27250945568084717, "tokens_per_second": 9005948.142491706, "eta_seconds": 9054.46980304718, "data_wait_seconds": 2.092123031616211e-05} {"step": 13300, "total_steps": 22439, "tokens": 118541516800, "source": "fineweb_hq", "phase": 2, "loss": 2.0055090188980103, "ce_loss": 2.0055090188980103, "logit_z_loss": 93.93581581115723, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36883974075317383, "tokens_per_second": 8354041.379673568, "eta_seconds": 9750.365462899208, "data_wait_seconds": 1.609325408935547e-05} {"step": 13310, "total_steps": 22439, "tokens": 118630645760, "source": "fineweb_hq", "phase": 2, "loss": 2.008502811193466, "ce_loss": 2.008502811193466, "logit_z_loss": 93.77739906311035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3299493193626404, "tokens_per_second": 9747516.706525123, "eta_seconds": 8347.339125823974, "data_wait_seconds": 1.4662742614746094e-05} {"step": 13320, "total_steps": 22439, "tokens": 118719774720, "source": "fineweb_hq", "phase": 2, "loss": 2.006993532180786, "ce_loss": 2.006993532180786, "logit_z_loss": 93.66401863098145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2908874750137329, "tokens_per_second": 9810232.887207894, "eta_seconds": 8284.889824581147, "data_wait_seconds": 1.704692840576172e-05} {"step": 13330, "total_steps": 22439, "tokens": 118808903680, "source": "fineweb_hq", "phase": 2, "loss": 2.009333372116089, "ce_loss": 2.009333372116089, "logit_z_loss": 93.45150566101074, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.43913763761520386, "tokens_per_second": 8861920.619665552, "eta_seconds": 9161.396625900268, "data_wait_seconds": 1.3887882232666016e-05} {"step": 13340, "total_steps": 22439, "tokens": 118898032640, "source": "fineweb_hq", "phase": 2, "loss": 2.0158379673957825, "ce_loss": 2.0158379673957825, "logit_z_loss": 88.30636596679688, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3230426013469696, "tokens_per_second": 10159831.139370766, "eta_seconds": 7982.262656879425, "data_wait_seconds": 1.5854835510253906e-05} {"step": 13350, "total_steps": 22439, "tokens": 118987161600, "source": "fineweb_hq", "phase": 2, "loss": 2.0107197761535645, "ce_loss": 2.0107197761535645, "logit_z_loss": 90.79269981384277, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3025785982608795, "tokens_per_second": 8805357.708811881, "eta_seconds": 9200.00236480236, "data_wait_seconds": 2.1576881408691406e-05} {"step": 13360, "total_steps": 22439, "tokens": 119076290560, "source": "fineweb_hq", "phase": 2, "loss": 2.005750358104706, "ce_loss": 2.005750358104706, "logit_z_loss": 93.15617179870605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29944688081741333, "tokens_per_second": 9086387.716335129, "eta_seconds": 8905.649341654778, "data_wait_seconds": 1.7821788787841797e-05} {"step": 13370, "total_steps": 22439, "tokens": 119165419520, "source": "fineweb_hq", "phase": 2, "loss": 2.003004789352417, "ce_loss": 2.003004789352417, "logit_z_loss": 92.03725051879883, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2776922285556793, "tokens_per_second": 9116460.23573298, "eta_seconds": 8866.495518422127, "data_wait_seconds": 1.6689300537109375e-05} {"step": 13380, "total_steps": 22439, "tokens": 119254548480, "source": "fineweb_hq", "phase": 2, "loss": 2.0149276852607727, "ce_loss": 2.0149276852607727, "logit_z_loss": 93.88196563720703, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38530588150024414, "tokens_per_second": 8920126.43581402, "eta_seconds": 9051.656996679305, "data_wait_seconds": 1.7464160919189453e-05} {"step": 13390, "total_steps": 22439, "tokens": 119343677440, "source": "fineweb_hq", "phase": 2, "loss": 1.998179852962494, "ce_loss": 1.998179852962494, "logit_z_loss": 89.80924415588379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30230262875556946, "tokens_per_second": 8822204.672224922, "eta_seconds": 9142.02275967598, "data_wait_seconds": 0.3887636065483093} {"step": 13400, "total_steps": 22439, "tokens": 119432806400, "source": "fineweb_hq", "phase": 2, "loss": 2.0240328311920166, "ce_loss": 2.0240328311920166, "logit_z_loss": 93.32171249389648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30306872725486755, "tokens_per_second": 9271621.624116566, "eta_seconds": 8689.274671697616, "data_wait_seconds": 1.5079975128173828e-05} {"step": 13410, "total_steps": 22439, "tokens": 119521935360, "source": "fineweb_hq", "phase": 2, "loss": 2.008731484413147, "ce_loss": 2.008731484413147, "logit_z_loss": 94.39014625549316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3112582862377167, "tokens_per_second": 8398153.343357485, "eta_seconds": 9582.408738422393, "data_wait_seconds": 1.722574234008789e-05} {"step": 13420, "total_steps": 22439, "tokens": 119611064320, "source": "fineweb_hq", "phase": 2, "loss": 1.991981953382492, "ce_loss": 1.991981953382492, "logit_z_loss": 90.96493911743164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32216864824295044, "tokens_per_second": 7637101.424791485, "eta_seconds": 10525.64376885891, "data_wait_seconds": 1.817941665649414e-05} {"step": 13430, "total_steps": 22439, "tokens": 119700193280, "source": "fineweb_hq", "phase": 2, "loss": 1.9725339710712433, "ce_loss": 1.9725339710712433, "logit_z_loss": 94.00249290466309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27955299615859985, "tokens_per_second": 5028905.149712836, "eta_seconds": 15966.950593328476, "data_wait_seconds": 0.20126348733901978} {"step": 13440, "total_steps": 22439, "tokens": 119789322240, "source": "fineweb_hq", "phase": 2, "loss": 1.9619758129119873, "ce_loss": 1.9619758129119873, "logit_z_loss": 91.33828163146973, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3316483199596405, "tokens_per_second": 7251958.567644405, "eta_seconds": 11060.067477750777, "data_wait_seconds": 0.43073534965515137} {"step": 13450, "total_steps": 22439, "tokens": 119878451200, "source": "fineweb_hq", "phase": 2, "loss": 1.9773535430431366, "ce_loss": 1.9773535430431366, "logit_z_loss": 95.12632751464844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2924151122570038, "tokens_per_second": 2402044.2472769264, "eta_seconds": 33354.09921562672, "data_wait_seconds": 3.8571633100509644} {"step": 13460, "total_steps": 22439, "tokens": 119967580160, "source": "fineweb_hq", "phase": 2, "loss": 1.9770936369895935, "ce_loss": 1.9770936369895935, "logit_z_loss": 93.97627258300781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36586833000183105, "tokens_per_second": 4469526.598337901, "eta_seconds": 17905.45182430744, "data_wait_seconds": 0.3176203966140747} {"step": 13470, "total_steps": 22439, "tokens": 120056709120, "source": "fineweb_hq", "phase": 2, "loss": 1.9908798933029175, "ce_loss": 1.9908798933029175, "logit_z_loss": 96.31475448608398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30338284373283386, "tokens_per_second": 9890143.836153526, "eta_seconds": 8082.770639975866, "data_wait_seconds": 1.9848346710205078e-05} {"step": 13480, "total_steps": 22439, "tokens": 120145838080, "source": "fineweb_hq", "phase": 2, "loss": 1.9907183647155762, "ce_loss": 1.9907183647155762, "logit_z_loss": 97.46763038635254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2803896963596344, "tokens_per_second": 3940048.2976099076, "eta_seconds": 20266.410265183447, "data_wait_seconds": 1.243204653263092} {"step": 13490, "total_steps": 22439, "tokens": 120234967040, "source": "fineweb_hq", "phase": 2, "loss": 1.9931279718875885, "ce_loss": 1.9931279718875885, "logit_z_loss": 93.00046730041504, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3082811236381531, "tokens_per_second": 8352343.991387098, "eta_seconds": 9549.5954652071, "data_wait_seconds": 2.6702880859375e-05} {"step": 13500, "total_steps": 22439, "tokens": 120324096000, "source": "fineweb_hq", "phase": 2, "loss": 1.9745163917541504, "ce_loss": 1.9745163917541504, "logit_z_loss": 93.80125617980957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3008025884628296, "tokens_per_second": 8726723.78153191, "eta_seconds": 9129.700829148293, "data_wait_seconds": 2.193450927734375e-05} {"step": 13510, "total_steps": 22439, "tokens": 120413224960, "source": "fineweb_hq", "phase": 2, "loss": 1.9842312932014465, "ce_loss": 1.9842312932014465, "logit_z_loss": 89.72903633117676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30001962184906006, "tokens_per_second": 4248619.465509025, "eta_seconds": 18731.554809761048, "data_wait_seconds": 0.2371746301651001} {"step": 13520, "total_steps": 22439, "tokens": 120502353920, "source": "fineweb_hq", "phase": 2, "loss": 1.9730369746685028, "ce_loss": 1.9730369746685028, "logit_z_loss": 97.64413642883301, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3043693006038666, "tokens_per_second": 4965512.988117895, "eta_seconds": 16009.246096873281, "data_wait_seconds": 1.6391277313232422e-05} {"step": 13530, "total_steps": 22439, "tokens": 120591482880, "source": "fineweb_hq", "phase": 2, "loss": 1.9769623577594757, "ce_loss": 1.9769623577594757, "logit_z_loss": 95.75336647033691, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3023589551448822, "tokens_per_second": 4474874.901245261, "eta_seconds": 17744.62799885273, "data_wait_seconds": 1.3725271224975586} {"step": 13540, "total_steps": 22439, "tokens": 120680611840, "source": "fineweb_hq", "phase": 2, "loss": 1.963119089603424, "ce_loss": 1.963119089603424, "logit_z_loss": 92.71071815490723, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3130733370780945, "tokens_per_second": 7343018.364537771, "eta_seconds": 10801.533860659598, "data_wait_seconds": 1.7881393432617188e-05} {"step": 13550, "total_steps": 22439, "tokens": 120769740800, "source": "fineweb_hq", "phase": 2, "loss": 1.9565820097923279, "ce_loss": 1.9565820097923279, "logit_z_loss": 96.15860557556152, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.316873699426651, "tokens_per_second": 9148647.676973118, "eta_seconds": 8659.939188981056, "data_wait_seconds": 1.8477439880371094e-05} {"step": 13560, "total_steps": 22439, "tokens": 120858869760, "source": "fineweb_hq", "phase": 2, "loss": 1.9497295916080475, "ce_loss": 1.9497295916080475, "logit_z_loss": 94.65755271911621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34692004323005676, "tokens_per_second": 9541498.698125876, "eta_seconds": 8294.04332461357, "data_wait_seconds": 2.008676528930664e-05} {"step": 13570, "total_steps": 22439, "tokens": 120947998720, "source": "fineweb_hq", "phase": 2, "loss": 1.958614021539688, "ce_loss": 1.958614021539688, "logit_z_loss": 97.69816970825195, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37370944023132324, "tokens_per_second": 9511233.009026863, "eta_seconds": 8311.064879703521, "data_wait_seconds": 1.9252300262451172e-05} {"step": 13580, "total_steps": 22439, "tokens": 121037127680, "source": "fineweb_hq", "phase": 2, "loss": 1.9582009315490723, "ce_loss": 1.9582009315490723, "logit_z_loss": 96.16808700561523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2904295325279236, "tokens_per_second": 9342791.174114492, "eta_seconds": 8451.365784859658, "data_wait_seconds": 1.7523765563964844e-05} {"step": 13590, "total_steps": 22439, "tokens": 121126256640, "source": "fineweb_hq", "phase": 2, "loss": 1.9591393172740936, "ce_loss": 1.9591393172740936, "logit_z_loss": 97.01742553710938, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3255210220813751, "tokens_per_second": 9529046.906917034, "eta_seconds": 8276.821121191979, "data_wait_seconds": 1.806020736694336e-05} {"step": 13600, "total_steps": 22439, "tokens": 121215385600, "source": "fineweb_hq", "phase": 2, "loss": 1.9597129225730896, "ce_loss": 1.9597129225730896, "logit_z_loss": 96.88886451721191, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30768924951553345, "tokens_per_second": 9224917.091711482, "eta_seconds": 8540.032063245773, "data_wait_seconds": 1.9431114196777344e-05} {"step": 13610, "total_steps": 22439, "tokens": 121304514560, "source": "fineweb_hq", "phase": 2, "loss": 1.9575677514076233, "ce_loss": 1.9575677514076233, "logit_z_loss": 95.36848068237305, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30157163739204407, "tokens_per_second": 10226735.051463189, "eta_seconds": 7694.7293919324875, "data_wait_seconds": 1.8537044525146484e-05} {"step": 13620, "total_steps": 22439, "tokens": 121393643520, "source": "fineweb_hq", "phase": 2, "loss": 1.963811069726944, "ce_loss": 1.963811069726944, "logit_z_loss": 99.71216011047363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2910251021385193, "tokens_per_second": 8307326.668724124, "eta_seconds": 9461.868174743653, "data_wait_seconds": 1.6629695892333984e-05} {"step": 13630, "total_steps": 22439, "tokens": 121482772480, "source": "fineweb_hq", "phase": 2, "loss": 1.9497116804122925, "ce_loss": 1.9497116804122925, "logit_z_loss": 95.90683937072754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3088696002960205, "tokens_per_second": 9910833.753728023, "eta_seconds": 7922.007654953003, "data_wait_seconds": 1.8477439880371094e-05} {"step": 13640, "total_steps": 22439, "tokens": 121571901440, "source": "fineweb_hq", "phase": 2, "loss": 1.961919903755188, "ce_loss": 1.961919903755188, "logit_z_loss": 99.61413955688477, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30549290776252747, "tokens_per_second": 9745522.96571926, "eta_seconds": 8047.240992593765, "data_wait_seconds": 1.9311904907226562e-05} {"step": 13650, "total_steps": 22439, "tokens": 121661030400, "source": "fineweb_hq", "phase": 2, "loss": 1.979222685098648, "ce_loss": 1.979222685098648, "logit_z_loss": 96.1176872253418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33531516790390015, "tokens_per_second": 8413528.117037976, "eta_seconds": 9310.653254413604, "data_wait_seconds": 1.811981201171875e-05} {"step": 13660, "total_steps": 22439, "tokens": 121750159360, "source": "fineweb_hq", "phase": 2, "loss": 1.9748959839344025, "ce_loss": 1.9748959839344025, "logit_z_loss": 99.53309631347656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2701698839664459, "tokens_per_second": 8576949.539740697, "eta_seconds": 9122.860478711127, "data_wait_seconds": 2.6345252990722656e-05} {"step": 13670, "total_steps": 22439, "tokens": 121839288320, "source": "fineweb_hq", "phase": 2, "loss": 1.9942564070224762, "ce_loss": 1.9942564070224762, "logit_z_loss": 93.3276596069336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3871513903141022, "tokens_per_second": 7865068.251332717, "eta_seconds": 9937.25451915264, "data_wait_seconds": 1.7821788787841797e-05} {"step": 13680, "total_steps": 22439, "tokens": 121928417280, "source": "fineweb_hq", "phase": 2, "loss": 1.9922995269298553, "ce_loss": 1.9922995269298553, "logit_z_loss": 93.55233383178711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31121528148651123, "tokens_per_second": 8168980.209303566, "eta_seconds": 9556.646492433549, "data_wait_seconds": 1.996755599975586e-05} {"step": 13690, "total_steps": 22439, "tokens": 122017546240, "source": "fineweb_hq", "phase": 2, "loss": 1.991873949766159, "ce_loss": 1.991873949766159, "logit_z_loss": 97.56992530822754, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28495675325393677, "tokens_per_second": 9740703.344245162, "eta_seconds": 8005.471920061111, "data_wait_seconds": 2.5212764739990234e-05} {"step": 13700, "total_steps": 22439, "tokens": 122106675200, "source": "fineweb_hq", "phase": 2, "loss": 2.0112223029136658, "ce_loss": 2.0112223029136658, "logit_z_loss": 92.97984504699707, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3046967685222626, "tokens_per_second": 9301722.163780188, "eta_seconds": 8373.696480345727, "data_wait_seconds": 1.6808509826660156e-05} {"step": 13710, "total_steps": 22439, "tokens": 122195804160, "source": "fineweb_hq", "phase": 2, "loss": 2.0004738569259644, "ce_loss": 2.0004738569259644, "logit_z_loss": 96.0723991394043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3360705077648163, "tokens_per_second": 8304286.965200512, "eta_seconds": 9368.735631370544, "data_wait_seconds": 1.430511474609375e-05} {"step": 13720, "total_steps": 22439, "tokens": 122284933120, "source": "fineweb_hq", "phase": 2, "loss": 1.9986938536167145, "ce_loss": 1.9986938536167145, "logit_z_loss": 94.94450950622559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3449920415878296, "tokens_per_second": 8340570.134931162, "eta_seconds": 9317.293538308144, "data_wait_seconds": 2.5928020477294922e-05} {"step": 13730, "total_steps": 22439, "tokens": 122374062080, "source": "fineweb_hq", "phase": 2, "loss": 1.9878675043582916, "ce_loss": 1.9878675043582916, "logit_z_loss": 92.23155212402344, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27405500411987305, "tokens_per_second": 9053754.13055369, "eta_seconds": 8573.505547499657, "data_wait_seconds": 1.823902130126953e-05} {"step": 13740, "total_steps": 22439, "tokens": 122463191040, "source": "fineweb_hq", "phase": 2, "loss": 2.0047789812088013, "ce_loss": 2.0047789812088013, "logit_z_loss": 90.76597023010254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.310519278049469, "tokens_per_second": 9566226.718476549, "eta_seconds": 8104.897007536888, "data_wait_seconds": 1.823902130126953e-05} {"step": 13750, "total_steps": 22439, "tokens": 122552320000, "source": "fineweb_hq", "phase": 2, "loss": 2.0058498680591583, "ce_loss": 2.0058498680591583, "logit_z_loss": 97.54479217529297, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.274586945772171, "tokens_per_second": 8477888.92624385, "eta_seconds": 9134.8393471241, "data_wait_seconds": 2.008676528930664e-05} {"step": 13760, "total_steps": 22439, "tokens": 122641448960, "source": "fineweb_hq", "phase": 2, "loss": 2.0089237093925476, "ce_loss": 2.0089237093925476, "logit_z_loss": 93.84281539916992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3392833173274994, "tokens_per_second": 8691516.895428484, "eta_seconds": 8900.06029036045, "data_wait_seconds": 2.2530555725097656e-05} {"step": 13770, "total_steps": 22439, "tokens": 122730577920, "source": "fineweb_hq", "phase": 2, "loss": 2.0201882123947144, "ce_loss": 2.0201882123947144, "logit_z_loss": 93.06369972229004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.40990352630615234, "tokens_per_second": 10784942.490546146, "eta_seconds": 7164.238056135177, "data_wait_seconds": 1.6391277313232422e-05} {"step": 13780, "total_steps": 22439, "tokens": 122819706880, "source": "fineweb_hq", "phase": 2, "loss": 2.02224999666214, "ce_loss": 2.02224999666214, "logit_z_loss": 96.03551864624023, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3332923650741577, "tokens_per_second": 8793286.618920963, "eta_seconds": 8776.78276720047, "data_wait_seconds": 1.9729137420654297e-05} {"step": 13790, "total_steps": 22439, "tokens": 122908835840, "source": "fineweb_hq", "phase": 2, "loss": 2.0087127685546875, "ce_loss": 2.0087127685546875, "logit_z_loss": 98.53915786743164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2842710018157959, "tokens_per_second": 9814143.191511542, "eta_seconds": 7854.749619984627, "data_wait_seconds": 1.9550323486328125e-05} {"step": 13800, "total_steps": 22439, "tokens": 122997964800, "source": "fineweb_hq", "phase": 2, "loss": 1.9947209358215332, "ce_loss": 1.9947209358215332, "logit_z_loss": 95.88209915161133, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37237992882728577, "tokens_per_second": 9428413.214908624, "eta_seconds": 8166.645520186425, "data_wait_seconds": 2.199411392211914e-05} {"step": 13810, "total_steps": 22439, "tokens": 123087093760, "source": "fineweb_hq", "phase": 2, "loss": 2.0063119530677795, "ce_loss": 2.0063119530677795, "logit_z_loss": 96.29217720031738, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28349411487579346, "tokens_per_second": 9836006.032934945, "eta_seconds": 7819.167589616776, "data_wait_seconds": 1.806020736694336e-05} {"step": 13820, "total_steps": 22439, "tokens": 123176222720, "source": "fineweb_hq", "phase": 2, "loss": 2.002077490091324, "ce_loss": 2.002077490091324, "logit_z_loss": 93.2352409362793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3349325954914093, "tokens_per_second": 8342049.963935626, "eta_seconds": 9208.79771232605, "data_wait_seconds": 1.710653305053711e-05} {"step": 13830, "total_steps": 22439, "tokens": 123265351680, "source": "fineweb_hq", "phase": 2, "loss": 2.0052240788936615, "ce_loss": 2.0052240788936615, "logit_z_loss": 97.81987190246582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3057960271835327, "tokens_per_second": 7480928.236114914, "eta_seconds": 10256.8985080719, "data_wait_seconds": 1.8835067749023438e-05} {"step": 13840, "total_steps": 22439, "tokens": 123354480640, "source": "fineweb_hq", "phase": 2, "loss": 1.9751497507095337, "ce_loss": 1.9751497507095337, "logit_z_loss": 95.08969688415527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27132001519203186, "tokens_per_second": 9595942.117950883, "eta_seconds": 7986.916944885254, "data_wait_seconds": 2.2470951080322266e-05} {"step": 13850, "total_steps": 22439, "tokens": 123443609600, "source": "fineweb_hq", "phase": 2, "loss": 1.9755214154720306, "ce_loss": 1.9755214154720306, "logit_z_loss": 98.82161712646484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28856155276298523, "tokens_per_second": 8794038.9416298, "eta_seconds": 8705.08582599163, "data_wait_seconds": 1.5437602996826172e-05} {"step": 13860, "total_steps": 22439, "tokens": 123532738560, "source": "fineweb_hq", "phase": 2, "loss": 1.9921892285346985, "ce_loss": 1.9921892285346985, "logit_z_loss": 94.8035774230957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29099181294441223, "tokens_per_second": 8861083.964936525, "eta_seconds": 8629.162649464606, "data_wait_seconds": 1.6987323760986328e-05} {"step": 13870, "total_steps": 22439, "tokens": 123621867520, "source": "fineweb_hq", "phase": 2, "loss": 1.9728728234767914, "ce_loss": 1.9728728234767914, "logit_z_loss": 95.1507511138916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26450544595718384, "tokens_per_second": 9700005.494194394, "eta_seconds": 7873.666243767739, "data_wait_seconds": 1.722574234008789e-05} {"step": 13880, "total_steps": 22439, "tokens": 123710996480, "source": "fineweb_hq", "phase": 2, "loss": 1.9895047843456268, "ce_loss": 1.9895047843456268, "logit_z_loss": 97.07826042175293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28037410974502563, "tokens_per_second": 9962791.193794826, "eta_seconds": 7657.0386129856115, "data_wait_seconds": 1.7702579498291016e-05} {"step": 13890, "total_steps": 22439, "tokens": 123800125440, "source": "fineweb_hq", "phase": 2, "loss": 1.9842492938041687, "ce_loss": 1.9842492938041687, "logit_z_loss": 94.22905349731445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35992431640625, "tokens_per_second": 9185250.698053489, "eta_seconds": 8295.51096739769, "data_wait_seconds": 1.5676021575927734e-05} {"step": 13900, "total_steps": 22439, "tokens": 123889254400, "source": "fineweb_hq", "phase": 2, "loss": 1.980204313993454, "ce_loss": 1.980204313993454, "logit_z_loss": 91.03021430969238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30469104647636414, "tokens_per_second": 9641445.180785308, "eta_seconds": 7893.756331849098, "data_wait_seconds": 1.7821788787841797e-05} {"step": 13910, "total_steps": 22439, "tokens": 123978383360, "source": "fineweb_hq", "phase": 2, "loss": 1.98056161403656, "ce_loss": 1.98056161403656, "logit_z_loss": 94.97837257385254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3258710205554962, "tokens_per_second": 8779769.674429301, "eta_seconds": 8658.323942756653, "data_wait_seconds": 1.823902130126953e-05} {"step": 13920, "total_steps": 22439, "tokens": 124067512320, "source": "fineweb_hq", "phase": 2, "loss": 2.0029188096523285, "ce_loss": 2.0029188096523285, "logit_z_loss": 97.59426879882812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2895285487174988, "tokens_per_second": 7755741.667216414, "eta_seconds": 9790.032247328758, "data_wait_seconds": 0.447968065738678} {"step": 13930, "total_steps": 22439, "tokens": 124156641280, "source": "fineweb_hq", "phase": 2, "loss": 1.9772913753986359, "ce_loss": 1.9772913753986359, "logit_z_loss": 98.74895477294922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3059866726398468, "tokens_per_second": 8782403.425038623, "eta_seconds": 8635.43023402691, "data_wait_seconds": 1.8417835235595703e-05} {"step": 13940, "total_steps": 22439, "tokens": 124245770240, "source": "fineweb_hq", "phase": 2, "loss": 1.9656686186790466, "ce_loss": 1.9656686186790466, "logit_z_loss": 96.29242324829102, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3366704285144806, "tokens_per_second": 7984830.998797749, "eta_seconds": 9486.82609755993, "data_wait_seconds": 1.8894672393798828e-05} {"step": 13950, "total_steps": 22439, "tokens": 124334899200, "source": "fineweb_hq", "phase": 2, "loss": 1.9692180156707764, "ce_loss": 1.9692180156707764, "logit_z_loss": 92.93194580078125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2771683931350708, "tokens_per_second": 8185560.206231982, "eta_seconds": 9243.298227334022, "data_wait_seconds": 1.4781951904296875e-05} {"step": 13960, "total_steps": 22439, "tokens": 124424028160, "source": "fineweb_hq", "phase": 2, "loss": 1.9771843254566193, "ce_loss": 1.9771843254566193, "logit_z_loss": 101.0455265045166, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30252185463905334, "tokens_per_second": 7851474.710200519, "eta_seconds": 9625.254869103432, "data_wait_seconds": 1.9848346710205078e-05} {"step": 13970, "total_steps": 22439, "tokens": 124513157120, "source": "fineweb_hq", "phase": 2, "loss": 1.9678263366222382, "ce_loss": 1.9678263366222382, "logit_z_loss": 92.38015365600586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2965554893016815, "tokens_per_second": 8876218.331810964, "eta_seconds": 8503.99499001503, "data_wait_seconds": 1.4483928680419922e-05} {"step": 13980, "total_steps": 22439, "tokens": 124602286080, "source": "fineweb_hq", "phase": 2, "loss": 1.986806482076645, "ce_loss": 1.986806482076645, "logit_z_loss": 99.47839546203613, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3058484196662903, "tokens_per_second": 10215448.88226114, "eta_seconds": 7380.408647036552, "data_wait_seconds": 1.7404556274414062e-05} {"step": 13990, "total_steps": 22439, "tokens": 124691415040, "source": "fineweb_hq", "phase": 2, "loss": 1.969456434249878, "ce_loss": 1.969456434249878, "logit_z_loss": 97.33378219604492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2941233813762665, "tokens_per_second": 8888512.428172637, "eta_seconds": 8472.177871441841, "data_wait_seconds": 1.823902130126953e-05} {"step": 14000, "total_steps": 22439, "tokens": 124780544000, "source": "fineweb_hq", "phase": 2, "loss": 1.9622715711593628, "ce_loss": 1.9622715711593628, "logit_z_loss": 93.25794219970703, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30921605229377747, "tokens_per_second": 8734321.842999754, "eta_seconds": 8611.536269903183, "data_wait_seconds": 1.722574234008789e-05} {"step": 14010, "total_steps": 22439, "tokens": 124869672960, "source": "fineweb_hq", "phase": 2, "loss": 1.9830798506736755, "ce_loss": 1.9830798506736755, "logit_z_loss": 99.16204452514648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2573091387748718, "tokens_per_second": 9244480.335869094, "eta_seconds": 8126.6656052589415, "data_wait_seconds": 1.6033649444580078e-05} {"step": 14020, "total_steps": 22439, "tokens": 124958801920, "source": "fineweb_hq", "phase": 2, "loss": 1.9837181568145752, "ce_loss": 1.9837181568145752, "logit_z_loss": 92.92790222167969, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3334904909133911, "tokens_per_second": 8958407.348558735, "eta_seconds": 8376.22899968624, "data_wait_seconds": 1.8477439880371094e-05} {"step": 14030, "total_steps": 22439, "tokens": 125047930880, "source": "fineweb_hq", "phase": 2, "loss": 1.99526447057724, "ce_loss": 1.99526447057724, "logit_z_loss": 98.20559310913086, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31456729769706726, "tokens_per_second": 9299090.914681526, "eta_seconds": 8059.770912194252, "data_wait_seconds": 1.6450881958007812e-05} {"step": 14040, "total_steps": 22439, "tokens": 125137059840, "source": "fineweb_hq", "phase": 2, "loss": 1.985258936882019, "ce_loss": 1.985258936882019, "logit_z_loss": 95.95027542114258, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.25484031438827515, "tokens_per_second": 10098141.984858863, "eta_seconds": 7413.18686311245, "data_wait_seconds": 1.722574234008789e-05} {"step": 14050, "total_steps": 22439, "tokens": 125226188800, "source": "fineweb_hq", "phase": 2, "loss": 1.9865747690200806, "ce_loss": 1.9865747690200806, "logit_z_loss": 92.23924827575684, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.309122771024704, "tokens_per_second": 8088131.104006645, "eta_seconds": 9244.445173120499, "data_wait_seconds": 1.8537044525146484e-05} {"step": 14060, "total_steps": 22439, "tokens": 125315317760, "source": "fineweb_hq", "phase": 2, "loss": 2.005124092102051, "ce_loss": 2.005124092102051, "logit_z_loss": 93.6155948638916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31346139311790466, "tokens_per_second": 9031196.312085254, "eta_seconds": 8269.242855906487, "data_wait_seconds": 2.0205974578857422e-05} {"step": 14070, "total_steps": 22439, "tokens": 125404446720, "source": "fineweb_hq", "phase": 2, "loss": 2.0218740701675415, "ce_loss": 2.0218740701675415, "logit_z_loss": 92.1976203918457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31870371103286743, "tokens_per_second": 10063572.241617292, "eta_seconds": 7412.082393121719, "data_wait_seconds": 1.7881393432617188e-05} {"step": 14080, "total_steps": 22439, "tokens": 125493575680, "source": "fineweb_hq", "phase": 2, "loss": 2.027435004711151, "ce_loss": 2.027435004711151, "logit_z_loss": 95.69656562805176, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3501337468624115, "tokens_per_second": 9034016.71252073, "eta_seconds": 8246.92935986519, "data_wait_seconds": 1.5616416931152344e-05} {"step": 14090, "total_steps": 22439, "tokens": 125582704640, "source": "fineweb_hq", "phase": 2, "loss": 1.997889220714569, "ce_loss": 1.997889220714569, "logit_z_loss": 93.30718421936035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35744979977607727, "tokens_per_second": 8956835.768901944, "eta_seconds": 8308.042105937006, "data_wait_seconds": 1.8596649169921875e-05} {"step": 14100, "total_steps": 22439, "tokens": 125671833600, "source": "fineweb_hq", "phase": 2, "loss": 2.0049900710582733, "ce_loss": 2.0049900710582733, "logit_z_loss": 95.80184936523438, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34531542658805847, "tokens_per_second": 9202217.859086027, "eta_seconds": 8076.818097782135, "data_wait_seconds": 1.9073486328125e-05} {"step": 14110, "total_steps": 22439, "tokens": 125760962560, "source": "fineweb_hq", "phase": 2, "loss": 1.99844491481781, "ce_loss": 1.99844491481781, "logit_z_loss": 96.23773956298828, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27372172474861145, "tokens_per_second": 8672554.423023026, "eta_seconds": 8559.820689845084, "data_wait_seconds": 1.728534698486328e-05} {"step": 14120, "total_steps": 22439, "tokens": 125850091520, "source": "fineweb_hq", "phase": 2, "loss": 2.0116965770721436, "ce_loss": 2.0116965770721436, "logit_z_loss": 95.12408256530762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2992122769355774, "tokens_per_second": 9301858.486939566, "eta_seconds": 7971.136297988891, "data_wait_seconds": 1.52587890625e-05} {"step": 14130, "total_steps": 22439, "tokens": 125939220480, "source": "fineweb_hq", "phase": 2, "loss": 2.0057371258735657, "ce_loss": 2.0057371258735657, "logit_z_loss": 95.55208969116211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3732229173183441, "tokens_per_second": 8629825.922668409, "eta_seconds": 8581.546548867225, "data_wait_seconds": 1.901388168334961e-05} {"step": 14140, "total_steps": 22439, "tokens": 126028349440, "source": "fineweb_hq", "phase": 2, "loss": 2.024927496910095, "ce_loss": 2.024927496910095, "logit_z_loss": 94.6763916015625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3206782639026642, "tokens_per_second": 9875349.784762817, "eta_seconds": 7490.177615594864, "data_wait_seconds": 1.6510486602783203e-05} {"step": 14150, "total_steps": 22439, "tokens": 126117478400, "source": "fineweb_hq", "phase": 2, "loss": 1.9961015284061432, "ce_loss": 1.9961015284061432, "logit_z_loss": 94.87278175354004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28063952922821045, "tokens_per_second": 9479316.186098844, "eta_seconds": 7793.705104207993, "data_wait_seconds": 1.5914440155029297e-05} {"step": 14160, "total_steps": 22439, "tokens": 126206607360, "source": "fineweb_hq", "phase": 2, "loss": 2.0066925287246704, "ce_loss": 2.0066925287246704, "logit_z_loss": 91.8175277709961, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3239360451698303, "tokens_per_second": 9730397.299761705, "eta_seconds": 7583.438138318062, "data_wait_seconds": 1.6391277313232422e-05} {"step": 14170, "total_steps": 22439, "tokens": 126295736320, "source": "fineweb_hq", "phase": 2, "loss": 1.9627718329429626, "ce_loss": 1.9627718329429626, "logit_z_loss": 98.17854881286621, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2916927635669708, "tokens_per_second": 8190241.0429694895, "eta_seconds": 8998.604148197175, "data_wait_seconds": 1.8894672393798828e-05} {"step": 14180, "total_steps": 22439, "tokens": 126384865280, "source": "fineweb_hq", "phase": 2, "loss": 1.928307682275772, "ce_loss": 1.928307682275772, "logit_z_loss": 95.96257209777832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26977673172950745, "tokens_per_second": 9321523.38866095, "eta_seconds": 7896.950422668457, "data_wait_seconds": 1.5735626220703125e-05} {"step": 14190, "total_steps": 22439, "tokens": 126473994240, "source": "fineweb_hq", "phase": 2, "loss": 1.8129609823226929, "ce_loss": 1.8129609823226929, "logit_z_loss": 100.46989440917969, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30233627557754517, "tokens_per_second": 7321236.909607818, "eta_seconds": 10042.357597732544, "data_wait_seconds": 0.16963988542556763} {"step": 14200, "total_steps": 22439, "tokens": 126563123200, "source": "fineweb_hq", "phase": 2, "loss": 1.7707538604736328, "ce_loss": 1.7707538604736328, "logit_z_loss": 104.35085487365723, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3212410807609558, "tokens_per_second": 8323077.821810138, "eta_seconds": 8822.859970331192, "data_wait_seconds": 1.7523765563964844e-05} {"step": 14210, "total_steps": 22439, "tokens": 126652252160, "source": "fineweb_hq", "phase": 2, "loss": 1.7763400375843048, "ce_loss": 1.7763400375843048, "logit_z_loss": 106.83868980407715, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28585079312324524, "tokens_per_second": 9493469.196727626, "eta_seconds": 7725.75542871952, "data_wait_seconds": 1.8775463104248047e-05} {"step": 14220, "total_steps": 22439, "tokens": 126741381120, "source": "fineweb_hq", "phase": 2, "loss": 1.7628418505191803, "ce_loss": 1.7628418505191803, "logit_z_loss": 104.75446510314941, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28538385033607483, "tokens_per_second": 9951656.683050979, "eta_seconds": 7361.095198225976, "data_wait_seconds": 1.7583370208740234e-05} {"step": 14230, "total_steps": 22439, "tokens": 126830510080, "source": "fineweb_hq", "phase": 2, "loss": 1.7654722034931183, "ce_loss": 1.7654722034931183, "logit_z_loss": 109.17740821838379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3142533600330353, "tokens_per_second": 8498184.853100803, "eta_seconds": 8609.598935389518, "data_wait_seconds": 1.800060272216797e-05} {"step": 14240, "total_steps": 22439, "tokens": 126919639040, "source": "fineweb_hq", "phase": 2, "loss": 1.7629989683628082, "ce_loss": 1.7629989683628082, "logit_z_loss": 103.23121070861816, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33120304346084595, "tokens_per_second": 10120873.71766437, "eta_seconds": 7220.407678484917, "data_wait_seconds": 2.7000904083251953e-05} {"step": 14250, "total_steps": 22439, "tokens": 127008768000, "source": "fineweb_hq", "phase": 2, "loss": 1.773029625415802, "ce_loss": 1.773029625415802, "logit_z_loss": 107.26554489135742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28386160731315613, "tokens_per_second": 9273338.745775037, "eta_seconds": 7870.704106140136, "data_wait_seconds": 1.704692840576172e-05} {"step": 14260, "total_steps": 22439, "tokens": 127097896960, "source": "fineweb_hq", "phase": 2, "loss": 1.7693215906620026, "ce_loss": 1.7693215906620026, "logit_z_loss": 102.12451553344727, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3392084836959839, "tokens_per_second": 9490379.72703496, "eta_seconds": 7681.312916946412, "data_wait_seconds": 1.6570091247558594e-05} {"step": 14270, "total_steps": 22439, "tokens": 127187025920, "source": "fineweb_hq", "phase": 2, "loss": 1.7643387913703918, "ce_loss": 1.7643387913703918, "logit_z_loss": 105.36952781677246, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35256248712539673, "tokens_per_second": 7899187.491778291, "eta_seconds": 9217.333744740487, "data_wait_seconds": 1.7523765563964844e-05} {"step": 14280, "total_steps": 22439, "tokens": 127276154880, "source": "fineweb_hq", "phase": 2, "loss": 1.7418715357780457, "ce_loss": 1.7418715357780457, "logit_z_loss": 102.43122863769531, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30978506803512573, "tokens_per_second": 9570265.827593572, "eta_seconds": 7598.568292045594, "data_wait_seconds": 2.1457672119140625e-05} {"step": 14290, "total_steps": 22439, "tokens": 127365283840, "source": "fineweb_hq", "phase": 2, "loss": 1.76570525765419, "ce_loss": 1.76570525765419, "logit_z_loss": 99.55355072021484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37096402049064636, "tokens_per_second": 9474761.013227826, "eta_seconds": 7665.754249906539, "data_wait_seconds": 1.9609928131103516e-05} {"step": 14300, "total_steps": 22439, "tokens": 127454412800, "source": "fineweb_hq", "phase": 2, "loss": 1.7570269703865051, "ce_loss": 1.7570269703865051, "logit_z_loss": 106.82740211486816, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35797712206840515, "tokens_per_second": 9699633.007936656, "eta_seconds": 7478.8458990812305, "data_wait_seconds": 1.8417835235595703e-05} {"step": 14310, "total_steps": 22439, "tokens": 127543541760, "source": "fineweb_hq", "phase": 2, "loss": 1.7452943623065948, "ce_loss": 1.7452943623065948, "logit_z_loss": 107.98658561706543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2925049662590027, "tokens_per_second": 10466645.202674279, "eta_seconds": 6922.26880543232, "data_wait_seconds": 1.9788742065429688e-05} {"step": 14320, "total_steps": 22439, "tokens": 127632670720, "source": "fineweb_hq", "phase": 2, "loss": 1.8167584836483002, "ce_loss": 1.8167584836483002, "logit_z_loss": 109.77354431152344, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30572274327278137, "tokens_per_second": 8089513.42520524, "eta_seconds": 8945.383834648133, "data_wait_seconds": 1.7344951629638672e-05} {"step": 14330, "total_steps": 22439, "tokens": 127721799680, "source": "fineweb_hq", "phase": 2, "loss": 1.8132677674293518, "ce_loss": 1.8132677674293518, "logit_z_loss": 103.17983818054199, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29820945858955383, "tokens_per_second": 7836999.542942752, "eta_seconds": 9222.237830686568, "data_wait_seconds": 0.3064226508140564} {"step": 14340, "total_steps": 22439, "tokens": 127810928640, "source": "fineweb_hq", "phase": 2, "loss": 1.9364085495471954, "ce_loss": 1.9364085495471954, "logit_z_loss": 97.53886413574219, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31525662541389465, "tokens_per_second": 8928766.722423956, "eta_seconds": 8084.604173016548, "data_wait_seconds": 1.811981201171875e-05} {"step": 14350, "total_steps": 22439, "tokens": 127900057600, "source": "fineweb_hq", "phase": 2, "loss": 1.9651338458061218, "ce_loss": 1.9651338458061218, "logit_z_loss": 99.82736206054688, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3000941872596741, "tokens_per_second": 9138545.724081712, "eta_seconds": 7889.265745425224, "data_wait_seconds": 1.4543533325195312e-05} {"step": 14360, "total_steps": 22439, "tokens": 127989186560, "source": "fineweb_hq", "phase": 2, "loss": 1.9373458921909332, "ce_loss": 1.9373458921909332, "logit_z_loss": 95.55550765991211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2861834764480591, "tokens_per_second": 9883638.354610926, "eta_seconds": 7285.5040017127985, "data_wait_seconds": 1.7583370208740234e-05} {"step": 14370, "total_steps": 22439, "tokens": 128078315520, "source": "fineweb_hq", "phase": 2, "loss": 1.968666136264801, "ce_loss": 1.968666136264801, "logit_z_loss": 98.99707984924316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3095116913318634, "tokens_per_second": 8996156.536518047, "eta_seconds": 7994.320411396026, "data_wait_seconds": 1.9729137420654297e-05} {"step": 14380, "total_steps": 22439, "tokens": 128167444480, "source": "fineweb_hq", "phase": 2, "loss": 1.954698532819748, "ce_loss": 1.954698532819748, "logit_z_loss": 99.08691596984863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2888941466808319, "tokens_per_second": 9787020.564145619, "eta_seconds": 7339.213031506539, "data_wait_seconds": 1.823902130126953e-05} {"step": 14390, "total_steps": 22439, "tokens": 128256573440, "source": "fineweb_hq", "phase": 2, "loss": 1.9571335911750793, "ce_loss": 1.9571335911750793, "logit_z_loss": 99.22920799255371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33190181851387024, "tokens_per_second": 9616139.526304865, "eta_seconds": 7460.363871359825, "data_wait_seconds": 1.6987323760986328e-05} {"step": 14400, "total_steps": 22439, "tokens": 128345702400, "source": "fineweb_hq", "phase": 2, "loss": 1.9464922845363617, "ce_loss": 1.9464922845363617, "logit_z_loss": 98.68599128723145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28488999605178833, "tokens_per_second": 8731085.8763933, "eta_seconds": 8206.398603606223, "data_wait_seconds": 1.728534698486328e-05} {"step": 14410, "total_steps": 22439, "tokens": 128434831360, "source": "fineweb_hq", "phase": 2, "loss": 1.953110933303833, "ce_loss": 1.953110933303833, "logit_z_loss": 98.56141090393066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3213728070259094, "tokens_per_second": 9808316.861086337, "eta_seconds": 7296.016533470154, "data_wait_seconds": 1.6510486602783203e-05} {"step": 14420, "total_steps": 22439, "tokens": 128523960320, "source": "fineweb_hq", "phase": 2, "loss": 1.9862341284751892, "ce_loss": 1.9862341284751892, "logit_z_loss": 98.39167976379395, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3033931255340576, "tokens_per_second": 8802441.13563876, "eta_seconds": 8119.624081850052, "data_wait_seconds": 1.6450881958007812e-05} {"step": 14430, "total_steps": 22439, "tokens": 128613089280, "source": "fineweb_hq", "phase": 2, "loss": 1.965514898300171, "ce_loss": 1.965514898300171, "logit_z_loss": 94.8831901550293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3366747498512268, "tokens_per_second": 8145674.164883628, "eta_seconds": 8763.348817920685, "data_wait_seconds": 0.356201171875} {"step": 14440, "total_steps": 22439, "tokens": 128702218240, "source": "fineweb_hq", "phase": 2, "loss": 1.9863119721412659, "ce_loss": 1.9863119721412659, "logit_z_loss": 96.20369720458984, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29244324564933777, "tokens_per_second": 9015114.703631872, "eta_seconds": 7908.302605986594, "data_wait_seconds": 1.5914440155029297e-05} {"step": 14450, "total_steps": 22439, "tokens": 128791347200, "source": "fineweb_hq", "phase": 2, "loss": 1.985419601202011, "ce_loss": 1.985419601202011, "logit_z_loss": 93.32354354858398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34377172589302063, "tokens_per_second": 9907653.930732336, "eta_seconds": 7186.880632066726, "data_wait_seconds": 1.6629695892333984e-05} {"step": 14460, "total_steps": 22439, "tokens": 128880476160, "source": "fineweb_hq", "phase": 2, "loss": 1.990942806005478, "ce_loss": 1.990942806005478, "logit_z_loss": 93.44063186645508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30876752734184265, "tokens_per_second": 9494211.316001918, "eta_seconds": 7490.458640217781, "data_wait_seconds": 1.52587890625e-05} {"step": 14470, "total_steps": 22439, "tokens": 128969605120, "source": "fineweb_hq", "phase": 2, "loss": 2.0042534470558167, "ce_loss": 2.0042534470558167, "logit_z_loss": 95.8858757019043, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3530663549900055, "tokens_per_second": 9424120.871998383, "eta_seconds": 7536.710234165192, "data_wait_seconds": 1.8656253814697266e-05} {"step": 14480, "total_steps": 22439, "tokens": 129058734080, "source": "fineweb_hq", "phase": 2, "loss": 1.9996347427368164, "ce_loss": 1.9996347427368164, "logit_z_loss": 91.42489051818848, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34185272455215454, "tokens_per_second": 9451268.043572305, "eta_seconds": 7505.631936049461, "data_wait_seconds": 1.895427703857422e-05} {"step": 14490, "total_steps": 22439, "tokens": 129147863040, "source": "fineweb_hq", "phase": 2, "loss": 2.018041282892227, "ce_loss": 2.018041282892227, "logit_z_loss": 94.1729965209961, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30648544430732727, "tokens_per_second": 9795295.437293623, "eta_seconds": 7232.922249007225, "data_wait_seconds": 1.6748905181884766e-05} {"step": 14500, "total_steps": 22439, "tokens": 129236992000, "source": "fineweb_hq", "phase": 2, "loss": 2.0254344046115875, "ce_loss": 2.0254344046115875, "logit_z_loss": 93.53703689575195, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.343906968832016, "tokens_per_second": 8244190.627185446, "eta_seconds": 8582.950655055047, "data_wait_seconds": 0.44628196954727173} {"step": 14510, "total_steps": 22439, "tokens": 129326120960, "source": "fineweb_hq", "phase": 2, "loss": 1.9988710284233093, "ce_loss": 1.9988710284233093, "logit_z_loss": 90.90956115722656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3538905382156372, "tokens_per_second": 9514928.64232366, "eta_seconds": 7427.312914323807, "data_wait_seconds": 2.002716064453125e-05} {"step": 14520, "total_steps": 22439, "tokens": 129415249920, "source": "fineweb_hq", "phase": 2, "loss": 2.006973147392273, "ce_loss": 2.006973147392273, "logit_z_loss": 92.85754585266113, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28119271993637085, "tokens_per_second": 8250006.095221803, "eta_seconds": 8555.293488192558, "data_wait_seconds": 0.4463387727737427} {"step": 14530, "total_steps": 22439, "tokens": 129504378880, "source": "fineweb_hq", "phase": 2, "loss": 2.029496431350708, "ce_loss": 2.029496431350708, "logit_z_loss": 92.3780574798584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3452734649181366, "tokens_per_second": 11120145.30442723, "eta_seconds": 6339.134294939041, "data_wait_seconds": 1.615285873413086e-05} {"step": 14540, "total_steps": 22439, "tokens": 129593507840, "source": "fineweb_hq", "phase": 2, "loss": 2.017759680747986, "ce_loss": 2.017759680747986, "logit_z_loss": 95.27079391479492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27483126521110535, "tokens_per_second": 8386462.102025887, "eta_seconds": 8394.834990906715, "data_wait_seconds": 1.7881393432617188e-05} {"step": 14550, "total_steps": 22439, "tokens": 129682636800, "source": "fineweb_hq", "phase": 2, "loss": 2.014095962047577, "ce_loss": 2.014095962047577, "logit_z_loss": 95.0628604888916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2911284565925598, "tokens_per_second": 10100289.178783549, "eta_seconds": 6961.566673922539, "data_wait_seconds": 1.6570091247558594e-05} {"step": 14560, "total_steps": 22439, "tokens": 129771765760, "source": "fineweb_hq", "phase": 2, "loss": 2.025866746902466, "ce_loss": 2.025866746902466, "logit_z_loss": 94.97734832763672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29338642954826355, "tokens_per_second": 8721360.810073176, "eta_seconds": 8052.035584044456, "data_wait_seconds": 2.282857894897461e-05} {"step": 14570, "total_steps": 22439, "tokens": 129860894720, "source": "fineweb_hq", "phase": 2, "loss": 2.018725037574768, "ce_loss": 2.018725037574768, "logit_z_loss": 93.41022109985352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2873447835445404, "tokens_per_second": 9191171.755518842, "eta_seconds": 7630.754868865013, "data_wait_seconds": 1.8775463104248047e-05} {"step": 14580, "total_steps": 22439, "tokens": 129950023680, "source": "fineweb_hq", "phase": 2, "loss": 2.0216932892799377, "ce_loss": 2.0216932892799377, "logit_z_loss": 93.0359115600586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3253130316734314, "tokens_per_second": 8542063.50983995, "eta_seconds": 8200.178982901572, "data_wait_seconds": 2.002716064453125e-05} {"step": 14590, "total_steps": 22439, "tokens": 130039152640, "source": "fineweb_hq", "phase": 2, "loss": 2.0136520862579346, "ce_loss": 2.0136520862579346, "logit_z_loss": 92.52362632751465, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3466210961341858, "tokens_per_second": 10062378.2104924, "eta_seconds": 6952.364464998245, "data_wait_seconds": 1.6987323760986328e-05} {"step": 14600, "total_steps": 22439, "tokens": 130128281600, "source": "fineweb_hq", "phase": 2, "loss": 2.0175969004631042, "ce_loss": 2.0175969004631042, "logit_z_loss": 91.14116668701172, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3974837064743042, "tokens_per_second": 7871622.620336766, "eta_seconds": 8875.957996702195, "data_wait_seconds": 1.531839370727539e-05} {"step": 14610, "total_steps": 22439, "tokens": 130217410560, "source": "fineweb_hq", "phase": 2, "loss": 2.009681820869446, "ce_loss": 2.009681820869446, "logit_z_loss": 95.7279281616211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3501010835170746, "tokens_per_second": 9696019.363402875, "eta_seconds": 7196.6711460351935, "data_wait_seconds": 1.6570091247558594e-05} {"step": 14620, "total_steps": 22439, "tokens": 130306539520, "source": "fineweb_hq", "phase": 2, "loss": 2.0226441621780396, "ce_loss": 2.0226441621780396, "logit_z_loss": 96.52519226074219, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2907390296459198, "tokens_per_second": 10127006.906729337, "eta_seconds": 6881.592405915261, "data_wait_seconds": 1.6391277313232422e-05} {"step": 14630, "total_steps": 22439, "tokens": 130395668480, "source": "fineweb_hq", "phase": 2, "loss": 2.0282801389694214, "ce_loss": 2.0282801389694214, "logit_z_loss": 88.7609977722168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3583281338214874, "tokens_per_second": 8049774.557745437, "eta_seconds": 8646.304857945443, "data_wait_seconds": 1.5854835510253906e-05} {"step": 14640, "total_steps": 22439, "tokens": 130484797440, "source": "fineweb_hq", "phase": 2, "loss": 2.0308249592781067, "ce_loss": 2.0308249592781067, "logit_z_loss": 97.61034393310547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3409040868282318, "tokens_per_second": 9567796.601791482, "eta_seconds": 7265.170738577843, "data_wait_seconds": 2.1219253540039062e-05} {"step": 14650, "total_steps": 22439, "tokens": 130573926400, "source": "fineweb_hq", "phase": 2, "loss": 2.0159021615982056, "ce_loss": 2.0159021615982056, "logit_z_loss": 94.69284057617188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34486615657806396, "tokens_per_second": 9100019.100121498, "eta_seconds": 7628.835300254822, "data_wait_seconds": 1.6510486602783203e-05} {"step": 14660, "total_steps": 22439, "tokens": 130663055360, "source": "fineweb_hq", "phase": 2, "loss": 2.0231234431266785, "ce_loss": 2.0231234431266785, "logit_z_loss": 94.13229942321777, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3156530261039734, "tokens_per_second": 8732012.378893808, "eta_seconds": 7940.141971349716, "data_wait_seconds": 1.8596649169921875e-05} {"step": 14670, "total_steps": 22439, "tokens": 130752184320, "source": "fineweb_hq", "phase": 2, "loss": 2.0015601217746735, "ce_loss": 2.0015601217746735, "logit_z_loss": 95.19261360168457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3194103240966797, "tokens_per_second": 9202006.747422982, "eta_seconds": 7524.911785507203, "data_wait_seconds": 1.9431114196777344e-05} {"step": 14680, "total_steps": 22439, "tokens": 130841313280, "source": "fineweb_hq", "phase": 2, "loss": 2.0229064226150513, "ce_loss": 2.0229064226150513, "logit_z_loss": 96.78209686279297, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3409104645252228, "tokens_per_second": 8929273.024315393, "eta_seconds": 7744.769353079796, "data_wait_seconds": 2.008676528930664e-05} {"step": 14690, "total_steps": 22439, "tokens": 130930442240, "source": "fineweb_hq", "phase": 2, "loss": 2.007388472557068, "ce_loss": 2.007388472557068, "logit_z_loss": 96.57562255859375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3150746524333954, "tokens_per_second": 9490804.021344906, "eta_seconds": 7277.15280482769, "data_wait_seconds": 1.6868114471435547e-05} {"step": 14700, "total_steps": 22439, "tokens": 131019571200, "source": "fineweb_hq", "phase": 2, "loss": 1.9859740138053894, "ce_loss": 1.9859740138053894, "logit_z_loss": 93.6133041381836, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26019415259361267, "tokens_per_second": 7654268.194626143, "eta_seconds": 9011.560660028457, "data_wait_seconds": 0.3911500573158264} {"step": 14710, "total_steps": 22439, "tokens": 131108700160, "source": "fineweb_hq", "phase": 2, "loss": 2.0023668110370636, "ce_loss": 2.0023668110370636, "logit_z_loss": 93.29830932617188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3317066729068756, "tokens_per_second": 7978716.336953573, "eta_seconds": 8633.941886734963, "data_wait_seconds": 1.9550323486328125e-05} {"step": 14720, "total_steps": 22439, "tokens": 131197829120, "source": "fineweb_hq", "phase": 2, "loss": 2.0245627760887146, "ce_loss": 2.0245627760887146, "logit_z_loss": 97.94016075134277, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3199366629123688, "tokens_per_second": 8139148.276170227, "eta_seconds": 8452.806348967551, "data_wait_seconds": 1.4781951904296875e-05} {"step": 14730, "total_steps": 22439, "tokens": 131286958080, "source": "fineweb_hq", "phase": 2, "loss": 1.992757797241211, "ce_loss": 1.992757797241211, "logit_z_loss": 94.07791709899902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3509534001350403, "tokens_per_second": 5683218.351762791, "eta_seconds": 12089.895374631882, "data_wait_seconds": 0.6590240597724915} {"step": 14740, "total_steps": 22439, "tokens": 131376087040, "source": "fineweb_hq", "phase": 2, "loss": 1.997624784708023, "ce_loss": 1.997624784708023, "logit_z_loss": 97.01161193847656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2959127724170685, "tokens_per_second": 4609999.424158055, "eta_seconds": 14885.118194246292, "data_wait_seconds": 2.0682811737060547e-05} {"step": 14750, "total_steps": 22439, "tokens": 131465216000, "source": "fineweb_hq", "phase": 2, "loss": 1.9903008043766022, "ce_loss": 1.9903008043766022, "logit_z_loss": 96.33057594299316, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2972245216369629, "tokens_per_second": 7708867.856040379, "eta_seconds": 8889.925034880638, "data_wait_seconds": 0.37001359462738037} {"step": 14760, "total_steps": 22439, "tokens": 131554344960, "source": "fineweb_hq", "phase": 2, "loss": 1.9744104444980621, "ce_loss": 1.9744104444980621, "logit_z_loss": 93.8248462677002, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3159419596195221, "tokens_per_second": 7736637.836832198, "eta_seconds": 8846.495057344437, "data_wait_seconds": 0.2052212357521057} {"step": 14770, "total_steps": 22439, "tokens": 131643473920, "source": "fineweb_hq", "phase": 2, "loss": 1.9987123608589172, "ce_loss": 1.9987123608589172, "logit_z_loss": 94.28643035888672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35357028245925903, "tokens_per_second": 6941625.129056728, "eta_seconds": 9846.829546856881, "data_wait_seconds": 2.187490463256836e-05} {"step": 14780, "total_steps": 22439, "tokens": 131732602880, "source": "fineweb_hq", "phase": 2, "loss": 1.9911671876907349, "ce_loss": 1.9911671876907349, "logit_z_loss": 94.85244369506836, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3268595039844513, "tokens_per_second": 5015001.1575020235, "eta_seconds": 13611.935136222839, "data_wait_seconds": 0.2925923466682434} {"step": 14790, "total_steps": 22439, "tokens": 131821731840, "source": "fineweb_hq", "phase": 2, "loss": 2.0502949357032776, "ce_loss": 2.0502949357032776, "logit_z_loss": 94.62043380737305, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35678213834762573, "tokens_per_second": 3254938.5522792777, "eta_seconds": 20945.01644470692, "data_wait_seconds": 1.5040567517280579} {"step": 14800, "total_steps": 22439, "tokens": 131910860800, "source": "fineweb_hq", "phase": 2, "loss": 1.990913212299347, "ce_loss": 1.990913212299347, "logit_z_loss": 95.4238395690918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32089969515800476, "tokens_per_second": 4930419.261810499, "eta_seconds": 13809.294692516329, "data_wait_seconds": 0.8861611485481262} {"step": 14810, "total_steps": 22439, "tokens": 131999989760, "source": "fineweb_hq", "phase": 2, "loss": 2.0116583704948425, "ce_loss": 2.0116583704948425, "logit_z_loss": 97.08924865722656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31329238414764404, "tokens_per_second": 4648172.030453579, "eta_seconds": 14628.650389552118, "data_wait_seconds": 1.895427703857422e-05} {"step": 14820, "total_steps": 22439, "tokens": 132089118720, "source": "fineweb_hq", "phase": 2, "loss": 1.9801717102527618, "ce_loss": 1.9801717102527618, "logit_z_loss": 97.70342063903809, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3672312796115875, "tokens_per_second": 4965723.987991425, "eta_seconds": 13675.217307329176, "data_wait_seconds": 1.6629695892333984e-05} {"step": 14830, "total_steps": 22439, "tokens": 132178247680, "source": "fineweb_hq", "phase": 2, "loss": 1.946037620306015, "ce_loss": 1.946037620306015, "logit_z_loss": 97.97448539733887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3336810767650604, "tokens_per_second": 4526762.170863139, "eta_seconds": 14981.6188931942, "data_wait_seconds": 1.6037375926971436} {"step": 14840, "total_steps": 22439, "tokens": 132267376640, "source": "fineweb_hq", "phase": 2, "loss": 1.911285012960434, "ce_loss": 1.911285012960434, "logit_z_loss": 100.0053768157959, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2298060953617096, "tokens_per_second": 4502421.975149948, "eta_seconds": 15042.814084911346, "data_wait_seconds": 1.3253012895584106} {"step": 14850, "total_steps": 22439, "tokens": 132356505600, "source": "fineweb_hq", "phase": 2, "loss": 1.8014699816703796, "ce_loss": 1.8014699816703796, "logit_z_loss": 103.60281944274902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28691789507865906, "tokens_per_second": 3530094.2945688292, "eta_seconds": 19160.952116227152, "data_wait_seconds": 2.0623207092285156e-05} {"step": 14860, "total_steps": 22439, "tokens": 132445634560, "source": "fineweb_hq", "phase": 2, "loss": 1.777652084827423, "ce_loss": 1.777652084827423, "logit_z_loss": 103.18743705749512, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.343996524810791, "tokens_per_second": 10865692.774073614, "eta_seconds": 6216.892027831078, "data_wait_seconds": 1.722574234008789e-05} {"step": 14870, "total_steps": 22439, "tokens": 132534763520, "source": "fineweb_hq", "phase": 2, "loss": 1.770420491695404, "ce_loss": 1.770420491695404, "logit_z_loss": 107.87649345397949, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2859829068183899, "tokens_per_second": 9938223.611197984, "eta_seconds": 6788.105446529388, "data_wait_seconds": 1.7344951629638672e-05} {"step": 14880, "total_steps": 22439, "tokens": 132623892480, "source": "fineweb_hq", "phase": 2, "loss": 1.7568184733390808, "ce_loss": 1.7568184733390808, "logit_z_loss": 112.14604568481445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3393523097038269, "tokens_per_second": 9008257.19124822, "eta_seconds": 7478.980610084534, "data_wait_seconds": 2.014636993408203e-05} {"step": 14890, "total_steps": 22439, "tokens": 132713021440, "source": "fineweb_hq", "phase": 2, "loss": 1.7904090285301208, "ce_loss": 1.7904090285301208, "logit_z_loss": 106.83683776855469, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33209770917892456, "tokens_per_second": 8836267.058411025, "eta_seconds": 7614.465640211105, "data_wait_seconds": 1.710653305053711e-05} {"step": 14900, "total_steps": 22439, "tokens": 132802150400, "source": "fineweb_hq", "phase": 2, "loss": 1.7801653444766998, "ce_loss": 1.7801653444766998, "logit_z_loss": 102.11863327026367, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2914285361766815, "tokens_per_second": 10904482.071423063, "eta_seconds": 6162.08294019699, "data_wait_seconds": 2.1159648895263672e-05} {"step": 14910, "total_steps": 22439, "tokens": 132891279360, "source": "fineweb_hq", "phase": 2, "loss": 1.7967010140419006, "ce_loss": 1.7967010140419006, "logit_z_loss": 109.09493827819824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2879788279533386, "tokens_per_second": 9288366.618233236, "eta_seconds": 7224.649579644204, "data_wait_seconds": 1.6868114471435547e-05} {"step": 14920, "total_steps": 22439, "tokens": 132980408320, "source": "fineweb_hq", "phase": 2, "loss": 1.881576418876648, "ce_loss": 1.881576418876648, "logit_z_loss": 99.70975112915039, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27377715706825256, "tokens_per_second": 7507809.902324392, "eta_seconds": 8926.180323672294, "data_wait_seconds": 1.7940998077392578e-05} {"step": 14930, "total_steps": 22439, "tokens": 133069537280, "source": "fineweb_hq", "phase": 2, "loss": 1.9623863697052002, "ce_loss": 1.9623863697052002, "logit_z_loss": 98.6226634979248, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33692246675491333, "tokens_per_second": 9339258.588273184, "eta_seconds": 7166.1937006473545, "data_wait_seconds": 1.8894672393798828e-05} {"step": 14940, "total_steps": 22439, "tokens": 133158666240, "source": "fineweb_hq", "phase": 2, "loss": 1.9842228591442108, "ce_loss": 1.9842228591442108, "logit_z_loss": 97.72370719909668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2697736322879791, "tokens_per_second": 9345707.248631183, "eta_seconds": 7151.712045526505, "data_wait_seconds": 1.609325408935547e-05} {"step": 14950, "total_steps": 22439, "tokens": 133247795200, "source": "fineweb_hq", "phase": 2, "loss": 1.973464161157608, "ce_loss": 1.973464161157608, "logit_z_loss": 99.94586753845215, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3503810167312622, "tokens_per_second": 9950247.252201593, "eta_seconds": 6708.243167448043, "data_wait_seconds": 1.5914440155029297e-05} {"step": 14960, "total_steps": 22439, "tokens": 133336924160, "source": "fineweb_hq", "phase": 2, "loss": 1.9773732423782349, "ce_loss": 1.9773732423782349, "logit_z_loss": 99.12940216064453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30550381541252136, "tokens_per_second": 9896573.087875785, "eta_seconds": 6735.619349455833, "data_wait_seconds": 1.5974044799804688e-05} {"step": 14970, "total_steps": 22439, "tokens": 133426053120, "source": "fineweb_hq", "phase": 2, "loss": 1.9563732743263245, "ce_loss": 1.9563732743263245, "logit_z_loss": 99.05923461914062, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3098500072956085, "tokens_per_second": 9399463.138853442, "eta_seconds": 7082.364092564582, "data_wait_seconds": 1.621246337890625e-05} {"step": 14980, "total_steps": 22439, "tokens": 133515182080, "source": "fineweb_hq", "phase": 2, "loss": 1.9654817581176758, "ce_loss": 1.9654817581176758, "logit_z_loss": 97.2364273071289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29726642370224, "tokens_per_second": 9845042.970548008, "eta_seconds": 6752.768013596535, "data_wait_seconds": 1.704692840576172e-05} {"step": 14990, "total_steps": 22439, "tokens": 133604311040, "source": "fineweb_hq", "phase": 2, "loss": 1.9683942198753357, "ce_loss": 1.9683942198753357, "logit_z_loss": 94.4383373260498, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3753325939178467, "tokens_per_second": 9482877.362268517, "eta_seconds": 7001.267628765106, "data_wait_seconds": 1.800060272216797e-05} {"step": 15000, "total_steps": 22439, "tokens": 133693440000, "source": "fineweb_hq", "phase": 2, "loss": 1.9651334881782532, "ce_loss": 1.9651334881782532, "logit_z_loss": 97.29190826416016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34224140644073486, "tokens_per_second": 10079165.311792014, "eta_seconds": 6578.226598429679, "data_wait_seconds": 3.0219554901123047e-05} {"step": 15010, "total_steps": 22439, "tokens": 133782568960, "source": "fineweb_hq", "phase": 2, "loss": 1.96481454372406, "ce_loss": 1.96481454372406, "logit_z_loss": 98.3708724975586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3519882261753082, "tokens_per_second": 8384729.323641455, "eta_seconds": 7896.963852763176, "data_wait_seconds": 1.901388168334961e-05} {"step": 15020, "total_steps": 22439, "tokens": 133871697920, "source": "fineweb_hq", "phase": 2, "loss": 1.9642924964427948, "ce_loss": 1.9642924964427948, "logit_z_loss": 96.9718189239502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32711952924728394, "tokens_per_second": 9643934.907851387, "eta_seconds": 6856.617766070366, "data_wait_seconds": 1.6570091247558594e-05} {"step": 15030, "total_steps": 22439, "tokens": 133960826880, "source": "fineweb_hq", "phase": 2, "loss": 1.971869945526123, "ce_loss": 1.971869945526123, "logit_z_loss": 97.20499610900879, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3192678987979889, "tokens_per_second": 9781181.853066815, "eta_seconds": 6751.295237731933, "data_wait_seconds": 2.0802021026611328e-05} {"step": 15040, "total_steps": 22439, "tokens": 134049955840, "source": "fineweb_hq", "phase": 2, "loss": 1.9863477945327759, "ce_loss": 1.9863477945327759, "logit_z_loss": 95.92649841308594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28985461592674255, "tokens_per_second": 10029784.882098755, "eta_seconds": 6575.067987918854, "data_wait_seconds": 1.4841556549072266e-05} {"step": 15050, "total_steps": 22439, "tokens": 134139084800, "source": "fineweb_hq", "phase": 2, "loss": 1.9979803264141083, "ce_loss": 1.9979803264141083, "logit_z_loss": 92.20333099365234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3101961612701416, "tokens_per_second": 7947985.38238945, "eta_seconds": 8286.048020410539, "data_wait_seconds": 1.6510486602783203e-05} {"step": 15060, "total_steps": 22439, "tokens": 134228213760, "source": "fineweb_hq", "phase": 2, "loss": 1.9918442368507385, "ce_loss": 1.9918442368507385, "logit_z_loss": 92.96438598632812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33218321204185486, "tokens_per_second": 9261899.442642856, "eta_seconds": 7100.947272348405, "data_wait_seconds": 1.6748905181884766e-05} {"step": 15070, "total_steps": 22439, "tokens": 134317342720, "source": "fineweb_hq", "phase": 2, "loss": 2.002086102962494, "ce_loss": 2.002086102962494, "logit_z_loss": 96.68719673156738, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38251885771751404, "tokens_per_second": 9038695.217318926, "eta_seconds": 7266.439352679254, "data_wait_seconds": 1.800060272216797e-05} {"step": 15080, "total_steps": 22439, "tokens": 134406471680, "source": "fineweb_hq", "phase": 2, "loss": 1.9981001317501068, "ce_loss": 1.9981001317501068, "logit_z_loss": 95.14848899841309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29968729615211487, "tokens_per_second": 10250891.036147837, "eta_seconds": 6398.4683314561835, "data_wait_seconds": 1.901388168334961e-05} {"step": 15090, "total_steps": 22439, "tokens": 134495600640, "source": "fineweb_hq", "phase": 2, "loss": 1.9861737489700317, "ce_loss": 1.9861737489700317, "logit_z_loss": 96.47919845581055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2901403307914734, "tokens_per_second": 10038944.598433036, "eta_seconds": 6524.677177143097, "data_wait_seconds": 2.1338462829589844e-05} {"step": 15100, "total_steps": 22439, "tokens": 134584729600, "source": "fineweb_hq", "phase": 2, "loss": 2.0139720737934113, "ce_loss": 2.0139720737934113, "logit_z_loss": 96.65775299072266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2997150123119354, "tokens_per_second": 9369444.611168653, "eta_seconds": 6981.38966166973, "data_wait_seconds": 1.8477439880371094e-05} {"step": 15110, "total_steps": 22439, "tokens": 134673858560, "source": "fineweb_hq", "phase": 2, "loss": 1.9883741736412048, "ce_loss": 1.9883741736412048, "logit_z_loss": 96.12100791931152, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33194082975387573, "tokens_per_second": 9509688.404714301, "eta_seconds": 6869.05942697525, "data_wait_seconds": 1.6987323760986328e-05} {"step": 15120, "total_steps": 22439, "tokens": 134762987520, "source": "fineweb_hq", "phase": 2, "loss": 1.9901798069477081, "ce_loss": 1.9901798069477081, "logit_z_loss": 93.23965263366699, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3080601692199707, "tokens_per_second": 9770865.101826403, "eta_seconds": 6676.326522183418, "data_wait_seconds": 1.8715858459472656e-05} {"step": 15130, "total_steps": 22439, "tokens": 134852116480, "source": "fineweb_hq", "phase": 2, "loss": 2.002685785293579, "ce_loss": 2.002685785293579, "logit_z_loss": 94.7859058380127, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3235759437084198, "tokens_per_second": 6184731.975924619, "eta_seconds": 10533.092964673042, "data_wait_seconds": 2.7418136596679688e-05} {"step": 15140, "total_steps": 22439, "tokens": 134941245440, "source": "fineweb_hq", "phase": 2, "loss": 2.033832311630249, "ce_loss": 2.033832311630249, "logit_z_loss": 96.70068740844727, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35466286540031433, "tokens_per_second": 9489304.102564324, "eta_seconds": 6855.637378764152, "data_wait_seconds": 1.9848346710205078e-05} {"step": 15150, "total_steps": 22439, "tokens": 135030374400, "source": "fineweb_hq", "phase": 2, "loss": 2.0126533806324005, "ce_loss": 2.0126533806324005, "logit_z_loss": 94.47840309143066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34814414381980896, "tokens_per_second": 8662596.900671793, "eta_seconds": 7499.610069465637, "data_wait_seconds": 2.0742416381835938e-05} {"step": 15160, "total_steps": 22439, "tokens": 135119503360, "source": "fineweb_hq", "phase": 2, "loss": 1.958181917667389, "ce_loss": 1.958181917667389, "logit_z_loss": 99.04524421691895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30609607696533203, "tokens_per_second": 9969397.514630388, "eta_seconds": 6507.611908221245, "data_wait_seconds": 1.5914440155029297e-05} {"step": 15170, "total_steps": 22439, "tokens": 135208632320, "source": "fineweb_hq", "phase": 2, "loss": 1.9792054891586304, "ce_loss": 1.9792054891586304, "logit_z_loss": 98.16515922546387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35058748722076416, "tokens_per_second": 8097626.7930041645, "eta_seconds": 8000.843046998978, "data_wait_seconds": 1.913309097290039e-05} {"step": 15180, "total_steps": 22439, "tokens": 135297761280, "source": "fineweb_hq", "phase": 2, "loss": 1.9661464989185333, "ce_loss": 1.9661464989185333, "logit_z_loss": 94.80651092529297, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31176134943962097, "tokens_per_second": 9651963.513207337, "eta_seconds": 6703.165835165977, "data_wait_seconds": 1.9550323486328125e-05} {"step": 15190, "total_steps": 22439, "tokens": 135386890240, "source": "fineweb_hq", "phase": 2, "loss": 1.9722565710544586, "ce_loss": 1.9722565710544586, "logit_z_loss": 95.70482635498047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33775708079338074, "tokens_per_second": 9773899.194807388, "eta_seconds": 6610.420449018478, "data_wait_seconds": 1.633167266845703e-05} {"step": 15200, "total_steps": 22439, "tokens": 135476019200, "source": "fineweb_hq", "phase": 2, "loss": 1.9643945693969727, "ce_loss": 1.9643945693969727, "logit_z_loss": 97.93184852600098, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32349953055381775, "tokens_per_second": 9566932.02495386, "eta_seconds": 6744.11127576828, "data_wait_seconds": 1.6748905181884766e-05} {"step": 15210, "total_steps": 22439, "tokens": 135565148160, "source": "fineweb_hq", "phase": 2, "loss": 1.9877332746982574, "ce_loss": 1.9877332746982574, "logit_z_loss": 96.31028938293457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3778592050075531, "tokens_per_second": 9481651.688738292, "eta_seconds": 6795.369340610504, "data_wait_seconds": 1.6391277313232422e-05} {"step": 15220, "total_steps": 22439, "tokens": 135654277120, "source": "fineweb_hq", "phase": 2, "loss": 1.9614651203155518, "ce_loss": 1.9614651203155518, "logit_z_loss": 96.65008163452148, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2634678781032562, "tokens_per_second": 10920393.166331343, "eta_seconds": 5891.93037686348, "data_wait_seconds": 1.6689300537109375e-05} {"step": 15230, "total_steps": 22439, "tokens": 135743406080, "source": "fineweb_hq", "phase": 2, "loss": 1.9730437994003296, "ce_loss": 1.9730437994003296, "logit_z_loss": 97.38429641723633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28528928756713867, "tokens_per_second": 9430480.562041918, "eta_seconds": 6813.339664006234, "data_wait_seconds": 1.728534698486328e-05} {"step": 15240, "total_steps": 22439, "tokens": 135832535040, "source": "fineweb_hq", "phase": 2, "loss": 1.9807662963867188, "ce_loss": 1.9807662963867188, "logit_z_loss": 97.58820533752441, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37157151103019714, "tokens_per_second": 9566737.632988479, "eta_seconds": 6706.982125520706, "data_wait_seconds": 1.7464160919189453e-05} {"step": 15250, "total_steps": 22439, "tokens": 135921664000, "source": "fineweb_hq", "phase": 2, "loss": 1.9879266917705536, "ce_loss": 1.9879266917705536, "logit_z_loss": 95.2136344909668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3601488769054413, "tokens_per_second": 8937346.201747883, "eta_seconds": 7169.3328083753595, "data_wait_seconds": 2.0444393157958984e-05} {"step": 15260, "total_steps": 22439, "tokens": 136010792960, "source": "fineweb_hq", "phase": 2, "loss": 1.9831722676753998, "ce_loss": 1.9831722676753998, "logit_z_loss": 101.56446075439453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2576424777507782, "tokens_per_second": 9682428.194696516, "eta_seconds": 6608.433246016502, "data_wait_seconds": 1.8477439880371094e-05} {"step": 15270, "total_steps": 22439, "tokens": 136099921920, "source": "fineweb_hq", "phase": 2, "loss": 1.9696341753005981, "ce_loss": 1.9696341753005981, "logit_z_loss": 96.33381080627441, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2616674304008484, "tokens_per_second": 9469071.041188871, "eta_seconds": 6747.92185485363, "data_wait_seconds": 0.31030774116516113} {"step": 15280, "total_steps": 22439, "tokens": 136189050880, "source": "fineweb_hq", "phase": 2, "loss": 1.984108418226242, "ce_loss": 1.984108418226242, "logit_z_loss": 93.4183292388916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3487296998500824, "tokens_per_second": 9674760.207661849, "eta_seconds": 6595.245886659623, "data_wait_seconds": 1.823902130126953e-05} {"step": 15290, "total_steps": 22439, "tokens": 136278179840, "source": "fineweb_hq", "phase": 2, "loss": 1.9881725311279297, "ce_loss": 1.9881725311279297, "logit_z_loss": 96.78926467895508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2687438130378723, "tokens_per_second": 9958752.543342812, "eta_seconds": 6398.220382189751, "data_wait_seconds": 1.9311904907226562e-05} {"step": 15300, "total_steps": 22439, "tokens": 136367308800, "source": "fineweb_hq", "phase": 2, "loss": 2.005921632051468, "ce_loss": 2.005921632051468, "logit_z_loss": 95.55441093444824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31026598811149597, "tokens_per_second": 9181218.569679365, "eta_seconds": 6930.361592102051, "data_wait_seconds": 1.9788742065429688e-05} {"step": 15310, "total_steps": 22439, "tokens": 136456437760, "source": "fineweb_hq", "phase": 2, "loss": 2.003606289625168, "ce_loss": 2.003606289625168, "logit_z_loss": 95.53251647949219, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34016627073287964, "tokens_per_second": 10131967.142880257, "eta_seconds": 6271.243746447563, "data_wait_seconds": 1.6450881958007812e-05} {"step": 15320, "total_steps": 22439, "tokens": 136545566720, "source": "fineweb_hq", "phase": 2, "loss": 1.9824929535388947, "ce_loss": 1.9824929535388947, "logit_z_loss": 95.60886573791504, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2781437635421753, "tokens_per_second": 9475949.356584698, "eta_seconds": 6695.994695234298, "data_wait_seconds": 1.8537044525146484e-05} {"step": 15330, "total_steps": 22439, "tokens": 136634695680, "source": "fineweb_hq", "phase": 2, "loss": 1.9933734834194183, "ce_loss": 1.9933734834194183, "logit_z_loss": 94.83284759521484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3648971617221832, "tokens_per_second": 9621084.244137263, "eta_seconds": 6585.721115851402, "data_wait_seconds": 1.9848346710205078e-05} {"step": 15340, "total_steps": 22439, "tokens": 136723824640, "source": "fineweb_hq", "phase": 2, "loss": 1.9920944273471832, "ce_loss": 1.9920944273471832, "logit_z_loss": 95.3900089263916, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32344377040863037, "tokens_per_second": 9789844.470675074, "eta_seconds": 6463.090286421776, "data_wait_seconds": 1.8894672393798828e-05} {"step": 15350, "total_steps": 22439, "tokens": 136812953600, "source": "fineweb_hq", "phase": 2, "loss": 1.983405351638794, "ce_loss": 1.983405351638794, "logit_z_loss": 98.97591400146484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3067392110824585, "tokens_per_second": 10638518.155547531, "eta_seconds": 5939.127876663209, "data_wait_seconds": 2.562999725341797e-05} {"step": 15360, "total_steps": 22439, "tokens": 136902082560, "source": "fineweb_hq", "phase": 2, "loss": 2.0066135823726654, "ce_loss": 2.0066135823726654, "logit_z_loss": 91.49168586730957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.325498104095459, "tokens_per_second": 9176073.356260305, "eta_seconds": 6875.968438172341, "data_wait_seconds": 1.6629695892333984e-05} {"step": 15370, "total_steps": 22439, "tokens": 136991211520, "source": "fineweb_hq", "phase": 2, "loss": 1.9938004612922668, "ce_loss": 1.9938004612922668, "logit_z_loss": 95.1066837310791, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33431318402290344, "tokens_per_second": 8950592.463046364, "eta_seconds": 7039.228082847596, "data_wait_seconds": 2.086162567138672e-05} {"step": 15380, "total_steps": 22439, "tokens": 137080340480, "source": "fineweb_hq", "phase": 2, "loss": 2.0021388828754425, "ce_loss": 2.0021388828754425, "logit_z_loss": 98.35233306884766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28457874059677124, "tokens_per_second": 9211036.338521311, "eta_seconds": 6830.516192936897, "data_wait_seconds": 1.5795230865478516e-05} {"step": 15390, "total_steps": 22439, "tokens": 137169469440, "source": "fineweb_hq", "phase": 2, "loss": 1.994642198085785, "ce_loss": 1.994642198085785, "logit_z_loss": 94.88144302368164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34610313177108765, "tokens_per_second": 8743516.917737879, "eta_seconds": 7185.552963995933, "data_wait_seconds": 2.1755695343017578e-05} {"step": 15400, "total_steps": 22439, "tokens": 137258598400, "source": "fineweb_hq", "phase": 2, "loss": 1.9633002281188965, "ce_loss": 1.9633002281188965, "logit_z_loss": 93.9540843963623, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26129770278930664, "tokens_per_second": 9894198.684350954, "eta_seconds": 6340.874783849716, "data_wait_seconds": 2.110004425048828e-05} {"step": 15410, "total_steps": 22439, "tokens": 137347727360, "source": "fineweb_hq", "phase": 2, "loss": 1.9451877176761627, "ce_loss": 1.9451877176761627, "logit_z_loss": 100.09150695800781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3145686686038971, "tokens_per_second": 9170746.499992408, "eta_seconds": 6831.368197131156, "data_wait_seconds": 1.919269561767578e-05} {"step": 15420, "total_steps": 22439, "tokens": 137436856320, "source": "fineweb_hq", "phase": 2, "loss": 1.9386737048625946, "ce_loss": 1.9386737048625946, "logit_z_loss": 100.43298149108887, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3251217007637024, "tokens_per_second": 8951892.389248772, "eta_seconds": 6988.423710179329, "data_wait_seconds": 1.9371509552001953e-05} {"step": 15430, "total_steps": 22439, "tokens": 137525985280, "source": "fineweb_hq", "phase": 2, "loss": 1.942022830247879, "ce_loss": 1.942022830247879, "logit_z_loss": 94.31047821044922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29597756266593933, "tokens_per_second": 9614084.435725974, "eta_seconds": 6497.809383893014, "data_wait_seconds": 1.627206802368164e-05} {"step": 15440, "total_steps": 22439, "tokens": 137615114240, "source": "fineweb_hq", "phase": 2, "loss": 1.941090852022171, "ce_loss": 1.941090852022171, "logit_z_loss": 99.35205841064453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3073543310165405, "tokens_per_second": 8782901.517441815, "eta_seconds": 7102.59120862484, "data_wait_seconds": 1.9729137420654297e-05} {"step": 15450, "total_steps": 22439, "tokens": 137704243200, "source": "fineweb_hq", "phase": 2, "loss": 1.9508624970912933, "ce_loss": 1.9508624970912933, "logit_z_loss": 97.83808898925781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3070363998413086, "tokens_per_second": 9467915.35499761, "eta_seconds": 6579.297322416305, "data_wait_seconds": 1.6868114471435547e-05} {"step": 15460, "total_steps": 22439, "tokens": 137793372160, "source": "fineweb_hq", "phase": 2, "loss": 1.9527799487113953, "ce_loss": 1.9527799487113953, "logit_z_loss": 96.40689659118652, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3091956675052643, "tokens_per_second": 8857959.30262583, "eta_seconds": 7022.283469462394, "data_wait_seconds": 1.9848346710205078e-05} {"step": 15470, "total_steps": 22439, "tokens": 137882501120, "source": "fineweb_hq", "phase": 2, "loss": 1.963731288909912, "ce_loss": 1.963731288909912, "logit_z_loss": 97.49946403503418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.330015629529953, "tokens_per_second": 9161226.980343943, "eta_seconds": 6780.0931422472, "data_wait_seconds": 1.817941665649414e-05} {"step": 15480, "total_steps": 22439, "tokens": 137971630080, "source": "fineweb_hq", "phase": 2, "loss": 2.0055160522460938, "ce_loss": 2.0055160522460938, "logit_z_loss": 94.11755752563477, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3617074191570282, "tokens_per_second": 8845194.256442145, "eta_seconds": 7012.2646790742865, "data_wait_seconds": 1.6033649444580078e-05} {"step": 15490, "total_steps": 22439, "tokens": 138060759040, "source": "fineweb_hq", "phase": 2, "loss": 2.011426120996475, "ce_loss": 2.011426120996475, "logit_z_loss": 92.8381118774414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30682551860809326, "tokens_per_second": 9249202.302625464, "eta_seconds": 6696.330372881889, "data_wait_seconds": 2.1457672119140625e-05} {"step": 15500, "total_steps": 22439, "tokens": 138149888000, "source": "fineweb_hq", "phase": 2, "loss": 2.002528488636017, "ce_loss": 2.002528488636017, "logit_z_loss": 95.2961368560791, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3156168758869171, "tokens_per_second": 10271765.838743746, "eta_seconds": 6021.027573537827, "data_wait_seconds": 2.0325183868408203e-05} {"step": 15510, "total_steps": 22439, "tokens": 138239016960, "source": "fineweb_hq", "phase": 2, "loss": 2.0112174451351166, "ce_loss": 2.0112174451351166, "logit_z_loss": 91.94931602478027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37655434012413025, "tokens_per_second": 9846134.628890408, "eta_seconds": 6272.253905892371, "data_wait_seconds": 1.9371509552001953e-05} {"step": 15520, "total_steps": 22439, "tokens": 138328145920, "source": "fineweb_hq", "phase": 2, "loss": 2.0094380974769592, "ce_loss": 2.0094380974769592, "logit_z_loss": 95.19046211242676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35547980666160583, "tokens_per_second": 10369821.817089906, "eta_seconds": 5946.903284525872, "data_wait_seconds": 1.8358230590820312e-05} {"step": 15530, "total_steps": 22439, "tokens": 138417274880, "source": "fineweb_hq", "phase": 2, "loss": 2.0118134319782257, "ce_loss": 2.0118134319782257, "logit_z_loss": 93.69089889526367, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28320175409317017, "tokens_per_second": 9022640.703093844, "eta_seconds": 6824.964053249359, "data_wait_seconds": 1.8537044525146484e-05} {"step": 15540, "total_steps": 22439, "tokens": 138506403840, "source": "fineweb_hq", "phase": 2, "loss": 2.0036580562591553, "ce_loss": 2.0036580562591553, "logit_z_loss": 91.89732360839844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30063754320144653, "tokens_per_second": 9605696.370903868, "eta_seconds": 6401.417151832581, "data_wait_seconds": 1.5079975128173828e-05} {"step": 15550, "total_steps": 22439, "tokens": 138595532800, "source": "fineweb_hq", "phase": 2, "loss": 2.014085203409195, "ce_loss": 2.014085203409195, "logit_z_loss": 92.1715087890625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36138927936553955, "tokens_per_second": 10665737.292394431, "eta_seconds": 5756.8397627592085, "data_wait_seconds": 1.6987323760986328e-05} {"step": 15560, "total_steps": 22439, "tokens": 138684661760, "source": "fineweb_hq", "phase": 2, "loss": 1.979317158460617, "ce_loss": 1.979317158460617, "logit_z_loss": 90.0765266418457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33961090445518494, "tokens_per_second": 8006526.492156662, "eta_seconds": 7657.729184317589, "data_wait_seconds": 0.37175172567367554} {"step": 15570, "total_steps": 22439, "tokens": 138773790720, "source": "fineweb_hq", "phase": 2, "loss": 1.9877421259880066, "ce_loss": 1.9877421259880066, "logit_z_loss": 93.9422607421875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.4005744159221649, "tokens_per_second": 9366016.914468348, "eta_seconds": 6536.682901930809, "data_wait_seconds": 1.6868114471435547e-05} {"step": 15580, "total_steps": 22439, "tokens": 138862919680, "source": "fineweb_hq", "phase": 2, "loss": 1.9992942214012146, "ce_loss": 1.9992942214012146, "logit_z_loss": 93.76961708068848, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3364638388156891, "tokens_per_second": 8549238.488090377, "eta_seconds": 7150.760123157502, "data_wait_seconds": 1.0644428730010986} {"step": 15590, "total_steps": 22439, "tokens": 138952048640, "source": "fineweb_hq", "phase": 2, "loss": 1.9632686376571655, "ce_loss": 1.9632686376571655, "logit_z_loss": 94.85371398925781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36759138107299805, "tokens_per_second": 10089928.875264853, "eta_seconds": 6050.035184454918, "data_wait_seconds": 1.4007091522216797e-05} {"step": 15600, "total_steps": 22439, "tokens": 139041177600, "source": "fineweb_hq", "phase": 2, "loss": 1.9489801824092865, "ce_loss": 1.9489801824092865, "logit_z_loss": 92.61198616027832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3677422106266022, "tokens_per_second": 10127681.819301777, "eta_seconds": 6018.681948304176, "data_wait_seconds": 1.728534698486328e-05} {"step": 15610, "total_steps": 22439, "tokens": 139130306560, "source": "fineweb_hq", "phase": 2, "loss": 1.9700801372528076, "ce_loss": 1.9700801372528076, "logit_z_loss": 92.28558349609375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38250669836997986, "tokens_per_second": 9998061.906608611, "eta_seconds": 6087.796550226211, "data_wait_seconds": 1.6868114471435547e-05} {"step": 15620, "total_steps": 22439, "tokens": 139219435520, "source": "fineweb_hq", "phase": 2, "loss": 1.9590018689632416, "ce_loss": 1.9590018689632416, "logit_z_loss": 96.51373672485352, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3058857321739197, "tokens_per_second": 8780638.066195253, "eta_seconds": 6921.710855841637, "data_wait_seconds": 1.8417835235595703e-05} {"step": 15630, "total_steps": 22439, "tokens": 139308564480, "source": "fineweb_hq", "phase": 2, "loss": 1.964502066373825, "ce_loss": 1.964502066373825, "logit_z_loss": 97.73604774475098, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35552912950515747, "tokens_per_second": 9133728.718734633, "eta_seconds": 6644.373917031287, "data_wait_seconds": 1.531839370727539e-05} {"step": 15640, "total_steps": 22439, "tokens": 139397693440, "source": "fineweb_hq", "phase": 2, "loss": 1.9582312405109406, "ce_loss": 1.9582312405109406, "logit_z_loss": 90.65789794921875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37138915061950684, "tokens_per_second": 6813831.45300161, "eta_seconds": 8893.495579099656, "data_wait_seconds": 1.7583370208740234e-05} {"step": 15650, "total_steps": 22439, "tokens": 139486822400, "source": "fineweb_hq", "phase": 2, "loss": 1.958782583475113, "ce_loss": 1.958782583475113, "logit_z_loss": 96.19264221191406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28676900267601013, "tokens_per_second": 8080488.39249329, "eta_seconds": 7488.365554761886, "data_wait_seconds": 1.8298625946044922e-05} {"step": 15660, "total_steps": 22439, "tokens": 139575951360, "source": "fineweb_hq", "phase": 2, "loss": 1.9551066160202026, "ce_loss": 1.9551066160202026, "logit_z_loss": 96.72973251342773, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.318793386220932, "tokens_per_second": 7008018.004955744, "eta_seconds": 8621.627675795555, "data_wait_seconds": 1.9550323486328125e-05} {"step": 15670, "total_steps": 22439, "tokens": 139665080320, "source": "fineweb_hq", "phase": 2, "loss": 1.9521700739860535, "ce_loss": 1.9521700739860535, "logit_z_loss": 100.4210090637207, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34433844685554504, "tokens_per_second": 8235735.33411302, "eta_seconds": 7325.562390780449, "data_wait_seconds": 1.627206802368164e-05} {"step": 15680, "total_steps": 22439, "tokens": 139754209280, "source": "fineweb_hq", "phase": 2, "loss": 1.9328944981098175, "ce_loss": 1.9328944981098175, "logit_z_loss": 95.45381736755371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36013466119766235, "tokens_per_second": 7441089.676350955, "eta_seconds": 8095.892763590813, "data_wait_seconds": 1.9669532775878906e-05} {"step": 15690, "total_steps": 22439, "tokens": 139843338240, "source": "fineweb_hq", "phase": 2, "loss": 1.9430266916751862, "ce_loss": 1.9430266916751862, "logit_z_loss": 97.46020889282227, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30501630902290344, "tokens_per_second": 8144423.580749908, "eta_seconds": 7385.806313681603, "data_wait_seconds": 1.710653305053711e-05} {"step": 15700, "total_steps": 22439, "tokens": 139932467200, "source": "fineweb_hq", "phase": 2, "loss": 1.958585411310196, "ce_loss": 1.958585411310196, "logit_z_loss": 99.64162635803223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31466829776763916, "tokens_per_second": 9750129.929777011, "eta_seconds": 6160.328793215752, "data_wait_seconds": 1.5139579772949219e-05} {"step": 15710, "total_steps": 22439, "tokens": 140021596160, "source": "fineweb_hq", "phase": 2, "loss": 1.9614531099796295, "ce_loss": 1.9614531099796295, "logit_z_loss": 100.9375114440918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27846989035606384, "tokens_per_second": 13700384.03562216, "eta_seconds": 4377.605549454689, "data_wait_seconds": 2.086162567138672e-05} {"step": 15720, "total_steps": 22439, "tokens": 140110725120, "source": "fineweb_hq", "phase": 2, "loss": 1.9907223582267761, "ce_loss": 1.9907223582267761, "logit_z_loss": 98.34610366821289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37572014331817627, "tokens_per_second": 9449022.237455666, "eta_seconds": 6337.771964025498, "data_wait_seconds": 1.919269561767578e-05} {"step": 15730, "total_steps": 22439, "tokens": 140199854080, "source": "fineweb_hq", "phase": 2, "loss": 1.9677022695541382, "ce_loss": 1.9677022695541382, "logit_z_loss": 94.77296447753906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31679514050483704, "tokens_per_second": 7147193.1775060445, "eta_seconds": 8366.447887849807, "data_wait_seconds": 2.3365020751953125e-05} {"step": 15740, "total_steps": 22439, "tokens": 140288983040, "source": "fineweb_hq", "phase": 2, "loss": 1.9660618007183075, "ce_loss": 1.9660618007183075, "logit_z_loss": 98.02240180969238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33555346727371216, "tokens_per_second": 4080926.142478741, "eta_seconds": 14630.867655873299, "data_wait_seconds": 1.6178926229476929} {"step": 15750, "total_steps": 22439, "tokens": 140378112000, "source": "fineweb_hq", "phase": 2, "loss": 1.9856494069099426, "ce_loss": 1.9856494069099426, "logit_z_loss": 96.54900360107422, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3741990923881531, "tokens_per_second": 3054270.357118723, "eta_seconds": 19519.673890376092, "data_wait_seconds": 2.881001055240631} {"step": 15760, "total_steps": 22439, "tokens": 140467240960, "source": "fineweb_hq", "phase": 2, "loss": 1.9556606113910675, "ce_loss": 1.9556606113910675, "logit_z_loss": 95.12099647521973, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3220710754394531, "tokens_per_second": 3998836.0726117967, "eta_seconds": 14886.639837956429, "data_wait_seconds": 2.3603439331054688e-05} {"step": 15770, "total_steps": 22439, "tokens": 140556369920, "source": "fineweb_hq", "phase": 2, "loss": 1.9696218073368073, "ce_loss": 1.9696218073368073, "logit_z_loss": 94.32963180541992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3454981744289398, "tokens_per_second": 4864379.335336821, "eta_seconds": 12219.463024234772, "data_wait_seconds": 0.8537062406539917} {"step": 15780, "total_steps": 22439, "tokens": 140645498880, "source": "fineweb_hq", "phase": 2, "loss": 1.970868468284607, "ce_loss": 1.970868468284607, "logit_z_loss": 98.18014717102051, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32500916719436646, "tokens_per_second": 2615537.0721423863, "eta_seconds": 22691.696897029877, "data_wait_seconds": 3.447858989238739} {"step": 15790, "total_steps": 22439, "tokens": 140734627840, "source": "fineweb_hq", "phase": 2, "loss": 1.977977305650711, "ce_loss": 1.977977305650711, "logit_z_loss": 98.37209701538086, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29960253834724426, "tokens_per_second": 4062299.908812367, "eta_seconds": 14588.249719190597, "data_wait_seconds": 2.2590160369873047e-05} {"step": 15800, "total_steps": 22439, "tokens": 140823756800, "source": "fineweb_hq", "phase": 2, "loss": 2.01907080411911, "ce_loss": 2.01907080411911, "logit_z_loss": 98.76775360107422, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32354649901390076, "tokens_per_second": 4244328.179431354, "eta_seconds": 13941.597831845284, "data_wait_seconds": 0.5465136766433716} {"step": 15810, "total_steps": 22439, "tokens": 140912885760, "source": "fineweb_hq", "phase": 2, "loss": 2.019794464111328, "ce_loss": 2.019794464111328, "logit_z_loss": 97.78037071228027, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3051099479198456, "tokens_per_second": 2928888.046354712, "eta_seconds": 20172.702626013757, "data_wait_seconds": 1.4393450021743774} {"step": 15820, "total_steps": 22439, "tokens": 141002014720, "source": "fineweb_hq", "phase": 2, "loss": 2.0055278539657593, "ce_loss": 2.0055278539657593, "logit_z_loss": 91.63825798034668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2967091500759125, "tokens_per_second": 6890631.545034749, "eta_seconds": 8561.54595386982, "data_wait_seconds": 1.8894672393798828e-05} {"step": 15830, "total_steps": 22439, "tokens": 141091143680, "source": "fineweb_hq", "phase": 2, "loss": 2.0218284726142883, "ce_loss": 2.0218284726142883, "logit_z_loss": 98.34530830383301, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29253897070884705, "tokens_per_second": 8623577.044532117, "eta_seconds": 6830.730375552177, "data_wait_seconds": 1.9550323486328125e-05} {"step": 15840, "total_steps": 22439, "tokens": 141180272640, "source": "fineweb_hq", "phase": 2, "loss": 2.0036264955997467, "ce_loss": 2.0036264955997467, "logit_z_loss": 98.10124588012695, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30686312913894653, "tokens_per_second": 9143832.543540856, "eta_seconds": 6432.335721802712, "data_wait_seconds": 2.1457672119140625e-05} {"step": 15850, "total_steps": 22439, "tokens": 141269401600, "source": "fineweb_hq", "phase": 2, "loss": 1.9987738132476807, "ce_loss": 1.9987738132476807, "logit_z_loss": 97.79511642456055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37507325410842896, "tokens_per_second": 7944697.040277061, "eta_seconds": 7391.9837907314295, "data_wait_seconds": 1.919269561767578e-05} {"step": 15860, "total_steps": 22439, "tokens": 141358530560, "source": "fineweb_hq", "phase": 2, "loss": 2.0233300030231476, "ce_loss": 2.0233300030231476, "logit_z_loss": 96.32109260559082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32896363735198975, "tokens_per_second": 9084356.982994063, "eta_seconds": 6454.825904989243, "data_wait_seconds": 1.919269561767578e-05} {"step": 15870, "total_steps": 22439, "tokens": 141447659520, "source": "fineweb_hq", "phase": 2, "loss": 1.9816043674945831, "ce_loss": 1.9816043674945831, "logit_z_loss": 98.73630905151367, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.4116891324520111, "tokens_per_second": 8294243.293895547, "eta_seconds": 7058.969908332825, "data_wait_seconds": 2.104043960571289e-05} {"step": 15880, "total_steps": 22439, "tokens": 141536788480, "source": "fineweb_hq", "phase": 2, "loss": 1.9829021990299225, "ce_loss": 1.9829021990299225, "logit_z_loss": 96.77873992919922, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32161858677864075, "tokens_per_second": 7932158.5237696795, "eta_seconds": 7369.959222173691, "data_wait_seconds": 1.7702579498291016e-05} {"step": 15890, "total_steps": 22439, "tokens": 141625917440, "source": "fineweb_hq", "phase": 2, "loss": 1.9814168810844421, "ce_loss": 1.9814168810844421, "logit_z_loss": 96.33778381347656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3394659161567688, "tokens_per_second": 10028656.158561777, "eta_seconds": 5820.3766268491745, "data_wait_seconds": 1.7642974853515625e-05} {"step": 15900, "total_steps": 22439, "tokens": 141715046400, "source": "fineweb_hq", "phase": 2, "loss": 1.9660309255123138, "ce_loss": 1.9660309255123138, "logit_z_loss": 100.77571105957031, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.26182788610458374, "tokens_per_second": 10125757.184235558, "eta_seconds": 5755.759878849983, "data_wait_seconds": 1.901388168334961e-05} {"step": 15910, "total_steps": 22439, "tokens": 141804175360, "source": "fineweb_hq", "phase": 2, "loss": 1.9778859317302704, "ce_loss": 1.9778859317302704, "logit_z_loss": 98.99795913696289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36102619767189026, "tokens_per_second": 9504557.11893766, "eta_seconds": 6122.568075060845, "data_wait_seconds": 1.52587890625e-05} {"step": 15920, "total_steps": 22439, "tokens": 141893304320, "source": "fineweb_hq", "phase": 2, "loss": 1.9691802263259888, "ce_loss": 1.9691802263259888, "logit_z_loss": 98.61417007446289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27601268887519836, "tokens_per_second": 9567199.632861733, "eta_seconds": 6073.163648056984, "data_wait_seconds": 1.71661376953125e-05} {"step": 15930, "total_steps": 22439, "tokens": 141982433280, "source": "fineweb_hq", "phase": 2, "loss": 1.9782888889312744, "ce_loss": 1.9782888889312744, "logit_z_loss": 93.59878730773926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3651025891304016, "tokens_per_second": 9736500.861681242, "eta_seconds": 5958.407531428336, "data_wait_seconds": 1.7762184143066406e-05} {"step": 15940, "total_steps": 22439, "tokens": 142071562240, "source": "fineweb_hq", "phase": 2, "loss": 1.98126682639122, "ce_loss": 1.98126682639122, "logit_z_loss": 100.44800567626953, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39573365449905396, "tokens_per_second": 8508156.390196498, "eta_seconds": 6808.162479329109, "data_wait_seconds": 1.5139579772949219e-05} {"step": 15950, "total_steps": 22439, "tokens": 142160691200, "source": "fineweb_hq", "phase": 2, "loss": 1.9635927975177765, "ce_loss": 1.9635927975177765, "logit_z_loss": 95.79397773742676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3016270101070404, "tokens_per_second": 10170455.373394703, "eta_seconds": 5686.64627301693, "data_wait_seconds": 1.71661376953125e-05} {"step": 15960, "total_steps": 22439, "tokens": 142249820160, "source": "fineweb_hq", "phase": 2, "loss": 1.9698392450809479, "ce_loss": 1.9698392450809479, "logit_z_loss": 97.45829963684082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27317503094673157, "tokens_per_second": 8012733.3326511625, "eta_seconds": 7206.860728621483, "data_wait_seconds": 2.008676528930664e-05} {"step": 15970, "total_steps": 22439, "tokens": 142338949120, "source": "fineweb_hq", "phase": 2, "loss": 1.9652096033096313, "ce_loss": 1.9652096033096313, "logit_z_loss": 96.08089447021484, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3423030376434326, "tokens_per_second": 10458575.073420614, "eta_seconds": 5512.942615914345, "data_wait_seconds": 1.6510486602783203e-05} {"step": 15980, "total_steps": 22439, "tokens": 142428078080, "source": "fineweb_hq", "phase": 2, "loss": 1.975413054227829, "ce_loss": 1.975413054227829, "logit_z_loss": 100.15649604797363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35021451115608215, "tokens_per_second": 8772619.762284536, "eta_seconds": 6562.280917668342, "data_wait_seconds": 1.6987323760986328e-05} {"step": 15990, "total_steps": 22439, "tokens": 142517207040, "source": "fineweb_hq", "phase": 2, "loss": 1.9603497087955475, "ce_loss": 1.9603497087955475, "logit_z_loss": 99.03256797790527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35149919986724854, "tokens_per_second": 9277883.238537928, "eta_seconds": 6195.299598646164, "data_wait_seconds": 1.9073486328125e-05} {"step": 16000, "total_steps": 22439, "tokens": 142606336000, "source": "fineweb_hq", "phase": 2, "loss": 1.9670139849185944, "ce_loss": 1.9670139849185944, "logit_z_loss": 92.56525993347168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3359661400318146, "tokens_per_second": 9121332.036711661, "eta_seconds": 6291.85924961567, "data_wait_seconds": 2.0563602447509766e-05} {"step": 16010, "total_steps": 22439, "tokens": 142695464960, "source": "fineweb_hq", "phase": 2, "loss": 1.9725160598754883, "ce_loss": 1.9725160598754883, "logit_z_loss": 97.46603202819824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3194923400878906, "tokens_per_second": 9861530.19172603, "eta_seconds": 5810.559545016289, "data_wait_seconds": 1.728534698486328e-05} {"step": 16020, "total_steps": 22439, "tokens": 142784593920, "source": "fineweb_hq", "phase": 2, "loss": 1.9583339393138885, "ce_loss": 1.9583339393138885, "logit_z_loss": 98.18105125427246, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3382602334022522, "tokens_per_second": 9949240.949417362, "eta_seconds": 5750.376306581497, "data_wait_seconds": 1.4066696166992188e-05} {"step": 16030, "total_steps": 22439, "tokens": 142873722880, "source": "fineweb_hq", "phase": 2, "loss": 1.964569091796875, "ce_loss": 1.964569091796875, "logit_z_loss": 99.59696197509766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27669814229011536, "tokens_per_second": 9441169.241045909, "eta_seconds": 6050.389417409898, "data_wait_seconds": 1.800060272216797e-05} {"step": 16040, "total_steps": 22439, "tokens": 142962851840, "source": "fineweb_hq", "phase": 2, "loss": 1.9559879302978516, "ce_loss": 1.9559879302978516, "logit_z_loss": 97.22983932495117, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3010951578617096, "tokens_per_second": 8812037.626760893, "eta_seconds": 6472.239897251129, "data_wait_seconds": 1.728534698486328e-05} {"step": 16050, "total_steps": 22439, "tokens": 143051980800, "source": "fineweb_hq", "phase": 2, "loss": 1.9489713311195374, "ce_loss": 1.9489713311195374, "logit_z_loss": 95.10434150695801, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33608749508857727, "tokens_per_second": 10654536.801421776, "eta_seconds": 5344.623948025703, "data_wait_seconds": 1.6391277313232422e-05} {"step": 16060, "total_steps": 22439, "tokens": 143141109760, "source": "fineweb_hq", "phase": 2, "loss": 1.960136502981186, "ce_loss": 1.960136502981186, "logit_z_loss": 96.93188667297363, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3043741285800934, "tokens_per_second": 10419853.337128514, "eta_seconds": 5456.445666217804, "data_wait_seconds": 1.6450881958007812e-05} {"step": 16070, "total_steps": 22439, "tokens": 143230238720, "source": "fineweb_hq", "phase": 2, "loss": 1.963560312986374, "ce_loss": 1.963560312986374, "logit_z_loss": 99.21430778503418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3413815498352051, "tokens_per_second": 7856667.417035095, "eta_seconds": 7225.230700349808, "data_wait_seconds": 0.287339448928833} {"step": 16080, "total_steps": 22439, "tokens": 143319367680, "source": "fineweb_hq", "phase": 2, "loss": 1.9826286137104034, "ce_loss": 1.9826286137104034, "logit_z_loss": 96.5697193145752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32558396458625793, "tokens_per_second": 9292754.9132182, "eta_seconds": 6099.063861393929, "data_wait_seconds": 1.5497207641601562e-05} {"step": 16090, "total_steps": 22439, "tokens": 143408496640, "source": "fineweb_hq", "phase": 2, "loss": 1.9744236469268799, "ce_loss": 1.9744236469268799, "logit_z_loss": 94.18740653991699, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3377709984779358, "tokens_per_second": 8037545.763814196, "eta_seconds": 7040.454681921005, "data_wait_seconds": 0.43762946128845215} {"step": 16100, "total_steps": 22439, "tokens": 143497625600, "source": "fineweb_hq", "phase": 2, "loss": 1.96378892660141, "ce_loss": 1.96378892660141, "logit_z_loss": 96.06398010253906, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31062570214271545, "tokens_per_second": 8393535.127589904, "eta_seconds": 6731.23384666443, "data_wait_seconds": 1.9431114196777344e-05} {"step": 16110, "total_steps": 22439, "tokens": 143586754560, "source": "fineweb_hq", "phase": 2, "loss": 1.9813160002231598, "ce_loss": 1.9813160002231598, "logit_z_loss": 96.65253639221191, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34996360540390015, "tokens_per_second": 10704442.800568515, "eta_seconds": 5269.748256397247, "data_wait_seconds": 1.7404556274414062e-05} {"step": 16120, "total_steps": 22439, "tokens": 143675883520, "source": "fineweb_hq", "phase": 2, "loss": 1.9589739441871643, "ce_loss": 1.9589739441871643, "logit_z_loss": 93.43876075744629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34391000866889954, "tokens_per_second": 8679327.27540914, "eta_seconds": 6489.050134515762, "data_wait_seconds": 1.5616416931152344e-05} {"step": 16130, "total_steps": 22439, "tokens": 143765012480, "source": "fineweb_hq", "phase": 2, "loss": 1.9703777432441711, "ce_loss": 1.9703777432441711, "logit_z_loss": 101.71489143371582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.40992262959480286, "tokens_per_second": 8315858.457632002, "eta_seconds": 6761.955022501946, "data_wait_seconds": 0.4729095697402954} {"step": 16140, "total_steps": 22439, "tokens": 143854141440, "source": "fineweb_hq", "phase": 2, "loss": 1.9811080992221832, "ce_loss": 1.9811080992221832, "logit_z_loss": 96.52978515625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31930011510849, "tokens_per_second": 9469974.154836986, "eta_seconds": 5928.456718683244, "data_wait_seconds": 1.7762184143066406e-05} {"step": 16150, "total_steps": 22439, "tokens": 143943270400, "source": "fineweb_hq", "phase": 2, "loss": 1.9834398329257965, "ce_loss": 1.9834398329257965, "logit_z_loss": 93.72845840454102, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3394157588481903, "tokens_per_second": 8430496.50739745, "eta_seconds": 6648.861415791511, "data_wait_seconds": 1.9609928131103516e-05} {"step": 16160, "total_steps": 22439, "tokens": 144032399360, "source": "fineweb_hq", "phase": 2, "loss": 1.959976702928543, "ce_loss": 1.959976702928543, "logit_z_loss": 100.5189323425293, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3410434126853943, "tokens_per_second": 9852962.592764808, "eta_seconds": 5679.923521184922, "data_wait_seconds": 1.9371509552001953e-05} {"step": 16170, "total_steps": 22439, "tokens": 144121528320, "source": "fineweb_hq", "phase": 2, "loss": 1.9717624485492706, "ce_loss": 1.9717624485492706, "logit_z_loss": 97.14109802246094, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.41742855310440063, "tokens_per_second": 9996187.553369727, "eta_seconds": 5589.62551729679, "data_wait_seconds": 1.7464160919189453e-05} {"step": 16180, "total_steps": 22439, "tokens": 144210657280, "source": "fineweb_hq", "phase": 2, "loss": 1.986955463886261, "ce_loss": 1.986955463886261, "logit_z_loss": 96.69881439208984, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32303327322006226, "tokens_per_second": 8000120.214404292, "eta_seconds": 6973.122224283219, "data_wait_seconds": 1.8417835235595703e-05} {"step": 16190, "total_steps": 22439, "tokens": 144299786240, "source": "fineweb_hq", "phase": 2, "loss": 1.9746825397014618, "ce_loss": 1.9746825397014618, "logit_z_loss": 92.80248260498047, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3055233061313629, "tokens_per_second": 9700169.850267682, "eta_seconds": 5741.8259642601015, "data_wait_seconds": 1.5676021575927734e-05} {"step": 16200, "total_steps": 22439, "tokens": 144388915200, "source": "fineweb_hq", "phase": 2, "loss": 1.9591716825962067, "ce_loss": 1.9591716825962067, "logit_z_loss": 98.53276443481445, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3100130558013916, "tokens_per_second": 6433972.61059546, "eta_seconds": 8642.803056454659, "data_wait_seconds": 0.42663657665252686} {"step": 16210, "total_steps": 22439, "tokens": 144478044160, "source": "fineweb_hq", "phase": 2, "loss": 1.9757117629051208, "ce_loss": 1.9757117629051208, "logit_z_loss": 98.87535285949707, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29508453607559204, "tokens_per_second": 10192268.02771816, "eta_seconds": 5447.112363314629, "data_wait_seconds": 2.276897430419922e-05} {"step": 16220, "total_steps": 22439, "tokens": 144567173120, "source": "fineweb_hq", "phase": 2, "loss": 1.9493500888347626, "ce_loss": 1.9493500888347626, "logit_z_loss": 98.28400039672852, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33570125699043274, "tokens_per_second": 8431155.134158777, "eta_seconds": 6574.342345976829, "data_wait_seconds": 1.6748905181884766e-05} {"step": 16230, "total_steps": 22439, "tokens": 144656302080, "source": "fineweb_hq", "phase": 2, "loss": 1.902295857667923, "ce_loss": 1.902295857667923, "logit_z_loss": 102.46158981323242, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3144000470638275, "tokens_per_second": 8388830.876509672, "eta_seconds": 6596.887227630616, "data_wait_seconds": 1.5616416931152344e-05} {"step": 16240, "total_steps": 22439, "tokens": 144745431040, "source": "fineweb_hq", "phase": 2, "loss": 1.9361056983470917, "ce_loss": 1.9361056983470917, "logit_z_loss": 102.44702529907227, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27857887744903564, "tokens_per_second": 10762432.487382784, "eta_seconds": 5133.694670677185, "data_wait_seconds": 2.1278858184814453e-05} {"step": 16250, "total_steps": 22439, "tokens": 144834560000, "source": "fineweb_hq", "phase": 2, "loss": 1.8915178775787354, "ce_loss": 1.8915178775787354, "logit_z_loss": 99.94204330444336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3329089283943176, "tokens_per_second": 10096188.204478772, "eta_seconds": 5463.637585473061, "data_wait_seconds": 1.633167266845703e-05} {"step": 16260, "total_steps": 22439, "tokens": 144923688960, "source": "fineweb_hq", "phase": 2, "loss": 1.898954600095749, "ce_loss": 1.898954600095749, "logit_z_loss": 97.51546669006348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30240294337272644, "tokens_per_second": 9285632.207651794, "eta_seconds": 5930.967666220665, "data_wait_seconds": 1.9490718841552734e-05} {"step": 16270, "total_steps": 22439, "tokens": 145012817920, "source": "fineweb_hq", "phase": 2, "loss": 1.9257816970348358, "ce_loss": 1.9257816970348358, "logit_z_loss": 101.26702880859375, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.375156044960022, "tokens_per_second": 8909282.84031692, "eta_seconds": 6171.501837968827, "data_wait_seconds": 1.7702579498291016e-05} {"step": 16280, "total_steps": 22439, "tokens": 145101946880, "source": "fineweb_hq", "phase": 2, "loss": 1.8877388834953308, "ce_loss": 1.8877388834953308, "logit_z_loss": 104.07142066955566, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29568299651145935, "tokens_per_second": 8671083.943240594, "eta_seconds": 6330.7571260213845, "data_wait_seconds": 1.9609928131103516e-05} {"step": 16290, "total_steps": 22439, "tokens": 145191075840, "source": "fineweb_hq", "phase": 2, "loss": 1.9041382372379303, "ce_loss": 1.9041382372379303, "logit_z_loss": 98.99339485168457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34654420614242554, "tokens_per_second": 9301049.401548501, "eta_seconds": 5892.388604545594, "data_wait_seconds": 1.71661376953125e-05} {"step": 16300, "total_steps": 22439, "tokens": 145280204800, "source": "fineweb_hq", "phase": 2, "loss": 1.912500649690628, "ce_loss": 1.912500649690628, "logit_z_loss": 102.47244834899902, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31123867630958557, "tokens_per_second": 9488835.143997382, "eta_seconds": 5766.384146595001, "data_wait_seconds": 2.2232532501220703e-05} {"step": 16310, "total_steps": 22439, "tokens": 145369333760, "source": "fineweb_hq", "phase": 2, "loss": 1.9213680028915405, "ce_loss": 1.9213680028915405, "logit_z_loss": 100.6303825378418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.42064034938812256, "tokens_per_second": 9876320.582135348, "eta_seconds": 5531.122560238839, "data_wait_seconds": 2.2411346435546875e-05} {"step": 16320, "total_steps": 22439, "tokens": 145458462720, "source": "fineweb_hq", "phase": 2, "loss": 1.9128331542015076, "ce_loss": 1.9128331542015076, "logit_z_loss": 101.17716598510742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29042696952819824, "tokens_per_second": 10255943.014943209, "eta_seconds": 5317.698289132119, "data_wait_seconds": 1.5139579772949219e-05} {"step": 16330, "total_steps": 22439, "tokens": 145547591680, "source": "fineweb_hq", "phase": 2, "loss": 1.9099583327770233, "ce_loss": 1.9099583327770233, "logit_z_loss": 101.03081893920898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.331276535987854, "tokens_per_second": 8006015.690447785, "eta_seconds": 6800.996122074127, "data_wait_seconds": 1.7523765563964844e-05} {"step": 16340, "total_steps": 22439, "tokens": 145636720640, "source": "fineweb_hq", "phase": 2, "loss": 1.9044282734394073, "ce_loss": 1.9044282734394073, "logit_z_loss": 99.76290130615234, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3122824430465698, "tokens_per_second": 8949200.363993019, "eta_seconds": 6074.258089327813, "data_wait_seconds": 1.7344951629638672e-05} {"step": 16350, "total_steps": 22439, "tokens": 145725849600, "source": "fineweb_hq", "phase": 2, "loss": 1.932779312133789, "ce_loss": 1.932779312133789, "logit_z_loss": 99.33279228210449, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32489120960235596, "tokens_per_second": 8069585.748891428, "eta_seconds": 6725.3295810699465, "data_wait_seconds": 1.6868114471435547e-05} {"step": 16360, "total_steps": 22439, "tokens": 145814978560, "source": "fineweb_hq", "phase": 2, "loss": 1.9177760779857635, "ce_loss": 1.9177760779857635, "logit_z_loss": 104.32372856140137, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2974756956100464, "tokens_per_second": 10402273.573641686, "eta_seconds": 5208.62044248581, "data_wait_seconds": 2.1696090698242188e-05} {"step": 16370, "total_steps": 22439, "tokens": 145904107520, "source": "fineweb_hq", "phase": 2, "loss": 1.9085413813591003, "ce_loss": 1.9085413813591003, "logit_z_loss": 96.69764709472656, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33614301681518555, "tokens_per_second": 9859701.995124929, "eta_seconds": 5486.206971645355, "data_wait_seconds": 1.722574234008789e-05} {"step": 16380, "total_steps": 22439, "tokens": 145993236480, "source": "fineweb_hq", "phase": 2, "loss": 1.9393459260463715, "ce_loss": 1.9393459260463715, "logit_z_loss": 98.27197074890137, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27982640266418457, "tokens_per_second": 9519777.794337438, "eta_seconds": 5672.741321349144, "data_wait_seconds": 1.7821788787841797e-05} {"step": 16390, "total_steps": 22439, "tokens": 146082365440, "source": "fineweb_hq", "phase": 2, "loss": 1.9327854812145233, "ce_loss": 1.9327854812145233, "logit_z_loss": 97.06391143798828, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29284337162971497, "tokens_per_second": 9481252.258823402, "eta_seconds": 5686.391041207314, "data_wait_seconds": 1.6927719116210938e-05} {"step": 16400, "total_steps": 22439, "tokens": 146171494400, "source": "fineweb_hq", "phase": 2, "loss": 1.9311096966266632, "ce_loss": 1.9311096966266632, "logit_z_loss": 103.02865219116211, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3076727092266083, "tokens_per_second": 8919878.90404831, "eta_seconds": 6034.272384524345, "data_wait_seconds": 1.9729137420654297e-05} {"step": 16410, "total_steps": 22439, "tokens": 146260623360, "source": "fineweb_hq", "phase": 2, "loss": 1.9199030697345734, "ce_loss": 1.9199030697345734, "logit_z_loss": 100.93799018859863, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32719796895980835, "tokens_per_second": 8956555.294993462, "eta_seconds": 5999.611258363724, "data_wait_seconds": 1.9788742065429688e-05} {"step": 16420, "total_steps": 22439, "tokens": 146349752320, "source": "fineweb_hq", "phase": 2, "loss": 1.9293272495269775, "ce_loss": 1.9293272495269775, "logit_z_loss": 100.76023864746094, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29420459270477295, "tokens_per_second": 8668164.578141147, "eta_seconds": 6188.93660132885, "data_wait_seconds": 1.8715858459472656e-05} {"step": 16430, "total_steps": 22439, "tokens": 146438881280, "source": "fineweb_hq", "phase": 2, "loss": 1.9299930334091187, "ce_loss": 1.9299930334091187, "logit_z_loss": 102.25050735473633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3248676657676697, "tokens_per_second": 8006144.627864593, "eta_seconds": 6689.560900211334, "data_wait_seconds": 2.1636486053466797e-05} {"step": 16440, "total_steps": 22439, "tokens": 146528010240, "source": "fineweb_hq", "phase": 2, "loss": 1.9223964214324951, "ce_loss": 1.9223964214324951, "logit_z_loss": 96.43156242370605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3261771500110626, "tokens_per_second": 9546806.974885777, "eta_seconds": 5600.664520049095, "data_wait_seconds": 2.4378299713134766e-05} {"step": 16450, "total_steps": 22439, "tokens": 146617139200, "source": "fineweb_hq", "phase": 2, "loss": 1.911606341600418, "ce_loss": 1.911606341600418, "logit_z_loss": 95.18816757202148, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3202759623527527, "tokens_per_second": 9564995.802679727, "eta_seconds": 5580.696034288406, "data_wait_seconds": 1.9252300262451172e-05} {"step": 16460, "total_steps": 22439, "tokens": 146706268160, "source": "fineweb_hq", "phase": 2, "loss": 1.9323704540729523, "ce_loss": 1.9323704540729523, "logit_z_loss": 102.04239273071289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3245953619480133, "tokens_per_second": 8894695.006740011, "eta_seconds": 5991.234679055214, "data_wait_seconds": 1.7404556274414062e-05} {"step": 16470, "total_steps": 22439, "tokens": 146795397120, "source": "fineweb_hq", "phase": 2, "loss": 1.8788004517555237, "ce_loss": 1.8788004517555237, "logit_z_loss": 99.04718017578125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3311658501625061, "tokens_per_second": 8723648.967509203, "eta_seconds": 6098.4888803005215, "data_wait_seconds": 1.811981201171875e-05} {"step": 16480, "total_steps": 22439, "tokens": 146884526080, "source": "fineweb_hq", "phase": 2, "loss": 1.8689435720443726, "ce_loss": 1.8689435720443726, "logit_z_loss": 103.63969039916992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3060179650783539, "tokens_per_second": 8286039.155666793, "eta_seconds": 6409.811282110214, "data_wait_seconds": 1.7523765563964844e-05} {"step": 16490, "total_steps": 22439, "tokens": 146973655040, "source": "fineweb_hq", "phase": 2, "loss": 1.7708542048931122, "ce_loss": 1.7708542048931122, "logit_z_loss": 107.03211402893066, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32496756315231323, "tokens_per_second": 8821740.416227508, "eta_seconds": 6010.471381187438, "data_wait_seconds": 1.7642974853515625e-05} {"step": 16500, "total_steps": 22439, "tokens": 147062784000, "source": "fineweb_hq", "phase": 2, "loss": 1.7833401560783386, "ce_loss": 1.7833401560783386, "logit_z_loss": 107.40299034118652, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31135180592536926, "tokens_per_second": 10114536.955746777, "eta_seconds": 5233.426856374741, "data_wait_seconds": 1.9490718841552734e-05} {"step": 16510, "total_steps": 22439, "tokens": 147151912960, "source": "fineweb_hq", "phase": 2, "loss": 1.7668522894382477, "ce_loss": 1.7668522894382477, "logit_z_loss": 108.05639266967773, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32679274678230286, "tokens_per_second": 9742285.320143126, "eta_seconds": 5424.246842241288, "data_wait_seconds": 1.9073486328125e-05} {"step": 16520, "total_steps": 22439, "tokens": 147241041920, "source": "fineweb_hq", "phase": 2, "loss": 1.7662643194198608, "ce_loss": 1.7662643194198608, "logit_z_loss": 108.27824211120605, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3147267997264862, "tokens_per_second": 8671717.335017353, "eta_seconds": 6083.6198166847225, "data_wait_seconds": 1.7940998077392578e-05} {"step": 16530, "total_steps": 22439, "tokens": 147330170880, "source": "fineweb_hq", "phase": 2, "loss": 1.7549050450325012, "ce_loss": 1.7549050450325012, "logit_z_loss": 107.92672729492188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.287421852350235, "tokens_per_second": 10213719.009385468, "eta_seconds": 5156.427586817741, "data_wait_seconds": 1.7881393432617188e-05} {"step": 16540, "total_steps": 22439, "tokens": 147419299840, "source": "fineweb_hq", "phase": 2, "loss": 1.7563019394874573, "ce_loss": 1.7563019394874573, "logit_z_loss": 105.58090782165527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33193284273147583, "tokens_per_second": 8755949.97887895, "eta_seconds": 6004.736622619629, "data_wait_seconds": 1.7642974853515625e-05} {"step": 16550, "total_steps": 22439, "tokens": 147508428800, "source": "fineweb_hq", "phase": 2, "loss": 1.7576781809329987, "ce_loss": 1.7576781809329987, "logit_z_loss": 113.76957702636719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29487329721450806, "tokens_per_second": 8995449.107029866, "eta_seconds": 5834.955422401427, "data_wait_seconds": 1.8835067749023438e-05} {"step": 16560, "total_steps": 22439, "tokens": 147597557760, "source": "fineweb_hq", "phase": 2, "loss": 1.7694433331489563, "ce_loss": 1.7694433331489563, "logit_z_loss": 110.58122825622559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2916402518749237, "tokens_per_second": 8531140.878124278, "eta_seconds": 6142.0759934186935, "data_wait_seconds": 1.8596649169921875e-05} {"step": 16570, "total_steps": 22439, "tokens": 147686686720, "source": "fineweb_hq", "phase": 2, "loss": 1.742748111486435, "ce_loss": 1.742748111486435, "logit_z_loss": 110.54549980163574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33382201194763184, "tokens_per_second": 9893623.131864037, "eta_seconds": 5287.2224792480465, "data_wait_seconds": 1.7464160919189453e-05} {"step": 16580, "total_steps": 22439, "tokens": 147775815680, "source": "fineweb_hq", "phase": 2, "loss": 1.741137832403183, "ce_loss": 1.741137832403183, "logit_z_loss": 111.33784484863281, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2972422242164612, "tokens_per_second": 9122804.031899484, "eta_seconds": 5724.189348077774, "data_wait_seconds": 1.996755599975586e-05} {"step": 16590, "total_steps": 22439, "tokens": 147864944640, "source": "fineweb_hq", "phase": 2, "loss": 1.7561090588569641, "ce_loss": 1.7561090588569641, "logit_z_loss": 110.81533241271973, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3737914562225342, "tokens_per_second": 8088696.891970941, "eta_seconds": 6444.984822678566, "data_wait_seconds": 1.8298625946044922e-05} {"step": 16600, "total_steps": 22439, "tokens": 147954073600, "source": "fineweb_hq", "phase": 2, "loss": 1.8120877146720886, "ce_loss": 1.8120877146720886, "logit_z_loss": 112.66720008850098, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2672203481197357, "tokens_per_second": 10342107.117341656, "eta_seconds": 5032.088640499115, "data_wait_seconds": 1.6808509826660156e-05} {"step": 16610, "total_steps": 22439, "tokens": 148043202560, "source": "fineweb_hq", "phase": 2, "loss": 1.8357249796390533, "ce_loss": 1.8357249796390533, "logit_z_loss": 106.10577392578125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3979584276676178, "tokens_per_second": 8756759.307728846, "eta_seconds": 5932.933515501022, "data_wait_seconds": 0.3558501601219177} {"step": 16620, "total_steps": 22439, "tokens": 148132331520, "source": "fineweb_hq", "phase": 2, "loss": 1.9264231026172638, "ce_loss": 1.9264231026172638, "logit_z_loss": 103.16790390014648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3827071189880371, "tokens_per_second": 8200038.94431872, "eta_seconds": 6324.865305662155, "data_wait_seconds": 1.9729137420654297e-05} {"step": 16630, "total_steps": 22439, "tokens": 148221460480, "source": "fineweb_hq", "phase": 2, "loss": 2.024326115846634, "ce_loss": 2.024326115846634, "logit_z_loss": 96.69404792785645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3170076310634613, "tokens_per_second": 9703118.382680163, "eta_seconds": 5335.914787602424, "data_wait_seconds": 1.8835067749023438e-05} {"step": 16640, "total_steps": 22439, "tokens": 148310589440, "source": "fineweb_hq", "phase": 2, "loss": 2.0227736830711365, "ce_loss": 2.0227736830711365, "logit_z_loss": 92.67868423461914, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28708913922309875, "tokens_per_second": 7974665.339664076, "eta_seconds": 6481.260554838181, "data_wait_seconds": 1.800060272216797e-05} {"step": 16650, "total_steps": 22439, "tokens": 148399718400, "source": "fineweb_hq", "phase": 2, "loss": 2.0241881012916565, "ce_loss": 2.0241881012916565, "logit_z_loss": 88.35152244567871, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36076390743255615, "tokens_per_second": 9603581.842633579, "eta_seconds": 5372.657388615608, "data_wait_seconds": 1.7642974853515625e-05} {"step": 16660, "total_steps": 22439, "tokens": 148488847360, "source": "fineweb_hq", "phase": 2, "loss": 2.012213349342346, "ce_loss": 2.012213349342346, "logit_z_loss": 91.06356430053711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3734607994556427, "tokens_per_second": 9819170.15018131, "eta_seconds": 5245.619048881531, "data_wait_seconds": 1.5974044799804688e-05} {"step": 16670, "total_steps": 22439, "tokens": 148577976320, "source": "fineweb_hq", "phase": 2, "loss": 2.0431371331214905, "ce_loss": 2.0431371331214905, "logit_z_loss": 101.31609344482422, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34765446186065674, "tokens_per_second": 8593924.487318618, "eta_seconds": 5983.121808886528, "data_wait_seconds": 1.627206802368164e-05} {"step": 16680, "total_steps": 22439, "tokens": 148667105280, "source": "fineweb_hq", "phase": 2, "loss": 2.0344021916389465, "ce_loss": 2.0344021916389465, "logit_z_loss": 93.10364532470703, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37273842096328735, "tokens_per_second": 10291915.12291885, "eta_seconds": 4987.348559617996, "data_wait_seconds": 1.7523765563964844e-05} {"step": 16690, "total_steps": 22439, "tokens": 148756234240, "source": "fineweb_hq", "phase": 2, "loss": 2.024651885032654, "ce_loss": 2.024651885032654, "logit_z_loss": 97.16495895385742, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31006062030792236, "tokens_per_second": 9245149.740606342, "eta_seconds": 5542.391474628449, "data_wait_seconds": 2.372264862060547e-05} {"step": 16700, "total_steps": 22439, "tokens": 148845363200, "source": "fineweb_hq", "phase": 2, "loss": 2.001502603292465, "ce_loss": 2.001502603292465, "logit_z_loss": 95.47774124145508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33020544052124023, "tokens_per_second": 9527209.268083705, "eta_seconds": 5368.949994134903, "data_wait_seconds": 1.7881393432617188e-05} {"step": 16710, "total_steps": 22439, "tokens": 148934492160, "source": "fineweb_hq", "phase": 2, "loss": 2.0243745148181915, "ce_loss": 2.0243745148181915, "logit_z_loss": 97.07783889770508, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2913619577884674, "tokens_per_second": 9661418.791955773, "eta_seconds": 5285.143133068084, "data_wait_seconds": 2.3663043975830078e-05} {"step": 16720, "total_steps": 22439, "tokens": 149023621120, "source": "fineweb_hq", "phase": 2, "loss": 2.0013867020606995, "ce_loss": 2.0013867020606995, "logit_z_loss": 93.31584739685059, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3218032121658325, "tokens_per_second": 8411025.394778641, "eta_seconds": 6060.2423404455185, "data_wait_seconds": 0.3964102864265442} {"step": 16730, "total_steps": 22439, "tokens": 149112750080, "source": "fineweb_hq", "phase": 2, "loss": 2.0147348642349243, "ce_loss": 2.0147348642349243, "logit_z_loss": 100.18355941772461, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31655168533325195, "tokens_per_second": 10027198.207709646, "eta_seconds": 5074.570404410362, "data_wait_seconds": 1.633167266845703e-05} {"step": 16740, "total_steps": 22439, "tokens": 149201879040, "source": "fineweb_hq", "phase": 2, "loss": 1.9906752109527588, "ce_loss": 1.9906752109527588, "logit_z_loss": 92.80105209350586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34423816204071045, "tokens_per_second": 8276873.088376821, "eta_seconds": 6136.930427908897, "data_wait_seconds": 1.627206802368164e-05} {"step": 16750, "total_steps": 22439, "tokens": 149291008000, "source": "fineweb_hq", "phase": 2, "loss": 1.973581850528717, "ce_loss": 1.973581850528717, "logit_z_loss": 95.65765571594238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3162451684474945, "tokens_per_second": 9294949.691584881, "eta_seconds": 5455.162967681885, "data_wait_seconds": 1.901388168334961e-05} {"step": 16760, "total_steps": 22439, "tokens": 149380136960, "source": "fineweb_hq", "phase": 2, "loss": 1.9564520418643951, "ce_loss": 1.9564520418643951, "logit_z_loss": 94.85568618774414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28284165263175964, "tokens_per_second": 8596086.759148143, "eta_seconds": 5888.2998511075975, "data_wait_seconds": 1.5676021575927734e-05} {"step": 16770, "total_steps": 22439, "tokens": 149469265920, "source": "fineweb_hq", "phase": 2, "loss": 1.9589620530605316, "ce_loss": 1.9589620530605316, "logit_z_loss": 100.51226615905762, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2686396539211273, "tokens_per_second": 9599255.502420818, "eta_seconds": 5263.6589797258375, "data_wait_seconds": 1.4841556549072266e-05} {"step": 16780, "total_steps": 22439, "tokens": 149558394880, "source": "fineweb_hq", "phase": 2, "loss": 1.9590276181697845, "ce_loss": 1.9590276181697845, "logit_z_loss": 99.03732872009277, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.40547725558280945, "tokens_per_second": 8731383.812275762, "eta_seconds": 5776.64200181961, "data_wait_seconds": 1.8715858459472656e-05} {"step": 16790, "total_steps": 22439, "tokens": 149647523840, "source": "fineweb_hq", "phase": 2, "loss": 1.9622130692005157, "ce_loss": 1.9622130692005157, "logit_z_loss": 95.1389331817627, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3351176679134369, "tokens_per_second": 9975386.234097635, "eta_seconds": 5047.318301510811, "data_wait_seconds": 1.817941665649414e-05} {"step": 16800, "total_steps": 22439, "tokens": 149736652800, "source": "fineweb_hq", "phase": 2, "loss": 1.9707068502902985, "ce_loss": 1.9707068502902985, "logit_z_loss": 98.09927940368652, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34405696392059326, "tokens_per_second": 9317773.917394195, "eta_seconds": 5393.972958517075, "data_wait_seconds": 1.710653305053711e-05} {"step": 16810, "total_steps": 22439, "tokens": 149825781760, "source": "fineweb_hq", "phase": 2, "loss": 1.9541586935520172, "ce_loss": 1.9541586935520172, "logit_z_loss": 98.5846004486084, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28659123182296753, "tokens_per_second": 8534279.4027241, "eta_seconds": 5878.726160287858, "data_wait_seconds": 1.633167266845703e-05} {"step": 16820, "total_steps": 22439, "tokens": 149914910720, "source": "fineweb_hq", "phase": 2, "loss": 1.9634315967559814, "ce_loss": 1.9634315967559814, "logit_z_loss": 93.82682800292969, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.41686952114105225, "tokens_per_second": 9413364.071894748, "eta_seconds": 5320.261942648888, "data_wait_seconds": 1.913309097290039e-05} {"step": 16830, "total_steps": 22439, "tokens": 150004039680, "source": "fineweb_hq", "phase": 2, "loss": 1.963296115398407, "ce_loss": 1.963296115398407, "logit_z_loss": 97.69516563415527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35026371479034424, "tokens_per_second": 8977475.198527308, "eta_seconds": 5568.651826763154, "data_wait_seconds": 1.901388168334961e-05} {"step": 16840, "total_steps": 22439, "tokens": 150093168640, "source": "fineweb_hq", "phase": 2, "loss": 1.9710581004619598, "ce_loss": 1.9710581004619598, "logit_z_loss": 96.1806526184082, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.424866646528244, "tokens_per_second": 9561853.007915411, "eta_seconds": 5218.999357414245, "data_wait_seconds": 1.823902130126953e-05} {"step": 16850, "total_steps": 22439, "tokens": 150182297600, "source": "fineweb_hq", "phase": 2, "loss": 1.9659022092819214, "ce_loss": 1.9659022092819214, "logit_z_loss": 98.31914710998535, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3781052529811859, "tokens_per_second": 8729413.652768785, "eta_seconds": 5706.474423766137, "data_wait_seconds": 2.390146255493164e-05} {"step": 16860, "total_steps": 22439, "tokens": 150271426560, "source": "fineweb_hq", "phase": 2, "loss": 1.965960144996643, "ce_loss": 1.965960144996643, "logit_z_loss": 100.53889846801758, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3190922141075134, "tokens_per_second": 8444754.85799451, "eta_seconds": 5888.275932240486, "data_wait_seconds": 0.26230770349502563} {"step": 16870, "total_steps": 22439, "tokens": 150360555520, "source": "fineweb_hq", "phase": 2, "loss": 1.9358614683151245, "ce_loss": 1.9358614683151245, "logit_z_loss": 96.61796188354492, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3862033486366272, "tokens_per_second": 7863294.949800851, "eta_seconds": 6312.356097650528, "data_wait_seconds": 1.722574234008789e-05} {"step": 16880, "total_steps": 22439, "tokens": 150449684480, "source": "fineweb_hq", "phase": 2, "loss": 1.9429166615009308, "ce_loss": 1.9429166615009308, "logit_z_loss": 100.67015266418457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34849950671195984, "tokens_per_second": 8814050.45752603, "eta_seconds": 5621.341641139984, "data_wait_seconds": 1.6450881958007812e-05} {"step": 16890, "total_steps": 22439, "tokens": 150538813440, "source": "fineweb_hq", "phase": 2, "loss": 1.9193769991397858, "ce_loss": 1.9193769991397858, "logit_z_loss": 98.58979034423828, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3115874230861664, "tokens_per_second": 8914963.25436716, "eta_seconds": 5547.713265085221, "data_wait_seconds": 1.8358230590820312e-05} {"step": 16900, "total_steps": 22439, "tokens": 150627942400, "source": "fineweb_hq", "phase": 2, "loss": 1.916527509689331, "ce_loss": 1.916527509689331, "logit_z_loss": 94.24143981933594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31859683990478516, "tokens_per_second": 9729369.388620628, "eta_seconds": 5074.175824975968, "data_wait_seconds": 1.7762184143066406e-05} {"step": 16910, "total_steps": 22439, "tokens": 150717071360, "source": "fineweb_hq", "phase": 2, "loss": 1.9228845238685608, "ce_loss": 1.9228845238685608, "logit_z_loss": 99.35866737365723, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3280104994773865, "tokens_per_second": 9293303.568389967, "eta_seconds": 5302.678603076934, "data_wait_seconds": 1.7702579498291016e-05} {"step": 16920, "total_steps": 22439, "tokens": 150806200320, "source": "fineweb_hq", "phase": 2, "loss": 1.9527130126953125, "ce_loss": 1.9527130126953125, "logit_z_loss": 101.68807792663574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32506996393203735, "tokens_per_second": 8547990.709371, "eta_seconds": 5754.600665402412, "data_wait_seconds": 1.8358230590820312e-05} {"step": 16930, "total_steps": 22439, "tokens": 150895329280, "source": "fineweb_hq", "phase": 2, "loss": 1.947354644536972, "ce_loss": 1.947354644536972, "logit_z_loss": 95.7802848815918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38333860039711, "tokens_per_second": 9849230.186951866, "eta_seconds": 4985.2773396492, "data_wait_seconds": 1.7404556274414062e-05} {"step": 16940, "total_steps": 22439, "tokens": 150984458240, "source": "fineweb_hq", "phase": 2, "loss": 1.9640107452869415, "ce_loss": 1.9640107452869415, "logit_z_loss": 95.51826667785645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35809701681137085, "tokens_per_second": 7959376.067223664, "eta_seconds": 6157.770997381211, "data_wait_seconds": 0.3128628730773926} {"step": 16950, "total_steps": 22439, "tokens": 151073587200, "source": "fineweb_hq", "phase": 2, "loss": 2.005416452884674, "ce_loss": 2.005416452884674, "logit_z_loss": 98.13551330566406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30399778485298157, "tokens_per_second": 9928878.541372519, "eta_seconds": 4927.332522010804, "data_wait_seconds": 2.5510787963867188e-05} {"step": 16960, "total_steps": 22439, "tokens": 151162716160, "source": "fineweb_hq", "phase": 2, "loss": 2.032431483268738, "ce_loss": 2.032431483268738, "logit_z_loss": 92.26342582702637, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3556276559829712, "tokens_per_second": 8638024.490938686, "eta_seconds": 5653.347849988937, "data_wait_seconds": 1.901388168334961e-05} {"step": 16970, "total_steps": 22439, "tokens": 151251845120, "source": "fineweb_hq", "phase": 2, "loss": 2.033568561077118, "ce_loss": 2.033568561077118, "logit_z_loss": 99.50997734069824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.312089741230011, "tokens_per_second": 8259597.749577601, "eta_seconds": 5901.574108314514, "data_wait_seconds": 2.008676528930664e-05} {"step": 16980, "total_steps": 22439, "tokens": 151340974080, "source": "fineweb_hq", "phase": 2, "loss": 2.014992892742157, "ce_loss": 2.014992892742157, "logit_z_loss": 93.56798362731934, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2977713644504547, "tokens_per_second": 9894068.013920838, "eta_seconds": 4917.643500685692, "data_wait_seconds": 1.7821788787841797e-05} {"step": 16990, "total_steps": 22439, "tokens": 151430103040, "source": "fineweb_hq", "phase": 2, "loss": 2.00809109210968, "ce_loss": 2.00809109210968, "logit_z_loss": 90.74345397949219, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30289721488952637, "tokens_per_second": 9654090.67703918, "eta_seconds": 5030.6519721746445, "data_wait_seconds": 1.7642974853515625e-05} {"step": 17000, "total_steps": 22439, "tokens": 151519232000, "source": "fineweb_hq", "phase": 2, "loss": 2.0175185203552246, "ce_loss": 2.0175185203552246, "logit_z_loss": 98.02590370178223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32726359367370605, "tokens_per_second": 9154187.161780445, "eta_seconds": 5295.635809850693, "data_wait_seconds": 1.722574234008789e-05} {"step": 17010, "total_steps": 22439, "tokens": 151608360960, "source": "fineweb_hq", "phase": 2, "loss": 2.009717643260956, "ce_loss": 2.009717643260956, "logit_z_loss": 97.28563690185547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3314872086048126, "tokens_per_second": 8925885.904298743, "eta_seconds": 5421.099138259889, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17020, "total_steps": 22439, "tokens": 151697489920, "source": "fineweb_hq", "phase": 2, "loss": 2.000354588031769, "ce_loss": 2.000354588031769, "logit_z_loss": 96.15951728820801, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2667737305164337, "tokens_per_second": 9170982.72785461, "eta_seconds": 5266.500314879418, "data_wait_seconds": 1.6033649444580078e-05} {"step": 17030, "total_steps": 22439, "tokens": 151786618880, "source": "fineweb_hq", "phase": 2, "loss": 2.0006309151649475, "ce_loss": 2.0006309151649475, "logit_z_loss": 93.28091812133789, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3369215726852417, "tokens_per_second": 8666800.67018655, "eta_seconds": 5562.589506626129, "data_wait_seconds": 2.1219253540039062e-05} {"step": 17040, "total_steps": 22439, "tokens": 151875747840, "source": "fineweb_hq", "phase": 2, "loss": 2.0214617252349854, "ce_loss": 2.0214617252349854, "logit_z_loss": 92.9416618347168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3244994282722473, "tokens_per_second": 9620898.787347727, "eta_seconds": 5001.687115478516, "data_wait_seconds": 1.7762184143066406e-05} {"step": 17050, "total_steps": 22439, "tokens": 151964876800, "source": "fineweb_hq", "phase": 2, "loss": 2.01143416762352, "ce_loss": 2.01143416762352, "logit_z_loss": 97.79770851135254, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3597185015678406, "tokens_per_second": 9332383.140462626, "eta_seconds": 5146.766460514069, "data_wait_seconds": 1.6629695892333984e-05} {"step": 17060, "total_steps": 22439, "tokens": 152054005760, "source": "fineweb_hq", "phase": 2, "loss": 2.0131903290748596, "ce_loss": 2.0131903290748596, "logit_z_loss": 93.9728775024414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33632123470306396, "tokens_per_second": 8831626.499972453, "eta_seconds": 5428.498089694977, "data_wait_seconds": 1.5914440155029297e-05} {"step": 17070, "total_steps": 22439, "tokens": 152143134720, "source": "fineweb_hq", "phase": 2, "loss": 1.9885449707508087, "ce_loss": 1.9885449707508087, "logit_z_loss": 92.77738952636719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30299249291419983, "tokens_per_second": 9569884.13002781, "eta_seconds": 5000.409406614303, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17080, "total_steps": 22439, "tokens": 152232263680, "source": "fineweb_hq", "phase": 2, "loss": 1.9838321208953857, "ce_loss": 1.9838321208953857, "logit_z_loss": 91.83365249633789, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3592414855957031, "tokens_per_second": 8278383.744853358, "eta_seconds": 5769.750610280037, "data_wait_seconds": 1.990795135498047e-05} {"step": 17090, "total_steps": 22439, "tokens": 152321392640, "source": "fineweb_hq", "phase": 2, "loss": 1.986294448375702, "ce_loss": 1.986294448375702, "logit_z_loss": 99.087158203125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31731516122817993, "tokens_per_second": 9566647.539643345, "eta_seconds": 4983.467876958847, "data_wait_seconds": 1.9729137420654297e-05} {"step": 17100, "total_steps": 22439, "tokens": 152410521600, "source": "fineweb_hq", "phase": 2, "loss": 1.9807744026184082, "ce_loss": 1.9807744026184082, "logit_z_loss": 93.5271224975586, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34325459599494934, "tokens_per_second": 8606298.622439068, "eta_seconds": 5529.2006275415415, "data_wait_seconds": 1.800060272216797e-05} {"step": 17110, "total_steps": 22439, "tokens": 152499650560, "source": "fineweb_hq", "phase": 2, "loss": 1.9747563004493713, "ce_loss": 1.9747563004493713, "logit_z_loss": 93.97607231140137, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3456002175807953, "tokens_per_second": 8760478.892768541, "eta_seconds": 5421.715338325501, "data_wait_seconds": 1.9073486328125e-05} {"step": 17120, "total_steps": 22439, "tokens": 152588779520, "source": "fineweb_hq", "phase": 2, "loss": 1.9672779738903046, "ce_loss": 1.9672779738903046, "logit_z_loss": 101.64155769348145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33154618740081787, "tokens_per_second": 8371769.585302711, "eta_seconds": 5662.8044215679165, "data_wait_seconds": 1.5556812286376953e-05} {"step": 17130, "total_steps": 22439, "tokens": 152677908480, "source": "fineweb_hq", "phase": 2, "loss": 1.9514316618442535, "ce_loss": 1.9514316618442535, "logit_z_loss": 101.36367988586426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.287456750869751, "tokens_per_second": 6605784.934149858, "eta_seconds": 7163.200942158699, "data_wait_seconds": 0.17068994045257568} {"step": 17140, "total_steps": 22439, "tokens": 152767037440, "source": "fineweb_hq", "phase": 2, "loss": 1.9485962092876434, "ce_loss": 1.9485962092876434, "logit_z_loss": 99.4126205444336, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33410778641700745, "tokens_per_second": 6589021.857840929, "eta_seconds": 7167.897894859314, "data_wait_seconds": 1.6629695892333984e-05} {"step": 17150, "total_steps": 22439, "tokens": 152856166400, "source": "fineweb_hq", "phase": 2, "loss": 1.9374496042728424, "ce_loss": 1.9374496042728424, "logit_z_loss": 99.1710205078125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33058756589889526, "tokens_per_second": 7154333.0114528015, "eta_seconds": 6589.05685107708, "data_wait_seconds": 0.0003762245178222656} {"step": 17160, "total_steps": 22439, "tokens": 152945295360, "source": "fineweb_hq", "phase": 2, "loss": 1.9354835450649261, "ce_loss": 1.9354835450649261, "logit_z_loss": 100.6258544921875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3282388150691986, "tokens_per_second": 7355654.861201384, "eta_seconds": 6396.599469637871, "data_wait_seconds": 0.413562536239624} {"step": 17170, "total_steps": 22439, "tokens": 153034424320, "source": "fineweb_hq", "phase": 2, "loss": 1.9503636956214905, "ce_loss": 1.9503636956214905, "logit_z_loss": 97.99270057678223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3526250422000885, "tokens_per_second": 4007204.7396900356, "eta_seconds": 11719.403443217278, "data_wait_seconds": 1.9276461005210876} {"step": 17180, "total_steps": 22439, "tokens": 153123553280, "source": "fineweb_hq", "phase": 2, "loss": 1.9431176483631134, "ce_loss": 1.9431176483631134, "logit_z_loss": 101.42075157165527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3828999698162079, "tokens_per_second": 6131081.631772506, "eta_seconds": 7645.130644011497, "data_wait_seconds": 2.2113323211669922e-05} {"step": 17190, "total_steps": 22439, "tokens": 153212682240, "source": "fineweb_hq", "phase": 2, "loss": 1.957691639661789, "ce_loss": 1.957691639661789, "logit_z_loss": 97.40041160583496, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3864705264568329, "tokens_per_second": 8487363.86360206, "eta_seconds": 5512.169839286804, "data_wait_seconds": 1.7702579498291016e-05} {"step": 17200, "total_steps": 22439, "tokens": 153301811200, "source": "fineweb_hq", "phase": 2, "loss": 1.9405791461467743, "ce_loss": 1.9405791461467743, "logit_z_loss": 93.70114135742188, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33487704396247864, "tokens_per_second": 7529072.52937567, "eta_seconds": 6201.914241337777, "data_wait_seconds": 0.5367669463157654} {"step": 17210, "total_steps": 22439, "tokens": 153390940160, "source": "fineweb_hq", "phase": 2, "loss": 1.9469800293445587, "ce_loss": 1.9469800293445587, "logit_z_loss": 100.3773365020752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32989513874053955, "tokens_per_second": 8176441.678205491, "eta_seconds": 5699.977449631691, "data_wait_seconds": 0.2759697437286377} {"step": 17220, "total_steps": 22439, "tokens": 153480069120, "source": "fineweb_hq", "phase": 2, "loss": 1.9383246004581451, "ce_loss": 1.9383246004581451, "logit_z_loss": 100.86137390136719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3320091962814331, "tokens_per_second": 5134134.854603671, "eta_seconds": 9060.222518754006, "data_wait_seconds": 1.3871358036994934} {"step": 17230, "total_steps": 22439, "tokens": 153569198080, "source": "fineweb_hq", "phase": 2, "loss": 1.9710546731948853, "ce_loss": 1.9710546731948853, "logit_z_loss": 100.33719825744629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3163922131061554, "tokens_per_second": 4131269.492036707, "eta_seconds": 11238.016632294655, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17240, "total_steps": 22439, "tokens": 153658327040, "source": "fineweb_hq", "phase": 2, "loss": 1.9760589301586151, "ce_loss": 1.9760589301586151, "logit_z_loss": 95.23676872253418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3652236759662628, "tokens_per_second": 7380102.457707049, "eta_seconds": 6278.7944435119625, "data_wait_seconds": 1.3470649719238281e-05} {"step": 17250, "total_steps": 22439, "tokens": 153747456000, "source": "fineweb_hq", "phase": 2, "loss": 2.0013160705566406, "ce_loss": 2.0013160705566406, "logit_z_loss": 96.38262176513672, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3088250756263733, "tokens_per_second": 8475998.821354575, "eta_seconds": 5456.468118834496, "data_wait_seconds": 1.5616416931152344e-05} {"step": 17260, "total_steps": 22439, "tokens": 153836584960, "source": "fineweb_hq", "phase": 2, "loss": 2.0269165635108948, "ce_loss": 2.0269165635108948, "logit_z_loss": 96.58785438537598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29247233271598816, "tokens_per_second": 9244073.893546525, "eta_seconds": 4993.457312822342, "data_wait_seconds": 2.47955322265625e-05} {"step": 17270, "total_steps": 22439, "tokens": 153925713920, "source": "fineweb_hq", "phase": 2, "loss": 2.005932092666626, "ce_loss": 2.005932092666626, "logit_z_loss": 96.54178619384766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32698819041252136, "tokens_per_second": 9070363.968406653, "eta_seconds": 5079.262484335899, "data_wait_seconds": 1.800060272216797e-05} {"step": 17280, "total_steps": 22439, "tokens": 154014842880, "source": "fineweb_hq", "phase": 2, "loss": 2.0277079343795776, "ce_loss": 2.0277079343795776, "logit_z_loss": 97.82308387756348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36362573504447937, "tokens_per_second": 10701361.083309915, "eta_seconds": 4296.802070879936, "data_wait_seconds": 2.2649765014648438e-05} {"step": 17290, "total_steps": 22439, "tokens": 154103971840, "source": "fineweb_hq", "phase": 2, "loss": 2.0007764399051666, "ce_loss": 2.0007764399051666, "logit_z_loss": 97.40678024291992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35086560249328613, "tokens_per_second": 8787785.56666184, "eta_seconds": 5222.305569005012, "data_wait_seconds": 2.1576881408691406e-05} {"step": 17300, "total_steps": 22439, "tokens": 154193100800, "source": "fineweb_hq", "phase": 2, "loss": 2.017524480819702, "ce_loss": 2.017524480819702, "logit_z_loss": 98.66264343261719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2635333240032196, "tokens_per_second": 8613165.002581526, "eta_seconds": 5317.832937169075, "data_wait_seconds": 2.2470951080322266e-05} {"step": 17310, "total_steps": 22439, "tokens": 154282229760, "source": "fineweb_hq", "phase": 2, "loss": 2.009581059217453, "ce_loss": 2.009581059217453, "logit_z_loss": 94.89430046081543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3800652325153351, "tokens_per_second": 9769122.442550076, "eta_seconds": 4679.462649059296, "data_wait_seconds": 1.6987323760986328e-05} {"step": 17320, "total_steps": 22439, "tokens": 154371358720, "source": "fineweb_hq", "phase": 2, "loss": 2.0068286061286926, "ce_loss": 2.0068286061286926, "logit_z_loss": 96.71214294433594, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3101975619792938, "tokens_per_second": 9310047.513883736, "eta_seconds": 4900.631769704819, "data_wait_seconds": 1.7583370208740234e-05} {"step": 17330, "total_steps": 22439, "tokens": 154460487680, "source": "fineweb_hq", "phase": 2, "loss": 2.0171123147010803, "ce_loss": 2.0171123147010803, "logit_z_loss": 95.18956756591797, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3426845073699951, "tokens_per_second": 8263787.471592274, "eta_seconds": 5510.304545044899, "data_wait_seconds": 0.148970365524292} {"step": 17340, "total_steps": 22439, "tokens": 154549616640, "source": "fineweb_hq", "phase": 2, "loss": 1.9998387694358826, "ce_loss": 1.9998387694358826, "logit_z_loss": 96.38604354858398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32758277654647827, "tokens_per_second": 8958923.243951466, "eta_seconds": 5072.803445959092, "data_wait_seconds": 0.13814795017242432} {"step": 17350, "total_steps": 22439, "tokens": 154638745600, "source": "fineweb_hq", "phase": 2, "loss": 2.01267147064209, "ce_loss": 2.01267147064209, "logit_z_loss": 96.43253517150879, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3361871838569641, "tokens_per_second": 8356247.671256001, "eta_seconds": 5428.001841068268, "data_wait_seconds": 1.6987323760986328e-05} {"step": 17360, "total_steps": 22439, "tokens": 154727874560, "source": "fineweb_hq", "phase": 2, "loss": 2.018187254667282, "ce_loss": 2.018187254667282, "logit_z_loss": 93.36882591247559, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3305668234825134, "tokens_per_second": 10090563.174599096, "eta_seconds": 4486.231144952774, "data_wait_seconds": 2.002716064453125e-05} {"step": 17370, "total_steps": 22439, "tokens": 154817003520, "source": "fineweb_hq", "phase": 2, "loss": 2.022616446018219, "ce_loss": 2.022616446018219, "logit_z_loss": 98.14248466491699, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34486210346221924, "tokens_per_second": 8160377.531483852, "eta_seconds": 5536.443583607674, "data_wait_seconds": 1.7523765563964844e-05} {"step": 17380, "total_steps": 22439, "tokens": 154906132480, "source": "fineweb_hq", "phase": 2, "loss": 1.9969800412654877, "ce_loss": 1.9969800412654877, "logit_z_loss": 97.02164649963379, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33735954761505127, "tokens_per_second": 9655282.537776994, "eta_seconds": 4670.017753243446, "data_wait_seconds": 1.823902130126953e-05} {"step": 17390, "total_steps": 22439, "tokens": 154995261440, "source": "fineweb_hq", "phase": 2, "loss": 2.0145946741104126, "ce_loss": 2.0145946741104126, "logit_z_loss": 93.27764511108398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.328229695558548, "tokens_per_second": 10332136.79125305, "eta_seconds": 4355.460328602791, "data_wait_seconds": 1.7642974853515625e-05} {"step": 17400, "total_steps": 22439, "tokens": 155084390400, "source": "fineweb_hq", "phase": 2, "loss": 2.0072329938411713, "ce_loss": 2.0072329938411713, "logit_z_loss": 97.01882743835449, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31035247445106506, "tokens_per_second": 9435931.313361837, "eta_seconds": 4759.687353849411, "data_wait_seconds": 1.8596649169921875e-05} {"step": 17410, "total_steps": 22439, "tokens": 155173519360, "source": "fineweb_hq", "phase": 2, "loss": 2.030858039855957, "ce_loss": 2.030858039855957, "logit_z_loss": 92.65978813171387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3478027284145355, "tokens_per_second": 5409816.56271766, "eta_seconds": 8285.485000157356, "data_wait_seconds": 1.2472262978553772} {"step": 17420, "total_steps": 22439, "tokens": 155262648320, "source": "fineweb_hq", "phase": 2, "loss": 2.0290560722351074, "ce_loss": 2.0290560722351074, "logit_z_loss": 95.69318580627441, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35661518573760986, "tokens_per_second": 2242812.48052845, "eta_seconds": 19945.414702463153, "data_wait_seconds": 1.806020736694336e-05} {"step": 17430, "total_steps": 22439, "tokens": 155351777280, "source": "fineweb_hq", "phase": 2, "loss": 2.00050750374794, "ce_loss": 2.00050750374794, "logit_z_loss": 95.95457649230957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3159710168838501, "tokens_per_second": 7492846.533699494, "eta_seconds": 5958.309150362015, "data_wait_seconds": 1.811981201171875e-05} {"step": 17440, "total_steps": 22439, "tokens": 155440906240, "source": "fineweb_hq", "phase": 2, "loss": 2.0042567253112793, "ce_loss": 2.0042567253112793, "logit_z_loss": 93.5715217590332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2973633408546448, "tokens_per_second": 9166681.014002759, "eta_seconds": 4860.599712800979, "data_wait_seconds": 1.6570091247558594e-05} {"step": 17450, "total_steps": 22439, "tokens": 155530035200, "source": "fineweb_hq", "phase": 2, "loss": 1.9925718903541565, "ce_loss": 1.9925718903541565, "logit_z_loss": 98.17568969726562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32150590419769287, "tokens_per_second": 8083343.714675667, "eta_seconds": 5500.99559211731, "data_wait_seconds": 1.6033649444580078e-05} {"step": 17460, "total_steps": 22439, "tokens": 155619164160, "source": "fineweb_hq", "phase": 2, "loss": 2.010081797838211, "ce_loss": 2.010081797838211, "logit_z_loss": 96.1785659790039, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34066975116729736, "tokens_per_second": 7769546.531300676, "eta_seconds": 5711.698746538163, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17470, "total_steps": 22439, "tokens": 155708293120, "source": "fineweb_hq", "phase": 2, "loss": 1.9787733256816864, "ce_loss": 1.9787733256816864, "logit_z_loss": 94.29537391662598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3122110366821289, "tokens_per_second": 8895929.421657432, "eta_seconds": 4978.4770230054855, "data_wait_seconds": 1.8358230590820312e-05} {"step": 17480, "total_steps": 22439, "tokens": 155797422080, "source": "fineweb_hq", "phase": 2, "loss": 1.9765282273292542, "ce_loss": 1.9765282273292542, "logit_z_loss": 100.27986717224121, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31353071331977844, "tokens_per_second": 8986300.656422094, "eta_seconds": 4918.492375659942, "data_wait_seconds": 1.6689300537109375e-05} {"step": 17490, "total_steps": 22439, "tokens": 155886551040, "source": "fineweb_hq", "phase": 2, "loss": 1.951472818851471, "ce_loss": 1.951472818851471, "logit_z_loss": 97.0996150970459, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32786908745765686, "tokens_per_second": 9213885.494913612, "eta_seconds": 4787.3312869310375, "data_wait_seconds": 1.8417835235595703e-05} {"step": 17500, "total_steps": 22439, "tokens": 155975680000, "source": "fineweb_hq", "phase": 2, "loss": 1.9583874642848969, "ce_loss": 1.9583874642848969, "logit_z_loss": 97.09908485412598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3411608934402466, "tokens_per_second": 10264896.028871339, "eta_seconds": 4288.479222798347, "data_wait_seconds": 2.4974346160888672e-05} {"step": 17510, "total_steps": 22439, "tokens": 156064808960, "source": "fineweb_hq", "phase": 2, "loss": 1.9677530825138092, "ce_loss": 1.9677530825138092, "logit_z_loss": 102.24548721313477, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3519105017185211, "tokens_per_second": 10709340.058152908, "eta_seconds": 4102.1822208881385, "data_wait_seconds": 2.2113323211669922e-05} {"step": 17520, "total_steps": 22439, "tokens": 156153937920, "source": "fineweb_hq", "phase": 2, "loss": 1.9546172320842743, "ce_loss": 1.9546172320842743, "logit_z_loss": 96.62191963195801, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36671847105026245, "tokens_per_second": 8747985.482935384, "eta_seconds": 5011.729330086709, "data_wait_seconds": 1.436471939086914e-05} {"step": 17530, "total_steps": 22439, "tokens": 156243066880, "source": "fineweb_hq", "phase": 2, "loss": 1.9784636795520782, "ce_loss": 1.9784636795520782, "logit_z_loss": 96.7600212097168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3301105201244354, "tokens_per_second": 9453973.936002055, "eta_seconds": 4628.043906211853, "data_wait_seconds": 1.895427703857422e-05} {"step": 17540, "total_steps": 22439, "tokens": 156332195840, "source": "fineweb_hq", "phase": 2, "loss": 1.9633925557136536, "ce_loss": 1.9633925557136536, "logit_z_loss": 96.85932922363281, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34995487332344055, "tokens_per_second": 8743742.69169938, "eta_seconds": 4993.774295926094, "data_wait_seconds": 2.104043960571289e-05} {"step": 17550, "total_steps": 22439, "tokens": 156421324800, "source": "fineweb_hq", "phase": 2, "loss": 1.9600829184055328, "ce_loss": 1.9600829184055328, "logit_z_loss": 98.2473258972168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2958163022994995, "tokens_per_second": 9732381.308699993, "eta_seconds": 4477.33675467968, "data_wait_seconds": 2.6226043701171875e-05} {"step": 17560, "total_steps": 22439, "tokens": 156510453760, "source": "fineweb_hq", "phase": 2, "loss": 1.9714820981025696, "ce_loss": 1.9714820981025696, "logit_z_loss": 97.96072387695312, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33853787183761597, "tokens_per_second": 8715157.913942952, "eta_seconds": 4989.699557185173, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17570, "total_steps": 22439, "tokens": 156599582720, "source": "fineweb_hq", "phase": 2, "loss": 1.947793334722519, "ce_loss": 1.947793334722519, "logit_z_loss": 98.27105331420898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3195074796676636, "tokens_per_second": 7979290.253103022, "eta_seconds": 5438.690566134453, "data_wait_seconds": 2.0563602447509766e-05} {"step": 17580, "total_steps": 22439, "tokens": 156688711680, "source": "fineweb_hq", "phase": 2, "loss": 1.965055376291275, "ce_loss": 1.965055376291275, "logit_z_loss": 96.18194389343262, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3475992679595947, "tokens_per_second": 8597352.178847687, "eta_seconds": 5037.337166500092, "data_wait_seconds": 0.3349863290786743} {"step": 17590, "total_steps": 22439, "tokens": 156777840640, "source": "fineweb_hq", "phase": 2, "loss": 1.9590928852558136, "ce_loss": 1.9590928852558136, "logit_z_loss": 94.55623435974121, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3178192973136902, "tokens_per_second": 8740848.392364008, "eta_seconds": 4944.443692874908, "data_wait_seconds": 2.0682811737060547e-05} {"step": 17600, "total_steps": 22439, "tokens": 156866969600, "source": "fineweb_hq", "phase": 2, "loss": 1.951667606830597, "ce_loss": 1.951667606830597, "logit_z_loss": 94.57657241821289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32874149084091187, "tokens_per_second": 10152442.912532698, "eta_seconds": 4248.189732813836, "data_wait_seconds": 2.014636993408203e-05} {"step": 17610, "total_steps": 22439, "tokens": 156956098560, "source": "fineweb_hq", "phase": 2, "loss": 1.9600532054901123, "ce_loss": 1.9600532054901123, "logit_z_loss": 100.35949325561523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3020731210708618, "tokens_per_second": 10073078.517038003, "eta_seconds": 4272.812399029732, "data_wait_seconds": 1.9490718841552734e-05} {"step": 17620, "total_steps": 22439, "tokens": 157045227520, "source": "fineweb_hq", "phase": 2, "loss": 1.9641358852386475, "ce_loss": 1.9641358852386475, "logit_z_loss": 99.28735160827637, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27305200695991516, "tokens_per_second": 9718213.86207816, "eta_seconds": 4419.664604377746, "data_wait_seconds": 1.8835067749023438e-05} {"step": 17630, "total_steps": 22439, "tokens": 157134356480, "source": "fineweb_hq", "phase": 2, "loss": 1.9517640173435211, "ce_loss": 1.9517640173435211, "logit_z_loss": 97.84289169311523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2927537262439728, "tokens_per_second": 8742869.313829416, "eta_seconds": 4902.522881841659, "data_wait_seconds": 2.205371856689453e-05} {"step": 17640, "total_steps": 22439, "tokens": 157223485440, "source": "fineweb_hq", "phase": 2, "loss": 1.9557964205741882, "ce_loss": 1.9557964205741882, "logit_z_loss": 95.28232955932617, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33404502272605896, "tokens_per_second": 10308344.360959586, "eta_seconds": 4149.355745816231, "data_wait_seconds": 2.104043960571289e-05} {"step": 17650, "total_steps": 22439, "tokens": 157312614400, "source": "fineweb_hq", "phase": 2, "loss": 1.9445303976535797, "ce_loss": 1.9445303976535797, "logit_z_loss": 99.22982215881348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2686925530433655, "tokens_per_second": 9759688.670812234, "eta_seconds": 4373.485710835457, "data_wait_seconds": 1.7821788787841797e-05} {"step": 17660, "total_steps": 22439, "tokens": 157401743360, "source": "fineweb_hq", "phase": 2, "loss": 1.9651190340518951, "ce_loss": 1.9651190340518951, "logit_z_loss": 99.39599227905273, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30421844124794006, "tokens_per_second": 9385035.582920706, "eta_seconds": 4538.579487276077, "data_wait_seconds": 2.205371856689453e-05} {"step": 17670, "total_steps": 22439, "tokens": 157490872320, "source": "fineweb_hq", "phase": 2, "loss": 1.9805349111557007, "ce_loss": 1.9805349111557007, "logit_z_loss": 98.77122116088867, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36225757002830505, "tokens_per_second": 10170568.543102344, "eta_seconds": 4179.274820661545, "data_wait_seconds": 2.3245811462402344e-05} {"step": 17680, "total_steps": 22439, "tokens": 157580001280, "source": "fineweb_hq", "phase": 2, "loss": 1.9609110653400421, "ce_loss": 1.9609110653400421, "logit_z_loss": 98.21670150756836, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32350391149520874, "tokens_per_second": 9650647.653601613, "eta_seconds": 4395.194352388382, "data_wait_seconds": 2.0444393157958984e-05} {"step": 17690, "total_steps": 22439, "tokens": 157669130240, "source": "fineweb_hq", "phase": 2, "loss": 1.968457967042923, "ce_loss": 1.968457967042923, "logit_z_loss": 93.16124534606934, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39158663153648376, "tokens_per_second": 8974465.486095656, "eta_seconds": 4716.419397854805, "data_wait_seconds": 1.996755599975586e-05} {"step": 17700, "total_steps": 22439, "tokens": 157758259200, "source": "fineweb_hq", "phase": 2, "loss": 1.9642956256866455, "ce_loss": 1.9642956256866455, "logit_z_loss": 98.46838188171387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.27792230248451233, "tokens_per_second": 8232201.912327569, "eta_seconds": 5130.852546358109, "data_wait_seconds": 1.9311904907226562e-05} {"step": 17710, "total_steps": 22439, "tokens": 157847388160, "source": "fineweb_hq", "phase": 2, "loss": 1.9658010303974152, "ce_loss": 1.9658010303974152, "logit_z_loss": 98.0110969543457, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36854326725006104, "tokens_per_second": 9711407.834883446, "eta_seconds": 4340.162198996543, "data_wait_seconds": 1.4066696166992188e-05} {"step": 17720, "total_steps": 22439, "tokens": 157936517120, "source": "fineweb_hq", "phase": 2, "loss": 1.972231924533844, "ce_loss": 1.972231924533844, "logit_z_loss": 96.40910530090332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31049099564552307, "tokens_per_second": 8511145.866466377, "eta_seconds": 4941.750133752823, "data_wait_seconds": 1.9073486328125e-05} {"step": 17730, "total_steps": 22439, "tokens": 158025646080, "source": "fineweb_hq", "phase": 2, "loss": 1.947891652584076, "ce_loss": 1.947891652584076, "logit_z_loss": 95.75148391723633, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3144948482513428, "tokens_per_second": 8818043.726585744, "eta_seconds": 4759.652885079384, "data_wait_seconds": 1.5795230865478516e-05} {"step": 17740, "total_steps": 22439, "tokens": 158114775040, "source": "fineweb_hq", "phase": 2, "loss": 1.9652434885501862, "ce_loss": 1.9652434885501862, "logit_z_loss": 100.0909194946289, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2865515947341919, "tokens_per_second": 8406901.926335646, "eta_seconds": 4981.823110461236, "data_wait_seconds": 1.5676021575927734e-05} {"step": 17750, "total_steps": 22439, "tokens": 158203904000, "source": "fineweb_hq", "phase": 2, "loss": 1.965955764055252, "ce_loss": 1.965955764055252, "logit_z_loss": 96.87933540344238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3989194929599762, "tokens_per_second": 8984570.712407902, "eta_seconds": 4651.593346166611, "data_wait_seconds": 0.3513634204864502} {"step": 17760, "total_steps": 22439, "tokens": 158293032960, "source": "fineweb_hq", "phase": 2, "loss": 1.9791938364505768, "ce_loss": 1.9791938364505768, "logit_z_loss": 99.58212280273438, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3125707507133484, "tokens_per_second": 9166824.421866711, "eta_seconds": 4549.387930297852, "data_wait_seconds": 1.8537044525146484e-05} {"step": 17770, "total_steps": 22439, "tokens": 158382161920, "source": "fineweb_hq", "phase": 2, "loss": 1.9822140336036682, "ce_loss": 1.9822140336036682, "logit_z_loss": 93.5108528137207, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.4138431251049042, "tokens_per_second": 7932807.23475573, "eta_seconds": 5245.849318218231, "data_wait_seconds": 1.9073486328125e-05} {"step": 17780, "total_steps": 22439, "tokens": 158471290880, "source": "fineweb_hq", "phase": 2, "loss": 2.018120378255844, "ce_loss": 2.018120378255844, "logit_z_loss": 94.47075653076172, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31418508291244507, "tokens_per_second": 9512117.559599593, "eta_seconds": 4365.503496336937, "data_wait_seconds": 1.728534698486328e-05} {"step": 17790, "total_steps": 22439, "tokens": 158560419840, "source": "fineweb_hq", "phase": 2, "loss": 1.9958075284957886, "ce_loss": 1.9958075284957886, "logit_z_loss": 97.68951034545898, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30958032608032227, "tokens_per_second": 10177652.885507911, "eta_seconds": 4071.277923321724, "data_wait_seconds": 1.9490718841552734e-05} {"step": 17800, "total_steps": 22439, "tokens": 158649548800, "source": "fineweb_hq", "phase": 2, "loss": 2.0018684566020966, "ce_loss": 2.0018684566020966, "logit_z_loss": 92.87697792053223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3366670608520508, "tokens_per_second": 8973926.903413909, "eta_seconds": 4607.450560832024, "data_wait_seconds": 1.609325408935547e-05} {"step": 17810, "total_steps": 22439, "tokens": 158738677760, "source": "fineweb_hq", "phase": 2, "loss": 1.9944812059402466, "ce_loss": 1.9944812059402466, "logit_z_loss": 95.95430564880371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38356053829193115, "tokens_per_second": 9180542.608800545, "eta_seconds": 4494.047611570359, "data_wait_seconds": 1.5854835510253906e-05} {"step": 17820, "total_steps": 22439, "tokens": 158827806720, "source": "fineweb_hq", "phase": 2, "loss": 1.9969244003295898, "ce_loss": 1.9969244003295898, "logit_z_loss": 97.98116111755371, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39558514952659607, "tokens_per_second": 9324226.188670129, "eta_seconds": 4415.236802601814, "data_wait_seconds": 1.5556812286376953e-05} {"step": 17830, "total_steps": 22439, "tokens": 158916935680, "source": "fineweb_hq", "phase": 2, "loss": 2.007891595363617, "ce_loss": 2.007891595363617, "logit_z_loss": 97.62471199035645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2738721966743469, "tokens_per_second": 7304580.522126512, "eta_seconds": 5623.805164384842, "data_wait_seconds": 0.1453041434288025} {"step": 17840, "total_steps": 22439, "tokens": 159006064640, "source": "fineweb_hq", "phase": 2, "loss": 1.9880889058113098, "ce_loss": 1.9880889058113098, "logit_z_loss": 93.41608428955078, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29933080077171326, "tokens_per_second": 6908702.223425026, "eta_seconds": 5933.156094789505, "data_wait_seconds": 0.4547703266143799} {"step": 17850, "total_steps": 22439, "tokens": 159095193600, "source": "fineweb_hq", "phase": 2, "loss": 1.9885435104370117, "ce_loss": 1.9885435104370117, "logit_z_loss": 101.16597938537598, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33115020394325256, "tokens_per_second": 10173740.80963266, "eta_seconds": 4020.279316067696, "data_wait_seconds": 1.621246337890625e-05} {"step": 17860, "total_steps": 22439, "tokens": 159184322560, "source": "fineweb_hq", "phase": 2, "loss": 2.0060843229293823, "ce_loss": 2.0060843229293823, "logit_z_loss": 95.1015853881836, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32010674476623535, "tokens_per_second": 8493525.65954234, "eta_seconds": 4805.089478731155, "data_wait_seconds": 0.31148964166641235} {"step": 17870, "total_steps": 22439, "tokens": 159273451520, "source": "fineweb_hq", "phase": 2, "loss": 2.015391767024994, "ce_loss": 2.015391767024994, "logit_z_loss": 94.96942329406738, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39701202511787415, "tokens_per_second": 10121163.622444276, "eta_seconds": 4023.5513764142993, "data_wait_seconds": 1.710653305053711e-05} {"step": 17880, "total_steps": 22439, "tokens": 159362580480, "source": "fineweb_hq", "phase": 2, "loss": 1.993990182876587, "ce_loss": 1.993990182876587, "logit_z_loss": 95.43209648132324, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3660629689693451, "tokens_per_second": 9292107.698916623, "eta_seconds": 4372.9468254804615, "data_wait_seconds": 1.6927719116210938e-05} {"step": 17890, "total_steps": 22439, "tokens": 159451709440, "source": "fineweb_hq", "phase": 2, "loss": 1.9974838495254517, "ce_loss": 1.9974838495254517, "logit_z_loss": 95.99584579467773, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30706194043159485, "tokens_per_second": 8887412.756649531, "eta_seconds": 4562.043534398079, "data_wait_seconds": 1.6927719116210938e-05} {"step": 17900, "total_steps": 22439, "tokens": 159540838400, "source": "fineweb_hq", "phase": 2, "loss": 1.9892581701278687, "ce_loss": 1.9892581701278687, "logit_z_loss": 96.7289810180664, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3231419324874878, "tokens_per_second": 9443061.852798916, "eta_seconds": 4284.164985322952, "data_wait_seconds": 2.3126602172851562e-05} {"step": 17910, "total_steps": 22439, "tokens": 159629967360, "source": "fineweb_hq", "phase": 2, "loss": 1.998843401670456, "ce_loss": 1.998843401670456, "logit_z_loss": 95.23994636535645, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3216363787651062, "tokens_per_second": 9732045.094998574, "eta_seconds": 4147.792739343643, "data_wait_seconds": 1.4901161193847656e-05} {"step": 17920, "total_steps": 22439, "tokens": 159719096320, "source": "fineweb_hq", "phase": 2, "loss": 1.9930969178676605, "ce_loss": 1.9930969178676605, "logit_z_loss": 95.46540832519531, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3741667568683624, "tokens_per_second": 9507594.409081904, "eta_seconds": 4236.337320566177, "data_wait_seconds": 1.4960765838623047e-05} {"step": 17930, "total_steps": 22439, "tokens": 159808225280, "source": "fineweb_hq", "phase": 2, "loss": 1.9889647364616394, "ce_loss": 1.9889647364616394, "logit_z_loss": 100.00315284729004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36404165625572205, "tokens_per_second": 8177723.939773668, "eta_seconds": 4914.356165599823, "data_wait_seconds": 1.7881393432617188e-05} {"step": 17940, "total_steps": 22439, "tokens": 159897354240, "source": "fineweb_hq", "phase": 2, "loss": 1.9985653758049011, "ce_loss": 1.9985653758049011, "logit_z_loss": 90.49711608886719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3302333354949951, "tokens_per_second": 5776202.129612507, "eta_seconds": 6942.125328063965, "data_wait_seconds": 0.4580506682395935} {"step": 17950, "total_steps": 22439, "tokens": 159986483200, "source": "fineweb_hq", "phase": 2, "loss": 1.9853385388851166, "ce_loss": 1.9853385388851166, "logit_z_loss": 99.4282112121582, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3392760157585144, "tokens_per_second": 5121526.125539673, "eta_seconds": 7812.122629714012, "data_wait_seconds": 1.8298625946044922e-05} {"step": 17960, "total_steps": 22439, "tokens": 160075612160, "source": "fineweb_hq", "phase": 2, "loss": 1.965518742799759, "ce_loss": 1.965518742799759, "logit_z_loss": 99.43943977355957, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30809563398361206, "tokens_per_second": 10438057.124153154, "eta_seconds": 3824.549023747444, "data_wait_seconds": 1.4424324035644531e-05} {"step": 17970, "total_steps": 22439, "tokens": 160164741120, "source": "fineweb_hq", "phase": 2, "loss": 2.002147763967514, "ce_loss": 2.002147763967514, "logit_z_loss": 98.40137481689453, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37267595529556274, "tokens_per_second": 9311945.671496574, "eta_seconds": 4277.4876088380815, "data_wait_seconds": 1.6570091247558594e-05} {"step": 17980, "total_steps": 22439, "tokens": 160253870080, "source": "fineweb_hq", "phase": 2, "loss": 1.9693255126476288, "ce_loss": 1.9693255126476288, "logit_z_loss": 95.1552848815918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3030140697956085, "tokens_per_second": 9112277.250439454, "eta_seconds": 4361.434817194939, "data_wait_seconds": 2.002716064453125e-05} {"step": 17990, "total_steps": 22439, "tokens": 160342999040, "source": "fineweb_hq", "phase": 2, "loss": 1.9695724844932556, "ce_loss": 1.9695724844932556, "logit_z_loss": 99.09075355529785, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31739017367362976, "tokens_per_second": 9510296.605362454, "eta_seconds": 4169.53076748848, "data_wait_seconds": 1.823902130126953e-05} {"step": 18000, "total_steps": 22439, "tokens": 160432128000, "source": "fineweb_hq", "phase": 2, "loss": 1.9570696949958801, "ce_loss": 1.9570696949958801, "logit_z_loss": 96.24184989929199, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2672783136367798, "tokens_per_second": 9095761.333032342, "eta_seconds": 4349.756320047379, "data_wait_seconds": 1.6629695892333984e-05} {"step": 18010, "total_steps": 22439, "tokens": 160521256960, "source": "fineweb_hq", "phase": 2, "loss": 2.0039989948272705, "ce_loss": 2.0039989948272705, "logit_z_loss": 96.61477088928223, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31603294610977173, "tokens_per_second": 9510891.091433367, "eta_seconds": 4150.527642941474, "data_wait_seconds": 2.014636993408203e-05} {"step": 18020, "total_steps": 22439, "tokens": 160610385920, "source": "fineweb_hq", "phase": 2, "loss": 1.9916872084140778, "ce_loss": 1.9916872084140778, "logit_z_loss": 98.01899909973145, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3239695429801941, "tokens_per_second": 9003267.745913193, "eta_seconds": 4374.643577814102, "data_wait_seconds": 1.7404556274414062e-05} {"step": 18030, "total_steps": 22439, "tokens": 160699514880, "source": "fineweb_hq", "phase": 2, "loss": 2.005425304174423, "ce_loss": 2.005425304174423, "logit_z_loss": 97.81391716003418, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39919841289520264, "tokens_per_second": 8229095.015464693, "eta_seconds": 4775.368177199363, "data_wait_seconds": 0.14135503768920898} {"step": 18040, "total_steps": 22439, "tokens": 160788643840, "source": "fineweb_hq", "phase": 2, "loss": 1.9785395860671997, "ce_loss": 1.9785395860671997, "logit_z_loss": 96.43569946289062, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3726417124271393, "tokens_per_second": 9774400.587787114, "eta_seconds": 4011.2771265983583, "data_wait_seconds": 1.9371509552001953e-05} {"step": 18050, "total_steps": 22439, "tokens": 160877772800, "source": "fineweb_hq", "phase": 2, "loss": 1.9808385372161865, "ce_loss": 1.9808385372161865, "logit_z_loss": 99.4512996673584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2966969609260559, "tokens_per_second": 8374963.781657507, "eta_seconds": 4670.909816908837, "data_wait_seconds": 2.187490463256836e-05} {"step": 18060, "total_steps": 22439, "tokens": 160966901760, "source": "fineweb_hq", "phase": 2, "loss": 1.9918268620967865, "ce_loss": 1.9918268620967865, "logit_z_loss": 96.37133598327637, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3241490125656128, "tokens_per_second": 8811014.527139207, "eta_seconds": 4429.634233808518, "data_wait_seconds": 1.424551010131836e-05} {"step": 18070, "total_steps": 22439, "tokens": 161056030720, "source": "fineweb_hq", "phase": 2, "loss": 2.023321211338043, "ce_loss": 2.023321211338043, "logit_z_loss": 93.92999076843262, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3497234582901001, "tokens_per_second": 8970065.436271027, "eta_seconds": 4341.154799890518, "data_wait_seconds": 1.633167266845703e-05} {"step": 18080, "total_steps": 22439, "tokens": 161145159680, "source": "fineweb_hq", "phase": 2, "loss": 2.003122329711914, "ce_loss": 2.003122329711914, "logit_z_loss": 98.69774436950684, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33213087916374207, "tokens_per_second": 8510865.677312767, "eta_seconds": 4564.907394504547, "data_wait_seconds": 1.5795230865478516e-05} {"step": 18090, "total_steps": 22439, "tokens": 161234288640, "source": "fineweb_hq", "phase": 2, "loss": 2.0032800436019897, "ce_loss": 2.0032800436019897, "logit_z_loss": 96.91409111022949, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3475627303123474, "tokens_per_second": 8976546.315044366, "eta_seconds": 4318.162391591071, "data_wait_seconds": 1.9431114196777344e-05} {"step": 18100, "total_steps": 22439, "tokens": 161323417600, "source": "fineweb_hq", "phase": 2, "loss": 2.0132707953453064, "ce_loss": 2.0132707953453064, "logit_z_loss": 99.42106819152832, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38311830163002014, "tokens_per_second": 8736132.321077218, "eta_seconds": 4426.79372549057, "data_wait_seconds": 2.288818359375e-05} {"step": 18110, "total_steps": 22439, "tokens": 161412546560, "source": "fineweb_hq", "phase": 2, "loss": 2.012435555458069, "ce_loss": 2.012435555458069, "logit_z_loss": 90.13602638244629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.402006059885025, "tokens_per_second": 9194059.058368906, "eta_seconds": 4196.615068387985, "data_wait_seconds": 1.9729137420654297e-05} {"step": 18120, "total_steps": 22439, "tokens": 161501675520, "source": "fineweb_hq", "phase": 2, "loss": 1.9902066886425018, "ce_loss": 1.9902066886425018, "logit_z_loss": 93.46353530883789, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31898435950279236, "tokens_per_second": 9391607.093758564, "eta_seconds": 4098.850967645645, "data_wait_seconds": 2.1696090698242188e-05} {"step": 18130, "total_steps": 22439, "tokens": 161590804480, "source": "fineweb_hq", "phase": 2, "loss": 2.0035828948020935, "ce_loss": 2.0035828948020935, "logit_z_loss": 98.30356407165527, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3596588671207428, "tokens_per_second": 9690967.696360044, "eta_seconds": 3963.037548708916, "data_wait_seconds": 1.823902130126953e-05} {"step": 18140, "total_steps": 22439, "tokens": 161679933440, "source": "fineweb_hq", "phase": 2, "loss": 2.0096271336078644, "ce_loss": 2.0096271336078644, "logit_z_loss": 94.89254570007324, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33761703968048096, "tokens_per_second": 10573145.463053083, "eta_seconds": 3623.948997759819, "data_wait_seconds": 2.0682811737060547e-05} {"step": 18150, "total_steps": 22439, "tokens": 161769062400, "source": "fineweb_hq", "phase": 2, "loss": 2.0058212876319885, "ce_loss": 2.0058212876319885, "logit_z_loss": 95.43593215942383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37932631373405457, "tokens_per_second": 9801016.624004306, "eta_seconds": 3900.351607441902, "data_wait_seconds": 2.014636993408203e-05} {"step": 18160, "total_steps": 22439, "tokens": 161858191360, "source": "fineweb_hq", "phase": 2, "loss": 1.994958758354187, "ce_loss": 1.994958758354187, "logit_z_loss": 98.03835868835449, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2920140326023102, "tokens_per_second": 7172321.8769224705, "eta_seconds": 5317.424766826629, "data_wait_seconds": 1.823902130126953e-05} {"step": 18170, "total_steps": 22439, "tokens": 161947320320, "source": "fineweb_hq", "phase": 2, "loss": 2.007260501384735, "ce_loss": 2.007260501384735, "logit_z_loss": 97.0285415649414, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3634319007396698, "tokens_per_second": 7529729.628378951, "eta_seconds": 5053.189809179306, "data_wait_seconds": 0.5644757747650146} {"step": 18180, "total_steps": 22439, "tokens": 162036449280, "source": "fineweb_hq", "phase": 2, "loss": 2.025576114654541, "ce_loss": 2.025576114654541, "logit_z_loss": 91.82894325256348, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3422970175743103, "tokens_per_second": 8261585.1787062995, "eta_seconds": 4594.762777709961, "data_wait_seconds": 1.8894672393798828e-05} {"step": 18190, "total_steps": 22439, "tokens": 162125578240, "source": "fineweb_hq", "phase": 2, "loss": 2.0103681683540344, "ce_loss": 2.0103681683540344, "logit_z_loss": 98.28057861328125, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3203881084918976, "tokens_per_second": 7987906.694933909, "eta_seconds": 4741.02872633934, "data_wait_seconds": 1.5854835510253906e-05} {"step": 18200, "total_steps": 22439, "tokens": 162214707200, "source": "fineweb_hq", "phase": 2, "loss": 2.020944654941559, "ce_loss": 2.020944654941559, "logit_z_loss": 93.17542457580566, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36857253313064575, "tokens_per_second": 8569725.438690089, "eta_seconds": 4408.7487299680715, "data_wait_seconds": 1.5497207641601562e-05} {"step": 18210, "total_steps": 22439, "tokens": 162303836160, "source": "fineweb_hq", "phase": 2, "loss": 1.996510922908783, "ce_loss": 1.996510922908783, "logit_z_loss": 93.98086357116699, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30824315547943115, "tokens_per_second": 1851191.7977479044, "eta_seconds": 20361.28143494129, "data_wait_seconds": 4.257327854633331} {"step": 18220, "total_steps": 22439, "tokens": 162392965120, "source": "fineweb_hq", "phase": 2, "loss": 2.014278680086136, "ce_loss": 2.014278680086136, "logit_z_loss": 92.11254501342773, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3192278742790222, "tokens_per_second": 4265582.363633884, "eta_seconds": 8815.562569975853, "data_wait_seconds": 0.38472187519073486} {"step": 18230, "total_steps": 22439, "tokens": 162482094080, "source": "fineweb_hq", "phase": 2, "loss": 2.02910715341568, "ce_loss": 2.02910715341568, "logit_z_loss": 98.95074462890625, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.24560795724391937, "tokens_per_second": 5959869.131436578, "eta_seconds": 6294.497150301933, "data_wait_seconds": 1.6808509826660156e-05} {"step": 18240, "total_steps": 22439, "tokens": 162571223040, "source": "fineweb_hq", "phase": 2, "loss": 2.014345169067383, "ce_loss": 2.014345169067383, "logit_z_loss": 92.87569999694824, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3614856004714966, "tokens_per_second": 5289913.0272362195, "eta_seconds": 7074.832820749282, "data_wait_seconds": 0.8877732753753662} {"step": 18250, "total_steps": 22439, "tokens": 162660352000, "source": "fineweb_hq", "phase": 2, "loss": 2.003686398267746, "ce_loss": 2.003686398267746, "logit_z_loss": 96.7684154510498, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3812764883041382, "tokens_per_second": 1767405.3424285515, "eta_seconds": 21124.820915555956, "data_wait_seconds": 1.9490718841552734e-05} {"step": 18260, "total_steps": 22439, "tokens": 162749480960, "source": "fineweb_hq", "phase": 2, "loss": 2.02264803647995, "ce_loss": 2.02264803647995, "logit_z_loss": 94.59133911132812, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33372581005096436, "tokens_per_second": 3538095.433205358, "eta_seconds": 10527.413148450853, "data_wait_seconds": 0.34490716457366943} {"step": 18270, "total_steps": 22439, "tokens": 162838609920, "source": "fineweb_hq", "phase": 2, "loss": 2.00893497467041, "ce_loss": 2.00893497467041, "logit_z_loss": 99.52404403686523, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.36524856090545654, "tokens_per_second": 6200766.968257428, "eta_seconds": 5992.462483143807, "data_wait_seconds": 1.0151103138923645} {"step": 18280, "total_steps": 22439, "tokens": 162927738880, "source": "fineweb_hq", "phase": 2, "loss": 2.0181382298469543, "ce_loss": 2.0181382298469543, "logit_z_loss": 94.39307022094727, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3526217043399811, "tokens_per_second": 7598583.601510854, "eta_seconds": 4878.374234986305, "data_wait_seconds": 1.5854835510253906e-05} {"step": 18290, "total_steps": 22439, "tokens": 163016867840, "source": "fineweb_hq", "phase": 2, "loss": 2.013260841369629, "ce_loss": 2.013260841369629, "logit_z_loss": 91.12716102600098, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3101779818534851, "tokens_per_second": 5858766.51699395, "eta_seconds": 6311.841476655006, "data_wait_seconds": 1.6689300537109375e-05} {"step": 18300, "total_steps": 22439, "tokens": 163105996800, "source": "fineweb_hq", "phase": 2, "loss": 2.001652240753174, "ce_loss": 2.001652240753174, "logit_z_loss": 97.44486045837402, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38997969031333923, "tokens_per_second": 3974792.3810835355, "eta_seconds": 9281.107793092728, "data_wait_seconds": 0.15578126907348633} {"step": 18310, "total_steps": 22439, "tokens": 163195125760, "source": "fineweb_hq", "phase": 2, "loss": 1.9772208034992218, "ce_loss": 1.9772208034992218, "logit_z_loss": 97.19540214538574, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35145828127861023, "tokens_per_second": 9517659.241305232, "eta_seconds": 3866.638492822647, "data_wait_seconds": 1.823902130126953e-05} {"step": 18320, "total_steps": 22439, "tokens": 163284254720, "source": "fineweb_hq", "phase": 2, "loss": 1.9995926320552826, "ce_loss": 1.9995926320552826, "logit_z_loss": 95.61187934875488, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3171335458755493, "tokens_per_second": 9703332.46086996, "eta_seconds": 3783.4649871110914, "data_wait_seconds": 1.7583370208740234e-05} {"step": 18330, "total_steps": 22439, "tokens": 163373383680, "source": "fineweb_hq", "phase": 2, "loss": 1.9867905974388123, "ce_loss": 1.9867905974388123, "logit_z_loss": 98.01746368408203, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2962477505207062, "tokens_per_second": 8836622.137662258, "eta_seconds": 4144.467093133926, "data_wait_seconds": 2.0265579223632812e-05} {"step": 18340, "total_steps": 22439, "tokens": 163462512640, "source": "fineweb_hq", "phase": 2, "loss": 2.004061460494995, "ce_loss": 2.004061460494995, "logit_z_loss": 95.84898376464844, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.39348074793815613, "tokens_per_second": 9536446.64281088, "eta_seconds": 3830.9825527668, "data_wait_seconds": 1.6927719116210938e-05} {"step": 18350, "total_steps": 22439, "tokens": 163551641600, "source": "fineweb_hq", "phase": 2, "loss": 1.963485985994339, "ce_loss": 1.963485985994339, "logit_z_loss": 94.91690063476562, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33582305908203125, "tokens_per_second": 9122638.84561319, "eta_seconds": 3994.9878933906552, "data_wait_seconds": 2.3663043975830078e-05} {"step": 18360, "total_steps": 22439, "tokens": 163640770560, "source": "fineweb_hq", "phase": 2, "loss": 1.9564872086048126, "ce_loss": 1.9564872086048126, "logit_z_loss": 100.00007629394531, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29982200264930725, "tokens_per_second": 9062152.927948635, "eta_seconds": 4011.8173984766004, "data_wait_seconds": 1.5795230865478516e-05} {"step": 18370, "total_steps": 22439, "tokens": 163729899520, "source": "fineweb_hq", "phase": 2, "loss": 1.9086967408657074, "ce_loss": 1.9086967408657074, "logit_z_loss": 96.77571487426758, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3535960018634796, "tokens_per_second": 8122366.072465478, "eta_seconds": 4465.025769639015, "data_wait_seconds": 0.4280989170074463} {"step": 18380, "total_steps": 22439, "tokens": 163819028480, "source": "fineweb_hq", "phase": 2, "loss": 1.8065293431282043, "ce_loss": 1.8065293431282043, "logit_z_loss": 104.51200294494629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3837413489818573, "tokens_per_second": 9692412.933748003, "eta_seconds": 3732.5529887437824, "data_wait_seconds": 1.6808509826660156e-05} {"step": 18390, "total_steps": 22439, "tokens": 163908157440, "source": "fineweb_hq", "phase": 2, "loss": 1.7650284171104431, "ce_loss": 1.7650284171104431, "logit_z_loss": 105.7940731048584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.391528844833374, "tokens_per_second": 9214968.182255022, "eta_seconds": 3916.2713522434237, "data_wait_seconds": 1.8656253814697266e-05} {"step": 18400, "total_steps": 22439, "tokens": 163997286400, "source": "fineweb_hq", "phase": 2, "loss": 1.7362429201602936, "ce_loss": 1.7362429201602936, "logit_z_loss": 105.35090637207031, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2865695655345917, "tokens_per_second": 8869943.546058824, "eta_seconds": 4058.558744716644, "data_wait_seconds": 1.4781951904296875e-05} {"step": 18410, "total_steps": 22439, "tokens": 164086415360, "source": "fineweb_hq", "phase": 2, "loss": 1.73140487074852, "ce_loss": 1.73140487074852, "logit_z_loss": 104.24940872192383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3328598737716675, "tokens_per_second": 9743665.39934518, "eta_seconds": 3685.477334475517, "data_wait_seconds": 1.8656253814697266e-05} {"step": 18420, "total_steps": 22439, "tokens": 164175544320, "source": "fineweb_hq", "phase": 2, "loss": 1.7420387268066406, "ce_loss": 1.7420387268066406, "logit_z_loss": 106.69975852966309, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3715188801288605, "tokens_per_second": 8767860.922642311, "eta_seconds": 4085.4809787750246, "data_wait_seconds": 1.7583370208740234e-05} {"step": 18430, "total_steps": 22439, "tokens": 164264673280, "source": "fineweb_hq", "phase": 2, "loss": 1.7169598639011383, "ce_loss": 1.7169598639011383, "logit_z_loss": 108.28219413757324, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3236575126647949, "tokens_per_second": 9977165.187655754, "eta_seconds": 3581.3579701185226, "data_wait_seconds": 2.294778823852539e-05} {"step": 18440, "total_steps": 22439, "tokens": 164353802240, "source": "fineweb_hq", "phase": 2, "loss": 1.7276869416236877, "ce_loss": 1.7276869416236877, "logit_z_loss": 112.6582145690918, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.347759485244751, "tokens_per_second": 9940309.672453202, "eta_seconds": 3585.6700926303865, "data_wait_seconds": 1.5676021575927734e-05} {"step": 18450, "total_steps": 22439, "tokens": 164442931200, "source": "fineweb_hq", "phase": 2, "loss": 1.7395675778388977, "ce_loss": 1.7395675778388977, "logit_z_loss": 109.01810836791992, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.316326379776001, "tokens_per_second": 8931410.83127971, "eta_seconds": 3980.730795574188, "data_wait_seconds": 2.0444393157958984e-05} {"step": 18460, "total_steps": 22439, "tokens": 164532060160, "source": "fineweb_hq", "phase": 2, "loss": 1.730341225862503, "ce_loss": 1.730341225862503, "logit_z_loss": 109.2951488494873, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31871241331100464, "tokens_per_second": 8836578.064509908, "eta_seconds": 4013.365006804466, "data_wait_seconds": 1.4781951904296875e-05} {"step": 18470, "total_steps": 22439, "tokens": 164621189120, "source": "fineweb_hq", "phase": 2, "loss": 1.7237332463264465, "ce_loss": 1.7237332463264465, "logit_z_loss": 107.49126434326172, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3174256980419159, "tokens_per_second": 9919324.409525178, "eta_seconds": 3566.2997562646865, "data_wait_seconds": 1.913309097290039e-05} {"step": 18480, "total_steps": 22439, "tokens": 164710318080, "source": "fineweb_hq", "phase": 2, "loss": 1.7297097742557526, "ce_loss": 1.7297097742557526, "logit_z_loss": 103.63557624816895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3436135947704315, "tokens_per_second": 10495028.774032008, "eta_seconds": 3362.178039121628, "data_wait_seconds": 1.6629695892333984e-05} {"step": 18490, "total_steps": 22439, "tokens": 164799447040, "source": "fineweb_hq", "phase": 2, "loss": 1.7673803269863129, "ce_loss": 1.7673803269863129, "logit_z_loss": 107.03047180175781, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.32857397198677063, "tokens_per_second": 7843929.659221234, "eta_seconds": 4487.167508268356, "data_wait_seconds": 1.7404556274414062e-05} {"step": 18500, "total_steps": 22439, "tokens": 164888576000, "source": "fineweb_hq", "phase": 2, "loss": 1.793746292591095, "ce_loss": 1.793746292591095, "logit_z_loss": 111.01614761352539, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29834669828414917, "tokens_per_second": 10559028.7028903, "eta_seconds": 3324.917313122749, "data_wait_seconds": 1.7523765563964844e-05} {"step": 18510, "total_steps": 22439, "tokens": 164977704960, "source": "fineweb_hq", "phase": 2, "loss": 1.8529208898544312, "ce_loss": 1.8529208898544312, "logit_z_loss": 101.78878784179688, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3301364481449127, "tokens_per_second": 9302818.185438346, "eta_seconds": 3764.318262052536, "data_wait_seconds": 1.6033649444580078e-05} {"step": 18520, "total_steps": 22439, "tokens": 165066833920, "source": "fineweb_hq", "phase": 2, "loss": 1.9735393226146698, "ce_loss": 1.9735393226146698, "logit_z_loss": 103.1303882598877, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3133184611797333, "tokens_per_second": 8439845.171666054, "eta_seconds": 4138.6587921381, "data_wait_seconds": 1.7583370208740234e-05} {"step": 18530, "total_steps": 22439, "tokens": 165155962880, "source": "fineweb_hq", "phase": 2, "loss": 1.9900164604187012, "ce_loss": 1.9900164604187012, "logit_z_loss": 96.7847843170166, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33746403455734253, "tokens_per_second": 6306340.247502891, "eta_seconds": 5524.679782032967, "data_wait_seconds": 1.3070167303085327} {"step": 18540, "total_steps": 22439, "tokens": 165245091840, "source": "fineweb_hq", "phase": 2, "loss": 1.982291966676712, "ce_loss": 1.982291966676712, "logit_z_loss": 90.8669548034668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31004205346107483, "tokens_per_second": 6105768.660401369, "eta_seconds": 5691.565376424789, "data_wait_seconds": 0.4258544445037842} {"step": 18550, "total_steps": 22439, "tokens": 165334220800, "source": "fineweb_hq", "phase": 2, "loss": 1.9812630712985992, "ce_loss": 1.9812630712985992, "logit_z_loss": 99.51958656311035, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3072567582130432, "tokens_per_second": 4418272.113326684, "eta_seconds": 7845.205468320846, "data_wait_seconds": 0.47436755895614624} {"step": 18560, "total_steps": 22439, "tokens": 165423349760, "source": "fineweb_hq", "phase": 2, "loss": 1.997081995010376, "ce_loss": 1.997081995010376, "logit_z_loss": 96.86809921264648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.38722893595695496, "tokens_per_second": 5431670.063944332, "eta_seconds": 6365.10008468628, "data_wait_seconds": 0.38899487257003784} {"step": 18570, "total_steps": 22439, "tokens": 165512478720, "source": "fineweb_hq", "phase": 2, "loss": 1.9966113865375519, "ce_loss": 1.9966113865375519, "logit_z_loss": 98.48329544067383, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3335217237472534, "tokens_per_second": 5246364.741105802, "eta_seconds": 6572.931224894523, "data_wait_seconds": 1.7583370208740234e-05} {"step": 18580, "total_steps": 22439, "tokens": 165601607680, "source": "fineweb_hq", "phase": 2, "loss": 1.9898335635662079, "ce_loss": 1.9898335635662079, "logit_z_loss": 93.63860702514648, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35912173986434937, "tokens_per_second": 5922669.312854525, "eta_seconds": 5807.3250163316725, "data_wait_seconds": 0.915230393409729} {"step": 18590, "total_steps": 22439, "tokens": 165690736640, "source": "fineweb_hq", "phase": 2, "loss": 1.9854616522789001, "ce_loss": 1.9854616522789001, "logit_z_loss": 94.55130195617676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3581237494945526, "tokens_per_second": 3530529.930157199, "eta_seconds": 9716.880293512344, "data_wait_seconds": 1.820290982723236} {"step": 18600, "total_steps": 22439, "tokens": 165779865600, "source": "fineweb_hq", "phase": 2, "loss": 1.9715295732021332, "ce_loss": 1.9715295732021332, "logit_z_loss": 99.05979347229004, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3692399263381958, "tokens_per_second": 5960723.5387498895, "eta_seconds": 5740.344694995881, "data_wait_seconds": 1.811981201171875e-05} {"step": 18610, "total_steps": 22439, "tokens": 165868994560, "source": "fineweb_hq", "phase": 2, "loss": 1.987697273492813, "ce_loss": 1.987697273492813, "logit_z_loss": 99.2496452331543, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31747275590896606, "tokens_per_second": 8871013.006002909, "eta_seconds": 3847.0779786825183, "data_wait_seconds": 1.7464160919189453e-05} {"step": 18620, "total_steps": 22439, "tokens": 165958123520, "source": "fineweb_hq", "phase": 2, "loss": 1.9904951751232147, "ce_loss": 1.9904951751232147, "logit_z_loss": 97.39540672302246, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3523496687412262, "tokens_per_second": 7215564.110878981, "eta_seconds": 4717.351173233986, "data_wait_seconds": 0.4309064745903015} {"step": 18630, "total_steps": 22439, "tokens": 166047252480, "source": "fineweb_hq", "phase": 2, "loss": 1.970940500497818, "ce_loss": 1.970940500497818, "logit_z_loss": 95.0477523803711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29188698530197144, "tokens_per_second": 7082766.209835761, "eta_seconds": 4793.214947128296, "data_wait_seconds": 0.5213354825973511} {"step": 18640, "total_steps": 22439, "tokens": 166136381440, "source": "fineweb_hq", "phase": 2, "loss": 2.0199347138404846, "ce_loss": 2.0199347138404846, "logit_z_loss": 98.56884002685547, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29053014516830444, "tokens_per_second": 9238101.851815177, "eta_seconds": 3665.2650563001635, "data_wait_seconds": 1.5795230865478516e-05} {"step": 18650, "total_steps": 22439, "tokens": 166225510400, "source": "fineweb_hq", "phase": 2, "loss": 2.015998423099518, "ce_loss": 2.015998423099518, "logit_z_loss": 96.55682373046875, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.31221091747283936, "tokens_per_second": 9113114.473427812, "eta_seconds": 3705.7542778015136, "data_wait_seconds": 1.9311904907226562e-05} {"step": 18660, "total_steps": 22439, "tokens": 166314639360, "source": "fineweb_hq", "phase": 2, "loss": 2.0007738173007965, "ce_loss": 2.0007738173007965, "logit_z_loss": 96.10343170166016, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33911991119384766, "tokens_per_second": 9893693.828516519, "eta_seconds": 3404.3739949703217, "data_wait_seconds": 2.008676528930664e-05} {"step": 18670, "total_steps": 22439, "tokens": 166403768320, "source": "fineweb_hq", "phase": 2, "loss": 1.997402161359787, "ce_loss": 1.997402161359787, "logit_z_loss": 95.64462661743164, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28740137815475464, "tokens_per_second": 8745286.610884853, "eta_seconds": 3841.2354584455493, "data_wait_seconds": 1.913309097290039e-05} {"step": 18680, "total_steps": 22439, "tokens": 166492897280, "source": "fineweb_hq", "phase": 2, "loss": 2.024332046508789, "ce_loss": 2.024332046508789, "logit_z_loss": 96.26777267456055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33070141077041626, "tokens_per_second": 9327029.68829393, "eta_seconds": 3592.0949309349057, "data_wait_seconds": 1.7702579498291016e-05} {"step": 18690, "total_steps": 22439, "tokens": 166582026240, "source": "fineweb_hq", "phase": 2, "loss": 1.9941217601299286, "ce_loss": 1.9941217601299286, "logit_z_loss": 94.1514949798584, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.354557603597641, "tokens_per_second": 9239590.998723159, "eta_seconds": 3616.442233061791, "data_wait_seconds": 0.27091270685195923} {"step": 18700, "total_steps": 22439, "tokens": 166671155200, "source": "fineweb_hq", "phase": 2, "loss": 2.0029087364673615, "ce_loss": 2.0029087364673615, "logit_z_loss": 95.7551498413086, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.29483482241630554, "tokens_per_second": 8111748.508551151, "eta_seconds": 4108.278025245666, "data_wait_seconds": 1.7464160919189453e-05} {"step": 18710, "total_steps": 22439, "tokens": 166760284160, "source": "fineweb_hq", "phase": 2, "loss": 1.9936915934085846, "ce_loss": 1.9936915934085846, "logit_z_loss": 96.2213191986084, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35166284441947937, "tokens_per_second": 9345352.130630257, "eta_seconds": 3556.440540647507, "data_wait_seconds": 0.2881588935852051} {"step": 18720, "total_steps": 22439, "tokens": 166849413120, "source": "fineweb_hq", "phase": 2, "loss": 2.0097727477550507, "ce_loss": 2.0097727477550507, "logit_z_loss": 97.52673721313477, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3371706008911133, "tokens_per_second": 9708738.167838188, "eta_seconds": 3414.1470962524418, "data_wait_seconds": 3.504753112792969e-05} {"step": 18730, "total_steps": 22439, "tokens": 166938542080, "source": "fineweb_hq", "phase": 2, "loss": 1.9984939694404602, "ce_loss": 1.9984939694404602, "logit_z_loss": 98.46711921691895, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3410572111606598, "tokens_per_second": 8889302.48316542, "eta_seconds": 3718.844231772423, "data_wait_seconds": 1.704692840576172e-05} {"step": 18740, "total_steps": 22439, "tokens": 167027671040, "source": "fineweb_hq", "phase": 2, "loss": 1.993867188692093, "ce_loss": 1.993867188692093, "logit_z_loss": 96.3643970489502, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3055460751056671, "tokens_per_second": 9632502.725517236, "eta_seconds": 3422.662130856514, "data_wait_seconds": 2.0503997802734375e-05} {"step": 18750, "total_steps": 22439, "tokens": 167116800000, "source": "fineweb_hq", "phase": 2, "loss": 1.9896749258041382, "ce_loss": 1.9896749258041382, "logit_z_loss": 93.3856430053711, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35746291279792786, "tokens_per_second": 9883767.965747844, "eta_seconds": 3326.6334719657893, "data_wait_seconds": 1.8596649169921875e-05} {"step": 18760, "total_steps": 22439, "tokens": 167205928960, "source": "fineweb_hq", "phase": 2, "loss": 1.9983131885528564, "ce_loss": 1.9983131885528564, "logit_z_loss": 92.59533882141113, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.4084186851978302, "tokens_per_second": 9450325.253125004, "eta_seconds": 3469.7794526338575, "data_wait_seconds": 1.5974044799804688e-05} {"step": 18770, "total_steps": 22439, "tokens": 167295057920, "source": "fineweb_hq", "phase": 2, "loss": 2.000869005918503, "ce_loss": 2.000869005918503, "logit_z_loss": 96.89505195617676, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3217791020870209, "tokens_per_second": 8363503.870908939, "eta_seconds": 3910.0137847423553, "data_wait_seconds": 2.5153160095214844e-05} {"step": 18780, "total_steps": 22439, "tokens": 167384186880, "source": "fineweb_hq", "phase": 2, "loss": 1.9805863201618195, "ce_loss": 1.9805863201618195, "logit_z_loss": 94.2093677520752, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3548106551170349, "tokens_per_second": 10002274.346023982, "eta_seconds": 3260.487098813057, "data_wait_seconds": 1.704692840576172e-05} {"step": 18790, "total_steps": 22439, "tokens": 167473315840, "source": "fineweb_hq", "phase": 2, "loss": 1.9929956197738647, "ce_loss": 1.9929956197738647, "logit_z_loss": 97.22968673706055, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3212241530418396, "tokens_per_second": 8954214.977782127, "eta_seconds": 3632.161790251732, "data_wait_seconds": 1.8835067749023438e-05} {"step": 18800, "total_steps": 22439, "tokens": 167562444800, "source": "fineweb_hq", "phase": 2, "loss": 1.9636682271957397, "ce_loss": 1.9636682271957397, "logit_z_loss": 98.33112907409668, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.318472683429718, "tokens_per_second": 8979264.525327561, "eta_seconds": 3612.1030238628387, "data_wait_seconds": 1.6033649444580078e-05} {"step": 18810, "total_steps": 22439, "tokens": 167651573760, "source": "fineweb_hq", "phase": 2, "loss": 1.9853626191616058, "ce_loss": 1.9853626191616058, "logit_z_loss": 101.1416187286377, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3103300631046295, "tokens_per_second": 8690196.132415216, "eta_seconds": 3721.9988008499145, "data_wait_seconds": 1.621246337890625e-05} {"step": 18820, "total_steps": 22439, "tokens": 167740702720, "source": "fineweb_hq", "phase": 2, "loss": 2.01407054066658, "ce_loss": 2.01407054066658, "logit_z_loss": 94.44103813171387, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35366091132164, "tokens_per_second": 10133062.112247434, "eta_seconds": 3183.220458602905, "data_wait_seconds": 1.6987323760986328e-05} {"step": 18830, "total_steps": 22439, "tokens": 167829831680, "source": "fineweb_hq", "phase": 2, "loss": 1.972678780555725, "ce_loss": 1.972678780555725, "logit_z_loss": 96.97567749023438, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3935280442237854, "tokens_per_second": 9712365.338096272, "eta_seconds": 3311.9266568183903, "data_wait_seconds": 1.6748905181884766e-05} {"step": 18840, "total_steps": 22439, "tokens": 167918960640, "source": "fineweb_hq", "phase": 2, "loss": 1.9516372084617615, "ce_loss": 1.9516372084617615, "logit_z_loss": 97.86978340148926, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3256843388080597, "tokens_per_second": 9413971.155569045, "eta_seconds": 3407.4369013786313, "data_wait_seconds": 2.1159648895263672e-05} {"step": 18850, "total_steps": 22439, "tokens": 168008089600, "source": "fineweb_hq", "phase": 2, "loss": 1.9791232645511627, "ce_loss": 1.9791232645511627, "logit_z_loss": 96.53302955627441, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.359151691198349, "tokens_per_second": 9205283.9204979, "eta_seconds": 3475.002402997017, "data_wait_seconds": 1.8477439880371094e-05} {"step": 18860, "total_steps": 22439, "tokens": 168097218560, "source": "fineweb_hq", "phase": 2, "loss": 1.9889809489250183, "ce_loss": 1.9889809489250183, "logit_z_loss": 97.84406852722168, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.35157471895217896, "tokens_per_second": 9090595.151170673, "eta_seconds": 3509.0392051935196, "data_wait_seconds": 1.5139579772949219e-05} {"step": 18870, "total_steps": 22439, "tokens": 168186347520, "source": "fineweb_hq", "phase": 2, "loss": 1.972695678472519, "ce_loss": 1.972695678472519, "logit_z_loss": 95.52171897888184, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3799366354942322, "tokens_per_second": 9645854.442100573, "eta_seconds": 3297.8028037786485, "data_wait_seconds": 2.1636486053466797e-05} {"step": 18880, "total_steps": 22439, "tokens": 168275476480, "source": "fineweb_hq", "phase": 2, "loss": 1.9586585760116577, "ce_loss": 1.9586585760116577, "logit_z_loss": 94.88632392883301, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.2844034433364868, "tokens_per_second": 9268025.458025595, "eta_seconds": 3422.62729074955, "data_wait_seconds": 1.6927719116210938e-05} {"step": 18890, "total_steps": 22439, "tokens": 168364605440, "source": "fineweb_hq", "phase": 2, "loss": 1.9854639768600464, "ce_loss": 1.9854639768600464, "logit_z_loss": 98.16592025756836, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3765071630477905, "tokens_per_second": 9193831.58892264, "eta_seconds": 3440.5533316612245, "data_wait_seconds": 2.014636993408203e-05} {"step": 18900, "total_steps": 22439, "tokens": 168453734400, "source": "fineweb_hq", "phase": 2, "loss": 1.9786675870418549, "ce_loss": 1.9786675870418549, "logit_z_loss": 94.61684226989746, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30032050609588623, "tokens_per_second": 9830178.020867378, "eta_seconds": 3208.765790104866, "data_wait_seconds": 1.7821788787841797e-05} {"step": 18910, "total_steps": 22439, "tokens": 168542863360, "source": "fineweb_hq", "phase": 2, "loss": 1.9725883901119232, "ce_loss": 1.9725883901119232, "logit_z_loss": 98.90067481994629, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28229963779449463, "tokens_per_second": 9057639.502390668, "eta_seconds": 3472.605635905266, "data_wait_seconds": 2.0444393157958984e-05} {"step": 18920, "total_steps": 22439, "tokens": 168631992320, "source": "fineweb_hq", "phase": 2, "loss": 2.0031856894493103, "ce_loss": 2.0031856894493103, "logit_z_loss": 95.10723495483398, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.34572985768318176, "tokens_per_second": 7338634.94242875, "eta_seconds": 4273.884894132614, "data_wait_seconds": 0.34526240825653076} {"step": 18930, "total_steps": 22439, "tokens": 168721121280, "source": "fineweb_hq", "phase": 2, "loss": 2.020111918449402, "ce_loss": 2.020111918449402, "logit_z_loss": 97.97975158691406, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.30732980370521545, "tokens_per_second": 10333544.521807106, "eta_seconds": 3026.585117816925, "data_wait_seconds": 1.5437602996826172e-05} {"step": 18940, "total_steps": 22439, "tokens": 168810250240, "source": "fineweb_hq", "phase": 2, "loss": 2.0464401841163635, "ce_loss": 2.0464401841163635, "logit_z_loss": 94.35844421386719, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3676729202270508, "tokens_per_second": 9020799.87353302, "eta_seconds": 3457.146100258827, "data_wait_seconds": 1.6808509826660156e-05} {"step": 18950, "total_steps": 22439, "tokens": 168899379200, "source": "fineweb_hq", "phase": 2, "loss": 2.0298156142234802, "ce_loss": 2.0298156142234802, "logit_z_loss": 96.04154205322266, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3128640055656433, "tokens_per_second": 6060887.015107051, "eta_seconds": 5130.782683539391, "data_wait_seconds": 0.34455639123916626} {"step": 18960, "total_steps": 22439, "tokens": 168988508160, "source": "fineweb_hq", "phase": 2, "loss": 2.0197598338127136, "ce_loss": 2.0197598338127136, "logit_z_loss": 98.17429161071777, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.37046676874160767, "tokens_per_second": 6031868.3072607, "eta_seconds": 5140.690015840531, "data_wait_seconds": 2.09808349609375e-05} {"step": 18970, "total_steps": 22439, "tokens": 169077637120, "source": "fineweb_hq", "phase": 2, "loss": 2.0244306325912476, "ce_loss": 2.0244306325912476, "logit_z_loss": 96.73675727844238, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3290812075138092, "tokens_per_second": 5659571.958787221, "eta_seconds": 5463.105063271523, "data_wait_seconds": 0.5082930326461792} {"step": 18980, "total_steps": 22439, "tokens": 169166766080, "source": "fineweb_hq", "phase": 2, "loss": 2.0143569111824036, "ce_loss": 2.0143569111824036, "logit_z_loss": 89.91248893737793, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3311729431152344, "tokens_per_second": 5973118.318961177, "eta_seconds": 5161.409102869034, "data_wait_seconds": 0.19732671976089478} {"step": 18990, "total_steps": 22439, "tokens": 169255895040, "source": "fineweb_hq", "phase": 2, "loss": 1.995511531829834, "ce_loss": 1.995511531829834, "logit_z_loss": 95.36063385009766, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.28671762347221375, "tokens_per_second": 6087721.95928547, "eta_seconds": 5049.60287437439, "data_wait_seconds": 1.901388168334961e-05} {"step": 19000, "total_steps": 22439, "tokens": 169345024000, "source": "fineweb_hq", "phase": 2, "loss": 2.017473876476288, "ce_loss": 2.017473876476288, "logit_z_loss": 94.40497016906738, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.4175923764705658, "tokens_per_second": 8011848.431392123, "eta_seconds": 3825.7650037288668, "data_wait_seconds": 1.4662742614746094e-05} {"step": 19010, "total_steps": 22439, "tokens": 169434152960, "source": "fineweb_hq", "phase": 2, "loss": 2.0089224874973297, "ce_loss": 2.0089224874973297, "logit_z_loss": 97.25529670715332, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.42458242177963257, "tokens_per_second": 7629371.7900076555, "eta_seconds": 4005.8763978481293, "data_wait_seconds": 0.26371580362319946} {"step": 19020, "total_steps": 22439, "tokens": 169523281920, "source": "fineweb_hq", "phase": 2, "loss": 1.9660462737083435, "ce_loss": 1.9660462737083435, "logit_z_loss": 95.92040634155273, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.343218058347702, "tokens_per_second": 9133596.163276374, "eta_seconds": 3336.384801697731, "data_wait_seconds": 1.7344951629638672e-05} {"step": 19030, "total_steps": 22439, "tokens": 169612410880, "source": "fineweb_hq", "phase": 2, "loss": 1.9708704352378845, "ce_loss": 1.9708704352378845, "logit_z_loss": 96.90866470336914, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3809452950954437, "tokens_per_second": 8557702.02306121, "eta_seconds": 3550.4931560039518, "data_wait_seconds": 0.45603108406066895} {"step": 19040, "total_steps": 22439, "tokens": 169701539840, "source": "fineweb_hq", "phase": 2, "loss": 1.8415059745311737, "ce_loss": 1.8415059745311737, "logit_z_loss": 102.65266799926758, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.376651793718338, "tokens_per_second": 9060993.62256187, "eta_seconds": 3343.44496486187, "data_wait_seconds": 1.6987323760986328e-05} {"step": 19050, "total_steps": 22439, "tokens": 169790668800, "source": "fineweb_hq", "phase": 2, "loss": 1.8293047547340393, "ce_loss": 1.8293047547340393, "logit_z_loss": 101.95938301086426, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3222925662994385, "tokens_per_second": 9051288.675644593, "eta_seconds": 3337.18276219368, "data_wait_seconds": 1.9669532775878906e-05} {"step": 19060, "total_steps": 22439, "tokens": 169879797760, "source": "fineweb_hq", "phase": 2, "loss": 1.814415603876114, "ce_loss": 1.814415603876114, "logit_z_loss": 106.60835647583008, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.3672824501991272, "tokens_per_second": 9649960.09089034, "eta_seconds": 3120.9119312763214, "data_wait_seconds": 3.11732292175293e-05} {"step": 19070, "total_steps": 22439, "tokens": 169968926720, "source": "fineweb_hq", "phase": 2, "loss": 1.8197243809700012, "ce_loss": 1.8197243809700012, "logit_z_loss": 109.8288345336914, "muon_lr": 0.07, "adamw_lr": 0.004, "grad_norm": 0.33823081851005554, "tokens_per_second": 10621130.950083543, "eta_seconds": 2827.151530766487, "data_wait_seconds": 1.6868114471435547e-05} {"step": 19080, "total_steps": 22439, "tokens": 170058055680, "source": "fineweb_hq", "phase": 2, "loss": 1.8115954399108887, "ce_loss": 1.8115954399108887, "logit_z_loss": 106.31680679321289, "muon_lr": 0.06999961843806778, "adamw_lr": 0.003999978196461015, "grad_norm": 0.3432227075099945, "tokens_per_second": 10445125.141346756, "eta_seconds": 2866.257441520691, "data_wait_seconds": 1.615285873413086e-05} {"step": 19090, "total_steps": 22439, "tokens": 170147184640, "source": "fineweb_hq", "phase": 2, "loss": 1.8042868077754974, "ce_loss": 1.8042868077754974, "logit_z_loss": 104.24834632873535, "muon_lr": 0.0699965659925261, "adamw_lr": 0.003999803771001491, "grad_norm": 0.3229518532752991, "tokens_per_second": 9998269.141846372, "eta_seconds": 2985.445608687401, "data_wait_seconds": 3.045797348022461e-05} {"step": 19100, "total_steps": 22439, "tokens": 170236313600, "source": "fineweb_hq", "phase": 2, "loss": 1.8192864060401917, "ce_loss": 1.8192864060401917, "logit_z_loss": 106.19583320617676, "muon_lr": 0.06999046136765774, "adamw_lr": 0.003999454935294728, "grad_norm": 0.3156251609325409, "tokens_per_second": 9834818.816730933, "eta_seconds": 3025.999797105789, "data_wait_seconds": 2.086162567138672e-05} {"step": 19110, "total_steps": 22439, "tokens": 170325442560, "source": "fineweb_hq", "phase": 2, "loss": 1.790729284286499, "ce_loss": 1.790729284286499, "logit_z_loss": 107.38431549072266, "muon_lr": 0.06998130509586954, "adamw_lr": 0.003998931719763974, "grad_norm": 0.3806309401988983, "tokens_per_second": 8863088.58748263, "eta_seconds": 3347.707798600197, "data_wait_seconds": 2.0265579223632812e-05} {"step": 19120, "total_steps": 22439, "tokens": 170414571520, "source": "fineweb_hq", "phase": 2, "loss": 1.8239244520664215, "ce_loss": 1.8239244520664215, "logit_z_loss": 106.17072868347168, "muon_lr": 0.06996909797571364, "adamw_lr": 0.003998234170040779, "grad_norm": 0.32472944259643555, "tokens_per_second": 9216156.546727402, "eta_seconds": 3209.78725502491, "data_wait_seconds": 1.7583370208740234e-05} {"step": 19130, "total_steps": 22439, "tokens": 170503700480, "source": "fineweb_hq", "phase": 2, "loss": 1.8479870855808258, "ce_loss": 1.8479870855808258, "logit_z_loss": 103.2541275024414, "muon_lr": 0.0699538410718179, "adamw_lr": 0.003997362346961023, "grad_norm": 0.36446040868759155, "tokens_per_second": 11197058.5214468, "eta_seconds": 2633.9750576019287, "data_wait_seconds": 1.537799835205078e-05} {"step": 19140, "total_steps": 22439, "tokens": 170592829440, "source": "fineweb_hq", "phase": 2, "loss": 1.8761783838272095, "ce_loss": 1.8761783838272095, "logit_z_loss": 106.23115158081055, "muon_lr": 0.0699355357147931, "adamw_lr": 0.0039963163265596055, "grad_norm": 0.2976381480693817, "tokens_per_second": 8193222.774113968, "eta_seconds": 3588.776323390007, "data_wait_seconds": 1.5974044799804688e-05} {"step": 19150, "total_steps": 22439, "tokens": 170681958400, "source": "fineweb_hq", "phase": 2, "loss": 1.9856676757335663, "ce_loss": 1.9856676757335663, "logit_z_loss": 100.51487159729004, "muon_lr": 0.06991418350111676, "adamw_lr": 0.0039950962000638145, "grad_norm": 0.3313066065311432, "tokens_per_second": 9567000.088491576, "eta_seconds": 3064.128219175339, "data_wait_seconds": 1.6510486602783203e-05} {"step": 19160, "total_steps": 22439, "tokens": 170771087360, "source": "fineweb_hq", "phase": 2, "loss": 1.980131834745407, "ce_loss": 1.980131834745407, "logit_z_loss": 97.70445823669434, "muon_lr": 0.06988978629299405, "adamw_lr": 0.003993702073885374, "grad_norm": 0.2938137352466583, "tokens_per_second": 8268835.493693119, "eta_seconds": 3534.401670742035, "data_wait_seconds": 2.104043960571289e-05} {"step": 19170, "total_steps": 22439, "tokens": 170860216320, "source": "fineweb_hq", "phase": 2, "loss": 1.9776781499385834, "ce_loss": 1.9776781499385834, "logit_z_loss": 98.32389450073242, "muon_lr": 0.06986234621819529, "adamw_lr": 0.0039921340696111585, "grad_norm": 0.349571168422699, "tokens_per_second": 9974126.281830028, "eta_seconds": 2921.1838912725448, "data_wait_seconds": 2.104043960571289e-05} {"step": 19180, "total_steps": 22439, "tokens": 170949345280, "source": "fineweb_hq", "phase": 2, "loss": 1.9868899285793304, "ce_loss": 1.9868899285793304, "logit_z_loss": 95.63092613220215, "muon_lr": 0.06983186566987037, "adamw_lr": 0.003990392323992592, "grad_norm": 0.30252572894096375, "tokens_per_second": 10277359.966886703, "eta_seconds": 2826.3219501495364, "data_wait_seconds": 1.710653305053711e-05} {"step": 19190, "total_steps": 22439, "tokens": 171038474240, "source": "fineweb_hq", "phase": 2, "loss": 1.9904397130012512, "ce_loss": 1.9904397130012512, "logit_z_loss": 93.9439525604248, "muon_lr": 0.0697983473063401, "adamw_lr": 0.00398847698893372, "grad_norm": 0.36928847432136536, "tokens_per_second": 8323464.758445735, "eta_seconds": 3479.0799197673796, "data_wait_seconds": 1.8298625946044922e-05} {"step": 19200, "total_steps": 22439, "tokens": 171127603200, "source": "fineweb_hq", "phase": 2, "loss": 1.981736421585083, "ce_loss": 1.981736421585083, "logit_z_loss": 99.16025352478027, "muon_lr": 0.06976179405086437, "adamw_lr": 0.003986388231477963, "grad_norm": 0.32141637802124023, "tokens_per_second": 9936173.813873721, "eta_seconds": 2905.43127412796, "data_wait_seconds": 1.5556812286376953e-05} {"step": 19210, "total_steps": 22439, "tokens": 171216732160, "source": "fineweb_hq", "phase": 2, "loss": 1.9831019043922424, "ce_loss": 1.9831019043922424, "logit_z_loss": 99.28917503356934, "muon_lr": 0.06972220909138707, "adamw_lr": 0.003984126233793546, "grad_norm": 0.32245954871177673, "tokens_per_second": 9101676.787661877, "eta_seconds": 3162.0262788295745, "data_wait_seconds": 2.1636486053466797e-05} {"step": 19220, "total_steps": 22439, "tokens": 171305861120, "source": "fineweb_hq", "phase": 2, "loss": 2.010662853717804, "ce_loss": 2.010662853717804, "logit_z_loss": 94.84764862060547, "muon_lr": 0.06967959588025824, "adamw_lr": 0.003981691193157614, "grad_norm": 0.3678632378578186, "tokens_per_second": 8592753.694418402, "eta_seconds": 3338.931062650681, "data_wait_seconds": 1.5079975128173828e-05} {"step": 19230, "total_steps": 22439, "tokens": 171394990080, "source": "fineweb_hq", "phase": 2, "loss": 1.991280049085617, "ce_loss": 1.991280049085617, "logit_z_loss": 98.23171043395996, "muon_lr": 0.06963395813393286, "adamw_lr": 0.00397908332193902, "grad_norm": 0.31219643354415894, "tokens_per_second": 9025223.48481673, "eta_seconds": 3169.0609448194505, "data_wait_seconds": 1.71661376953125e-05} {"step": 19240, "total_steps": 22439, "tokens": 171484119040, "source": "fineweb_hq", "phase": 2, "loss": 1.9902754127979279, "ce_loss": 1.9902754127979279, "logit_z_loss": 94.4031810760498, "muon_lr": 0.06958529983264676, "adamw_lr": 0.003976302847579815, "grad_norm": 0.3126307725906372, "tokens_per_second": 10346231.37999964, "eta_seconds": 2755.8202843904496, "data_wait_seconds": 1.9669532775878906e-05} {"step": 19250, "total_steps": 22439, "tokens": 171573248000, "source": "fineweb_hq", "phase": 2, "loss": 1.9907587468624115, "ce_loss": 1.9907587468624115, "logit_z_loss": 97.6782283782959, "muon_lr": 0.06953362522006948, "adamw_lr": 0.003973350012575399, "grad_norm": 0.3245856463909149, "tokens_per_second": 8155450.351013346, "eta_seconds": 3485.1815804958346, "data_wait_seconds": 1.913309097290039e-05} {"step": 19260, "total_steps": 22439, "tokens": 171662376960, "source": "fineweb_hq", "phase": 2, "loss": 2.0038043558597565, "ce_loss": 2.0038043558597565, "logit_z_loss": 96.15466690063477, "muon_lr": 0.06947893880293417, "adamw_lr": 0.003970225074453381, "grad_norm": 0.3840566873550415, "tokens_per_second": 9899792.99034487, "eta_seconds": 2862.0897842645645, "data_wait_seconds": 1.6748905181884766e-05} {"step": 19270, "total_steps": 22439, "tokens": 171751505920, "source": "fineweb_hq", "phase": 2, "loss": 2.002715051174164, "ce_loss": 2.002715051174164, "logit_z_loss": 97.47039413452148, "muon_lr": 0.06942124535064453, "adamw_lr": 0.003966928305751116, "grad_norm": 0.331316202878952, "tokens_per_second": 8771835.491537767, "eta_seconds": 3219.9609136819836, "data_wait_seconds": 1.5556812286376953e-05} {"step": 19280, "total_steps": 22439, "tokens": 171840634880, "source": "fineweb_hq", "phase": 2, "loss": 2.007376551628113, "ce_loss": 2.007376551628113, "logit_z_loss": 92.2960205078125, "muon_lr": 0.06936054989485893, "adamw_lr": 0.003963459993991938, "grad_norm": 0.34761422872543335, "tokens_per_second": 8102116.613455535, "eta_seconds": 3475.1213549852373, "data_wait_seconds": 1.7642974853515625e-05} {"step": 19290, "total_steps": 22439, "tokens": 171929763840, "source": "fineweb_hq", "phase": 2, "loss": 1.9922126531600952, "ce_loss": 1.9922126531600952, "logit_z_loss": 95.15262794494629, "muon_lr": 0.0692968577290514, "adamw_lr": 0.00395982044166008, "grad_norm": 0.33466118574142456, "tokens_per_second": 10150859.996643297, "eta_seconds": 2764.9587831258773, "data_wait_seconds": 1.5676021575927734e-05} {"step": 19300, "total_steps": 22439, "tokens": 172018892800, "source": "fineweb_hq", "phase": 2, "loss": 1.956406444311142, "ce_loss": 1.956406444311142, "logit_z_loss": 102.03507232666016, "muon_lr": 0.0692301744080502, "adamw_lr": 0.003956009966174297, "grad_norm": 0.29166167974472046, "tokens_per_second": 7579696.697412474, "eta_seconds": 3691.1213813543322, "data_wait_seconds": 1.7821788787841797e-05} {"step": 19310, "total_steps": 22439, "tokens": 172108021760, "source": "fineweb_hq", "phase": 2, "loss": 1.9349212050437927, "ce_loss": 1.9349212050437927, "logit_z_loss": 98.30118179321289, "muon_lr": 0.06916050574755313, "adamw_lr": 0.003952028899860178, "grad_norm": 0.3933544456958771, "tokens_per_second": 8490961.62544855, "eta_seconds": 3284.486824250221, "data_wait_seconds": 1.9311904907226562e-05} {"step": 19320, "total_steps": 22439, "tokens": 172197150720, "source": "fineweb_hq", "phase": 2, "loss": 1.9356444478034973, "ce_loss": 1.9356444478034973, "logit_z_loss": 101.07486343383789, "muon_lr": 0.06908785782362052, "adamw_lr": 0.0039478775899211725, "grad_norm": 0.32795894145965576, "tokens_per_second": 10006939.534098547, "eta_seconds": 2778.0044567346577, "data_wait_seconds": 1.7404556274414062e-05} {"step": 19330, "total_steps": 22439, "tokens": 172286279680, "source": "fineweb_hq", "phase": 2, "loss": 1.9443558156490326, "ce_loss": 1.9443558156490326, "logit_z_loss": 100.4367790222168, "muon_lr": 0.0690122369721452, "adamw_lr": 0.003943556398408297, "grad_norm": 0.404300332069397, "tokens_per_second": 8138365.985517549, "eta_seconds": 3404.884188461304, "data_wait_seconds": 1.9431114196777344e-05} {"step": 19340, "total_steps": 22439, "tokens": 172375408640, "source": "fineweb_hq", "phase": 2, "loss": 1.9220384061336517, "ce_loss": 1.9220384061336517, "logit_z_loss": 96.64208984375, "muon_lr": 0.06893364978829995, "adamw_lr": 0.003939065702188568, "grad_norm": 0.3583891987800598, "tokens_per_second": 10645137.34948992, "eta_seconds": 2594.711913728714, "data_wait_seconds": 2.014636993408203e-05} {"step": 19350, "total_steps": 22439, "tokens": 172464537600, "source": "fineweb_hq", "phase": 2, "loss": 1.9365795254707336, "ce_loss": 1.9365795254707336, "logit_z_loss": 103.13103103637695, "muon_lr": 0.06885210312596231, "adamw_lr": 0.003934405892912132, "grad_norm": 0.3244110345840454, "tokens_per_second": 8403431.135333734, "eta_seconds": 3276.2731437444686, "data_wait_seconds": 1.913309097290039e-05} {"step": 19360, "total_steps": 22439, "tokens": 172553666560, "source": "fineweb_hq", "phase": 2, "loss": 1.9244379699230194, "ce_loss": 1.9244379699230194, "logit_z_loss": 100.62914657592773, "muon_lr": 0.06876760409711685, "adamw_lr": 0.003929577376978105, "grad_norm": 0.3278604745864868, "tokens_per_second": 10570189.080732115, "eta_seconds": 2596.2455897808077, "data_wait_seconds": 1.8596649169921875e-05} {"step": 19370, "total_steps": 22439, "tokens": 172642795520, "source": "fineweb_hq", "phase": 2, "loss": 1.9037951231002808, "ce_loss": 1.9037951231002808, "logit_z_loss": 99.67067909240723, "muon_lr": 0.06868016007123487, "adamw_lr": 0.003924580575499135, "grad_norm": 0.2757795751094818, "tokens_per_second": 8682488.68444071, "eta_seconds": 3150.442093062401, "data_wait_seconds": 1.8537044525146484e-05} {"step": 19380, "total_steps": 22439, "tokens": 172731924480, "source": "fineweb_hq", "phase": 2, "loss": 1.930611789226532, "ce_loss": 1.930611789226532, "logit_z_loss": 102.77549362182617, "muon_lr": 0.0685897786746317, "adamw_lr": 0.003919415924264669, "grad_norm": 0.37435832619667053, "tokens_per_second": 10160507.672765262, "eta_seconds": 2683.384506177902, "data_wait_seconds": 1.7583370208740234e-05} {"step": 19390, "total_steps": 22439, "tokens": 172821053440, "source": "fineweb_hq", "phase": 2, "loss": 1.9116033911705017, "ce_loss": 1.9116033911705017, "logit_z_loss": 103.38683891296387, "muon_lr": 0.06849646778980163, "adamw_lr": 0.00391408387370295, "grad_norm": 0.3588482737541199, "tokens_per_second": 8607059.317463707, "eta_seconds": 3157.340841007233, "data_wait_seconds": 1.704692840576172e-05} {"step": 19400, "total_steps": 22439, "tokens": 172910182400, "source": "fineweb_hq", "phase": 2, "loss": 1.9180322587490082, "ce_loss": 1.9180322587490082, "logit_z_loss": 102.59267234802246, "muon_lr": 0.06840023555473031, "adamw_lr": 0.003908584888841732, "grad_norm": 0.32407161593437195, "tokens_per_second": 9185864.37740006, "eta_seconds": 2948.692668557167, "data_wait_seconds": 0.15834635496139526} {"step": 19410, "total_steps": 22439, "tokens": 172999311360, "source": "fineweb_hq", "phase": 2, "loss": 1.9428526163101196, "ce_loss": 1.9428526163101196, "logit_z_loss": 96.33477020263672, "muon_lr": 0.06830109036218518, "adamw_lr": 0.003902919449267724, "grad_norm": 0.43458402156829834, "tokens_per_second": 8852409.133024588, "eta_seconds": 3049.696594262123, "data_wait_seconds": 1.71661376953125e-05} {"step": 19420, "total_steps": 22439, "tokens": 173088440320, "source": "fineweb_hq", "phase": 2, "loss": 1.9612203538417816, "ce_loss": 1.9612203538417816, "logit_z_loss": 99.41912269592285, "muon_lr": 0.06819904085898337, "adamw_lr": 0.003897088049084764, "grad_norm": 0.38826051354408264, "tokens_per_second": 8820304.44660908, "eta_seconds": 3050.692091965675, "data_wait_seconds": 0.5098279714584351} {"step": 19430, "total_steps": 22439, "tokens": 173177569280, "source": "fineweb_hq", "phase": 2, "loss": 1.9692934453487396, "ce_loss": 1.9692934453487396, "logit_z_loss": 93.93903732299805, "muon_lr": 0.06809409594523767, "adamw_lr": 0.0038910911968707243, "grad_norm": 0.3337586522102356, "tokens_per_second": 9949211.293054841, "eta_seconds": 2695.5809133052826, "data_wait_seconds": 1.615285873413086e-05} {"step": 19440, "total_steps": 22439, "tokens": 173266698240, "source": "fineweb_hq", "phase": 2, "loss": 1.9974434077739716, "ce_loss": 1.9974434077739716, "logit_z_loss": 95.56488609313965, "muon_lr": 0.06798626477358027, "adamw_lr": 0.0038849294156331577, "grad_norm": 0.3681563138961792, "tokens_per_second": 8405053.16452627, "eta_seconds": 3180.202977991104, "data_wait_seconds": 2.092123031616211e-05} {"step": 19450, "total_steps": 22439, "tokens": 173355827200, "source": "fineweb_hq", "phase": 2, "loss": 1.9871771931648254, "ce_loss": 1.9871771931648254, "logit_z_loss": 100.41986656188965, "muon_lr": 0.06787555674836449, "adamw_lr": 0.003878603242763685, "grad_norm": 0.3114509880542755, "tokens_per_second": 9966454.740391435, "eta_seconds": 2673.031367516518, "data_wait_seconds": 2.5212764739990234e-05} {"step": 19460, "total_steps": 22439, "tokens": 173444956160, "source": "fineweb_hq", "phase": 2, "loss": 1.9999180138111115, "ce_loss": 1.9999180138111115, "logit_z_loss": 94.59343338012695, "muon_lr": 0.06776198152484472, "adamw_lr": 0.0038721132299911263, "grad_norm": 0.3073788285255432, "tokens_per_second": 10175163.865516474, "eta_seconds": 2609.443693971634, "data_wait_seconds": 1.8477439880371094e-05} {"step": 19470, "total_steps": 22439, "tokens": 173534085120, "source": "fineweb_hq", "phase": 2, "loss": 1.9917677640914917, "ce_loss": 1.9917677640914917, "logit_z_loss": 97.6484146118164, "muon_lr": 0.06764554900833418, "adamw_lr": 0.003865459943333382, "grad_norm": 0.32041773200035095, "tokens_per_second": 8071573.74880357, "eta_seconds": 3278.4670062541963, "data_wait_seconds": 1.6570091247558594e-05} {"step": 19480, "total_steps": 22439, "tokens": 173623214080, "source": "fineweb_hq", "phase": 2, "loss": 2.007250279188156, "ce_loss": 2.007250279188156, "logit_z_loss": 98.85545539855957, "muon_lr": 0.0675262693533412, "adamw_lr": 0.003858643963048069, "grad_norm": 0.3199550211429596, "tokens_per_second": 10351366.614703353, "eta_seconds": 2547.8045794010163, "data_wait_seconds": 1.722574234008789e-05} {"step": 19490, "total_steps": 22439, "tokens": 173712343040, "source": "fineweb_hq", "phase": 2, "loss": 2.020092725753784, "ce_loss": 2.020092725753784, "logit_z_loss": 97.80499458312988, "muon_lr": 0.0674041529626835, "adamw_lr": 0.003851665883581914, "grad_norm": 0.3661147654056549, "tokens_per_second": 9236175.258416226, "eta_seconds": 2845.7808095455166, "data_wait_seconds": 1.6689300537109375e-05} {"step": 19500, "total_steps": 22439, "tokens": 173801472000, "source": "fineweb_hq", "phase": 2, "loss": 1.9920507669448853, "ce_loss": 1.9920507669448853, "logit_z_loss": 95.1522045135498, "muon_lr": 0.06727921048658096, "adamw_lr": 0.0038445263135189114, "grad_norm": 0.37789759039878845, "tokens_per_second": 9417165.97574693, "eta_seconds": 2781.6225615501403, "data_wait_seconds": 1.5795230865478516e-05} {"step": 19510, "total_steps": 22439, "tokens": 173890600960, "source": "fineweb_hq", "phase": 2, "loss": 2.0078954100608826, "ce_loss": 2.0078954100608826, "logit_z_loss": 96.09622192382812, "muon_lr": 0.06715145282172677, "adamw_lr": 0.0038372258755272437, "grad_norm": 0.39966803789138794, "tokens_per_second": 8420611.420606073, "eta_seconds": 3100.234778690338, "data_wait_seconds": 1.7583370208740234e-05} {"step": 19520, "total_steps": 22439, "tokens": 173979729920, "source": "fineweb_hq", "phase": 2, "loss": 2.0032006204128265, "ce_loss": 2.0032006204128265, "logit_z_loss": 93.53397369384766, "muon_lr": 0.06702089111033711, "adamw_lr": 0.0038297652063049776, "grad_norm": 0.3665102422237396, "tokens_per_second": 10205999.502737228, "eta_seconds": 2549.161737370491, "data_wait_seconds": 1.5914440155029297e-05} {"step": 19530, "total_steps": 22439, "tokens": 174068858880, "source": "fineweb_hq", "phase": 2, "loss": 2.0087883174419403, "ce_loss": 2.0087883174419403, "logit_z_loss": 98.91171455383301, "muon_lr": 0.06688753673917937, "adamw_lr": 0.003822144956524535, "grad_norm": 0.3983410596847534, "tokens_per_second": 7890800.593682166, "eta_seconds": 3285.8027719974516, "data_wait_seconds": 1.9490718841552734e-05} {"step": 19540, "total_steps": 22439, "tokens": 174157987840, "source": "fineweb_hq", "phase": 2, "loss": 2.004176527261734, "ce_loss": 2.004176527261734, "logit_z_loss": 95.4532470703125, "muon_lr": 0.06675140133857907, "adamw_lr": 0.0038143657907759466, "grad_norm": 0.3351048529148102, "tokens_per_second": 10030181.004547568, "eta_seconds": 2576.0737011909487, "data_wait_seconds": 1.7821788787841797e-05} {"step": 19550, "total_steps": 22439, "tokens": 174247116800, "source": "fineweb_hq", "phase": 2, "loss": 1.9885312616825104, "ce_loss": 1.9885312616825104, "logit_z_loss": 92.02595138549805, "muon_lr": 0.06661249678140556, "adamw_lr": 0.0038064283875088884, "grad_norm": 0.3306865096092224, "tokens_per_second": 8573899.901903128, "eta_seconds": 3003.2257010936733, "data_wait_seconds": 1.4781951904296875e-05} {"step": 19560, "total_steps": 22439, "tokens": 174336245760, "source": "fineweb_hq", "phase": 2, "loss": 1.9839977025985718, "ce_loss": 1.9839977025985718, "logit_z_loss": 101.25559997558594, "muon_lr": 0.06647083518203649, "adamw_lr": 0.0037983334389735134, "grad_norm": 0.34344813227653503, "tokens_per_second": 9498528.902057337, "eta_seconds": 2701.4949208021167, "data_wait_seconds": 2.0742416381835938e-05} {"step": 19570, "total_steps": 22439, "tokens": 174425374720, "source": "fineweb_hq", "phase": 2, "loss": 2.0125721991062164, "ce_loss": 2.0125721991062164, "logit_z_loss": 97.73648452758789, "muon_lr": 0.06632642889530135, "adamw_lr": 0.0037900816511600775, "grad_norm": 0.32962390780448914, "tokens_per_second": 8376401.411692941, "eta_seconds": 3052.754681539536, "data_wait_seconds": 1.8894672393798828e-05} {"step": 19580, "total_steps": 22439, "tokens": 174514503680, "source": "fineweb_hq", "phase": 2, "loss": 2.00698584318161, "ce_loss": 2.00698584318161, "logit_z_loss": 93.60843276977539, "muon_lr": 0.06617929051540392, "adamw_lr": 0.0037816737437373666, "grad_norm": 0.2984445095062256, "tokens_per_second": 8812773.009522965, "eta_seconds": 2891.481448173523, "data_wait_seconds": 1.8298625946044922e-05} {"step": 19590, "total_steps": 22439, "tokens": 174603632640, "source": "fineweb_hq", "phase": 2, "loss": 2.0014726519584656, "ce_loss": 2.0014726519584656, "logit_z_loss": 97.14739799499512, "muon_lr": 0.06602943287482382, "adamw_lr": 0.0037731104499899326, "grad_norm": 0.312802255153656, "tokens_per_second": 10996148.945512442, "eta_seconds": 2309.248522353172, "data_wait_seconds": 1.9311904907226562e-05} {"step": 19600, "total_steps": 22439, "tokens": 174692761600, "source": "fineweb_hq", "phase": 2, "loss": 1.9961905479431152, "ce_loss": 1.9961905479431152, "logit_z_loss": 95.27328300476074, "muon_lr": 0.06587686904319746, "adamw_lr": 0.003764392516754141, "grad_norm": 0.32714709639549255, "tokens_per_second": 8451840.987512216, "eta_seconds": 2993.8698304176332, "data_wait_seconds": 1.537799835205078e-05} {"step": 19610, "total_steps": 22439, "tokens": 174781890560, "source": "fineweb_hq", "phase": 2, "loss": 2.0066860914230347, "ce_loss": 2.0066860914230347, "logit_z_loss": 95.27567481994629, "muon_lr": 0.06572161232617814, "adamw_lr": 0.0037555207043530364, "grad_norm": 0.3989483118057251, "tokens_per_second": 9394212.591067966, "eta_seconds": 2684.05494761467, "data_wait_seconds": 1.7523765563964844e-05} {"step": 19620, "total_steps": 22439, "tokens": 174871019520, "source": "fineweb_hq", "phase": 2, "loss": 1.991454839706421, "ce_loss": 1.991454839706421, "logit_z_loss": 91.48034286499023, "muon_lr": 0.06556367626427555, "adamw_lr": 0.003746495786530031, "grad_norm": 0.2970179617404938, "tokens_per_second": 8303240.967105117, "eta_seconds": 3025.981532216072, "data_wait_seconds": 2.0205974578857422e-05} {"step": 19630, "total_steps": 22439, "tokens": 174960148480, "source": "fineweb_hq", "phase": 2, "loss": 1.981344848871231, "ce_loss": 1.981344848871231, "logit_z_loss": 98.25697326660156, "muon_lr": 0.06540307463167494, "adamw_lr": 0.0037373185503814252, "grad_norm": 0.35564327239990234, "tokens_per_second": 10067382.412217127, "eta_seconds": 2486.875320601463, "data_wait_seconds": 2.1219253540039062e-05} {"step": 19640, "total_steps": 22439, "tokens": 175049277440, "source": "fineweb_hq", "phase": 2, "loss": 1.9723089039325714, "ce_loss": 1.9723089039325714, "logit_z_loss": 98.7834415435791, "muon_lr": 0.0652398214350358, "adamw_lr": 0.00372798979628776, "grad_norm": 0.33393755555152893, "tokens_per_second": 9085774.006620882, "eta_seconds": 2745.7425075531005, "data_wait_seconds": 2.092123031616211e-05} {"step": 19650, "total_steps": 22439, "tokens": 175138406400, "source": "fineweb_hq", "phase": 2, "loss": 2.0165835916996, "ce_loss": 2.0165835916996, "logit_z_loss": 93.70169067382812, "muon_lr": 0.06507393091227028, "adamw_lr": 0.0037185103378440153, "grad_norm": 0.4647543132305145, "tokens_per_second": 9257890.543828143, "eta_seconds": 2685.0681401252746, "data_wait_seconds": 2.181529998779297e-05} {"step": 19660, "total_steps": 22439, "tokens": 175227535360, "source": "fineweb_hq", "phase": 2, "loss": 1.9912970960140228, "ce_loss": 1.9912970960140228, "logit_z_loss": 90.95748710632324, "muon_lr": 0.06490541753130141, "adamw_lr": 0.003708881001788652, "grad_norm": 0.3512067496776581, "tokens_per_second": 9456474.21767216, "eta_seconds": 2619.2571791410446, "data_wait_seconds": 1.7821788787841797e-05} {"step": 19670, "total_steps": 22439, "tokens": 175316664320, "source": "fineweb_hq", "phase": 2, "loss": 1.971030205488205, "ce_loss": 1.971030205488205, "logit_z_loss": 98.85235595703125, "muon_lr": 0.06473429598880139, "adamw_lr": 0.0036991026279315077, "grad_norm": 0.3620174825191498, "tokens_per_second": 9874667.653546447, "eta_seconds": 2499.305281949043, "data_wait_seconds": 2.396106719970703e-05} {"step": 19680, "total_steps": 22439, "tokens": 175405793280, "source": "fineweb_hq", "phase": 2, "loss": 1.98936727643013, "ce_loss": 1.98936727643013, "logit_z_loss": 96.70642852783203, "muon_lr": 0.06456058120890974, "adamw_lr": 0.003689176069080556, "grad_norm": 0.29864001274108887, "tokens_per_second": 8887392.261896458, "eta_seconds": 2766.9173745632174, "data_wait_seconds": 1.823902130126953e-05} {"step": 19690, "total_steps": 22439, "tokens": 175494922240, "source": "fineweb_hq", "phase": 2, "loss": 1.9724730551242828, "ce_loss": 1.9724730551242828, "logit_z_loss": 100.79594230651855, "muon_lr": 0.0643842883419318, "adamw_lr": 0.0036791021909675314, "grad_norm": 0.3698233664035797, "tokens_per_second": 10028661.539239341, "eta_seconds": 2443.1526588201523, "data_wait_seconds": 1.7464160919189453e-05} {"step": 19700, "total_steps": 22439, "tokens": 175584051200, "source": "fineweb_hq", "phase": 2, "loss": 2.0018686056137085, "ce_loss": 2.0018686056137085, "logit_z_loss": 97.60370254516602, "muon_lr": 0.06420543276301735, "adamw_lr": 0.00366888187217242, "grad_norm": 0.27720940113067627, "tokens_per_second": 8800866.81945009, "eta_seconds": 2773.86564810276, "data_wait_seconds": 0.16173052787780762} {"step": 19710, "total_steps": 22439, "tokens": 175673180160, "source": "fineweb_hq", "phase": 2, "loss": 1.9875790774822235, "ce_loss": 1.9875790774822235, "logit_z_loss": 96.14850807189941, "muon_lr": 0.0640240300708197, "adamw_lr": 0.0036585160040468402, "grad_norm": 0.35521429777145386, "tokens_per_second": 9749814.102533013, "eta_seconds": 2494.7443026304245, "data_wait_seconds": 1.823902130126953e-05} {"step": 19720, "total_steps": 22439, "tokens": 175762309120, "source": "fineweb_hq", "phase": 2, "loss": 1.978615790605545, "ce_loss": 1.978615790605545, "logit_z_loss": 96.73612785339355, "muon_lr": 0.06384009608613532, "adamw_lr": 0.003648005490636304, "grad_norm": 0.30277007818222046, "tokens_per_second": 9652237.643871957, "eta_seconds": 2510.730166220665, "data_wait_seconds": 0.040255069732666016} {"step": 19730, "total_steps": 22439, "tokens": 175851438080, "source": "fineweb_hq", "phase": 2, "loss": 1.9813168942928314, "ce_loss": 1.9813168942928314, "logit_z_loss": 100.83143043518066, "muon_lr": 0.06365364685052398, "adamw_lr": 0.00363735124860137, "grad_norm": 0.3035475015640259, "tokens_per_second": 8569255.159907652, "eta_seconds": 2817.6352335691454, "data_wait_seconds": 1.8358230590820312e-05} {"step": 19740, "total_steps": 22439, "tokens": 175940567040, "source": "fineweb_hq", "phase": 2, "loss": 1.9735566973686218, "ce_loss": 1.9735566973686218, "logit_z_loss": 97.95806694030762, "muon_lr": 0.06346469862490975, "adamw_lr": 0.0036265542071376995, "grad_norm": 0.3591097295284271, "tokens_per_second": 10294995.991535626, "eta_seconds": 2336.6600942611694, "data_wait_seconds": 1.5735626220703125e-05} {"step": 19750, "total_steps": 22439, "tokens": 176029696000, "source": "fineweb_hq", "phase": 2, "loss": 1.979945957660675, "ce_loss": 1.979945957660675, "logit_z_loss": 99.81876373291016, "muon_lr": 0.0632732678881628, "adamw_lr": 0.003615615307895017, "grad_norm": 0.266200453042984, "tokens_per_second": 8797283.656927874, "eta_seconds": 2724.338361549377, "data_wait_seconds": 1.6987323760986328e-05} {"step": 19760, "total_steps": 22439, "tokens": 176118824960, "source": "fineweb_hq", "phase": 2, "loss": 1.9740092158317566, "ce_loss": 1.9740092158317566, "logit_z_loss": 93.13092422485352, "muon_lr": 0.06307937133566228, "adamw_lr": 0.0036045355048949877, "grad_norm": 0.3467254340648651, "tokens_per_second": 9031150.276670178, "eta_seconds": 2643.921056842804, "data_wait_seconds": 1.7464160919189453e-05} {"step": 19770, "total_steps": 22439, "tokens": 176207953920, "source": "fineweb_hq", "phase": 2, "loss": 1.9817664623260498, "ce_loss": 1.9817664623260498, "logit_z_loss": 96.25656127929688, "muon_lr": 0.06288302587784018, "adamw_lr": 0.0035933157644480102, "grad_norm": 0.341808944940567, "tokens_per_second": 8288598.884720207, "eta_seconds": 2870.0290308237077, "data_wait_seconds": 0.3086075782775879} {"step": 19780, "total_steps": 22439, "tokens": 176297082880, "source": "fineweb_hq", "phase": 2, "loss": 1.9727942049503326, "ce_loss": 1.9727942049503326, "logit_z_loss": 100.89604568481445, "muon_lr": 0.06268424863870652, "adamw_lr": 0.003581957065068943, "grad_norm": 0.2886621057987213, "tokens_per_second": 8984774.772270946, "eta_seconds": 2637.7278301000597, "data_wait_seconds": 0.23426759243011475} {"step": 19790, "total_steps": 22439, "tokens": 176386211840, "source": "fineweb_hq", "phase": 2, "loss": 1.9756250381469727, "ce_loss": 1.9756250381469727, "logit_z_loss": 99.3545036315918, "muon_lr": 0.06248305695435593, "adamw_lr": 0.003570460397391767, "grad_norm": 0.3333895206451416, "tokens_per_second": 7230756.135784593, "eta_seconds": 3265.2548448085786, "data_wait_seconds": 0.6596333384513855} {"step": 19800, "total_steps": 22439, "tokens": 176475340800, "source": "fineweb_hq", "phase": 2, "loss": 1.9855551719665527, "ce_loss": 1.9855551719665527, "logit_z_loss": 101.0711669921875, "muon_lr": 0.06227946837145571, "adamw_lr": 0.003558826764083183, "grad_norm": 0.3963225781917572, "tokens_per_second": 8723614.971150862, "eta_seconds": 2696.259821391106, "data_wait_seconds": 1.9609928131103516e-05} {"step": 19810, "total_steps": 22439, "tokens": 176564469760, "source": "fineweb_hq", "phase": 2, "loss": 1.9546213150024414, "ce_loss": 1.9546213150024414, "logit_z_loss": 99.74259757995605, "muon_lr": 0.06207350064571549, "adamw_lr": 0.0035470571797551705, "grad_norm": 0.3589343726634979, "tokens_per_second": 8491655.581016244, "eta_seconds": 2759.4152118444445, "data_wait_seconds": 1.919269561767578e-05} {"step": 19820, "total_steps": 22439, "tokens": 176653598720, "source": "fineweb_hq", "phase": 2, "loss": 1.9730973839759827, "ce_loss": 1.9730973839759827, "logit_z_loss": 99.34999465942383, "muon_lr": 0.0618651717403387, "adamw_lr": 0.003535152670876497, "grad_norm": 0.3444134593009949, "tokens_per_second": 9766353.595522787, "eta_seconds": 2390.132038092613, "data_wait_seconds": 3.0934810638427734e-05} {"step": 19830, "total_steps": 22439, "tokens": 176742727680, "source": "fineweb_hq", "phase": 2, "loss": 1.952784240245819, "ce_loss": 1.952784240245819, "logit_z_loss": 99.39868354797363, "muon_lr": 0.06165449982445595, "adamw_lr": 0.0035231142756831967, "grad_norm": 0.2932511270046234, "tokens_per_second": 9002558.980823714, "eta_seconds": 2583.0150864362718, "data_wait_seconds": 1.7523765563964844e-05} {"step": 19840, "total_steps": 22439, "tokens": 176831856640, "source": "fineweb_hq", "phase": 2, "loss": 1.9490482807159424, "ce_loss": 1.9490482807159424, "logit_z_loss": 96.5870475769043, "muon_lr": 0.061441503271540396, "adamw_lr": 0.003510943044088022, "grad_norm": 0.2961852252483368, "tokens_per_second": 7902561.210777192, "eta_seconds": 2931.2796302556994, "data_wait_seconds": 2.1755695343017578e-05} {"step": 19850, "total_steps": 22439, "tokens": 176920985600, "source": "fineweb_hq", "phase": 2, "loss": 1.9600580036640167, "ce_loss": 1.9600580036640167, "logit_z_loss": 97.35949516296387, "muon_lr": 0.061226200657805374, "adamw_lr": 0.003498640037588878, "grad_norm": 0.3256329298019409, "tokens_per_second": 8332249.810788183, "eta_seconds": 2769.4186165809633, "data_wait_seconds": 2.288818359375e-05} {"step": 19860, "total_steps": 22439, "tokens": 177010114560, "source": "fineweb_hq", "phase": 2, "loss": 1.947264403104782, "ce_loss": 1.947264403104782, "logit_z_loss": 97.30531311035156, "muon_lr": 0.06100861076058425, "adamw_lr": 0.003486206329176243, "grad_norm": 0.31083858013153076, "tokens_per_second": 8613086.2194345, "eta_seconds": 2668.7714715003967, "data_wait_seconds": 0.160763680934906} {"step": 19870, "total_steps": 22439, "tokens": 177099243520, "source": "fineweb_hq", "phase": 2, "loss": 1.961327999830246, "ce_loss": 1.961327999830246, "logit_z_loss": 98.70391464233398, "muon_lr": 0.06078875255669283, "adamw_lr": 0.0034736430032395902, "grad_norm": 0.34762781858444214, "tokens_per_second": 8662530.860217085, "eta_seconds": 2643.24943754673, "data_wait_seconds": 1.7404556274414062e-05} {"step": 19880, "total_steps": 22439, "tokens": 177188372480, "source": "fineweb_hq", "phase": 2, "loss": 1.9673119485378265, "ce_loss": 1.9673119485378265, "logit_z_loss": 98.9455680847168, "muon_lr": 0.06056664522077426, "adamw_lr": 0.0034609511554728146, "grad_norm": 0.3625636100769043, "tokens_per_second": 8940509.385865271, "eta_seconds": 2551.0963502883915, "data_wait_seconds": 1.895427703857422e-05} {"step": 19890, "total_steps": 22439, "tokens": 177277501440, "source": "fineweb_hq", "phase": 2, "loss": 1.9690393507480621, "ce_loss": 1.9690393507480621, "logit_z_loss": 94.27217483520508, "muon_lr": 0.06034230812362677, "adamw_lr": 0.0034481318927786723, "grad_norm": 0.29470884799957275, "tokens_per_second": 9196279.624652686, "eta_seconds": 2470.4524907112122, "data_wait_seconds": 1.996755599975586e-05} {"step": 19900, "total_steps": 22439, "tokens": 177366630400, "source": "fineweb_hq", "phase": 2, "loss": 1.9784173965454102, "ce_loss": 1.9784173965454102, "logit_z_loss": 99.94176292419434, "muon_lr": 0.060115760830514314, "adamw_lr": 0.003435186333172246, "grad_norm": 0.2931779623031616, "tokens_per_second": 9354130.047426987, "eta_seconds": 2419.235442447662, "data_wait_seconds": 1.806020736694336e-05} {"step": 19910, "total_steps": 22439, "tokens": 177455759360, "source": "fineweb_hq", "phase": 2, "loss": 1.979276180267334, "ce_loss": 1.979276180267334, "logit_z_loss": 95.98761367797852, "muon_lr": 0.05988702309946011, "adamw_lr": 0.0034221156056834347, "grad_norm": 0.324918657541275, "tokens_per_second": 9239566.563889902, "eta_seconds": 2439.585648107529, "data_wait_seconds": 1.9431114196777344e-05} {"step": 19920, "total_steps": 22439, "tokens": 177544888320, "source": "fineweb_hq", "phase": 2, "loss": 1.9856651723384857, "ce_loss": 1.9856651723384857, "logit_z_loss": 100.09841728210449, "muon_lr": 0.05965611487952359, "adamw_lr": 0.0034089208502584905, "grad_norm": 0.3025656044483185, "tokens_per_second": 8879594.851809626, "eta_seconds": 2528.4470067262646, "data_wait_seconds": 0.16344988346099854} {"step": 19930, "total_steps": 22439, "tokens": 177634017280, "source": "fineweb_hq", "phase": 2, "loss": 1.9656601250171661, "ce_loss": 1.9656601250171661, "logit_z_loss": 99.07984924316406, "muon_lr": 0.05942305630906046, "adamw_lr": 0.0033956032176605975, "grad_norm": 0.32972630858421326, "tokens_per_second": 9167879.43925435, "eta_seconds": 2439.2179469823836, "data_wait_seconds": 1.633167266845703e-05} {"step": 19940, "total_steps": 22439, "tokens": 177723146240, "source": "fineweb_hq", "phase": 2, "loss": 1.9596152901649475, "ce_loss": 1.9596152901649475, "logit_z_loss": 99.73912239074707, "muon_lr": 0.05918786771396645, "adamw_lr": 0.003382163869369511, "grad_norm": 0.2992822229862213, "tokens_per_second": 8360275.967007774, "eta_seconds": 2664.1856311798097, "data_wait_seconds": 1.901388168334961e-05} {"step": 19950, "total_steps": 22439, "tokens": 177812275200, "source": "fineweb_hq", "phase": 2, "loss": 1.9457648694515228, "ce_loss": 1.9457648694515228, "logit_z_loss": 100.90079116821289, "muon_lr": 0.05895056960590455, "adamw_lr": 0.00336860397748026, "grad_norm": 0.3093985915184021, "tokens_per_second": 7604292.01620515, "eta_seconds": 2917.3259123563766, "data_wait_seconds": 1.633167266845703e-05} {"step": 19960, "total_steps": 22439, "tokens": 177901404160, "source": "fineweb_hq", "phase": 2, "loss": 1.9273811876773834, "ce_loss": 1.9273811876773834, "logit_z_loss": 100.26827049255371, "muon_lr": 0.058711182680516165, "adamw_lr": 0.0033549247246009235, "grad_norm": 0.316666841506958, "tokens_per_second": 6585183.510419693, "eta_seconds": 3355.2700769901276, "data_wait_seconds": 2.0682811737060547e-05} {"step": 19970, "total_steps": 22439, "tokens": 177990533120, "source": "fineweb_hq", "phase": 2, "loss": 1.9429328739643097, "ce_loss": 1.9429328739643097, "logit_z_loss": 96.3702449798584, "muon_lr": 0.05846972781561611, "adamw_lr": 0.0033411273037494914, "grad_norm": 0.2850782573223114, "tokens_per_second": 6293007.523700372, "eta_seconds": 3496.8876393556598, "data_wait_seconds": 2.0384788513183594e-05} {"step": 19980, "total_steps": 22439, "tokens": 178079662080, "source": "fineweb_hq", "phase": 2, "loss": 1.9387704730033875, "ce_loss": 1.9387704730033875, "logit_z_loss": 100.60917472839355, "muon_lr": 0.058226226069371854, "adamw_lr": 0.00332721291824982, "grad_norm": 0.34937146306037903, "tokens_per_second": 7941680.842040825, "eta_seconds": 2759.7194724798205, "data_wait_seconds": 1.8835067749023438e-05} {"step": 19990, "total_steps": 22439, "tokens": 178168791040, "source": "fineweb_hq", "phase": 2, "loss": 1.9374864399433136, "ce_loss": 1.9374864399433136, "logit_z_loss": 101.71585464477539, "muon_lr": 0.057980698678466905, "adamw_lr": 0.00331318278162668, "grad_norm": 0.34407687187194824, "tokens_per_second": 5834007.040807811, "eta_seconds": 3741.4562840461726, "data_wait_seconds": 0.41281574964523315} {"step": 20000, "total_steps": 22439, "tokens": 178257920000, "source": "fineweb_hq", "phase": 2, "loss": 1.9428208768367767, "ce_loss": 1.9428208768367767, "logit_z_loss": 100.47715759277344, "muon_lr": 0.05773316705624869, "adamw_lr": 0.003299038117499925, "grad_norm": 0.365927129983902, "tokens_per_second": 7364924.441888035, "eta_seconds": 2951.6329075098038, "data_wait_seconds": 2.014636993408203e-05} {"step": 20010, "total_steps": 22439, "tokens": 178347048960, "source": "fineweb_hq", "phase": 2, "loss": 1.9283939599990845, "ce_loss": 1.9283939599990845, "logit_z_loss": 100.78992462158203, "muon_lr": 0.057483652790861046, "adamw_lr": 0.0032847801594777736, "grad_norm": 0.3201388418674469, "tokens_per_second": 11306903.475998694, "eta_seconds": 1914.7085167884827, "data_wait_seconds": 1.8596649169921875e-05} {"step": 20020, "total_steps": 22439, "tokens": 178436177920, "source": "fineweb_hq", "phase": 2, "loss": 1.9457659423351288, "ce_loss": 1.9457659423351288, "logit_z_loss": 102.80153274536133, "muon_lr": 0.05723217764336141, "adamw_lr": 0.003270410151049223, "grad_norm": 0.33229416608810425, "tokens_per_second": 7529758.596148631, "eta_seconds": 2863.344840168953, "data_wait_seconds": 0.2085026502609253} {"step": 20030, "total_steps": 22439, "tokens": 178525306880, "source": "fineweb_hq", "phase": 2, "loss": 1.9406559467315674, "ce_loss": 1.9406559467315674, "logit_z_loss": 99.24288749694824, "muon_lr": 0.05697876354582294, "adamw_lr": 0.0032559293454755963, "grad_norm": 0.31985676288604736, "tokens_per_second": 7981005.170398412, "eta_seconds": 2690.283492565155, "data_wait_seconds": 1.8715858459472656e-05} {"step": 20040, "total_steps": 22439, "tokens": 178614435840, "source": "fineweb_hq", "phase": 2, "loss": 1.9395206272602081, "ce_loss": 1.9395206272602081, "logit_z_loss": 103.45383262634277, "muon_lr": 0.0567234325994218, "adamw_lr": 0.0032413390056812456, "grad_norm": 0.29466670751571655, "tokens_per_second": 8704839.06775217, "eta_seconds": 2456.339208292961, "data_wait_seconds": 2.7477741241455078e-05} {"step": 20050, "total_steps": 22439, "tokens": 178703564800, "source": "fineweb_hq", "phase": 2, "loss": 1.9036086797714233, "ce_loss": 1.9036086797714233, "logit_z_loss": 99.11339569091797, "muon_lr": 0.05646620707250958, "adamw_lr": 0.0032266404041434043, "grad_norm": 0.3292168974876404, "tokens_per_second": 6681604.841558023, "eta_seconds": 3186.795545220375, "data_wait_seconds": 1.8835067749023438e-05} {"step": 20060, "total_steps": 22439, "tokens": 178792693760, "source": "fineweb_hq", "phase": 2, "loss": 1.9195380508899689, "ce_loss": 1.9195380508899689, "logit_z_loss": 98.8975944519043, "muon_lr": 0.05620710939867121, "adamw_lr": 0.003211834822781212, "grad_norm": 0.36700335144996643, "tokens_per_second": 9213887.538765796, "eta_seconds": 2301.2848262786865, "data_wait_seconds": 2.0325183868408203e-05} {"step": 20070, "total_steps": 22439, "tokens": 178881822720, "source": "fineweb_hq", "phase": 2, "loss": 1.8926385939121246, "ce_loss": 1.8926385939121246, "logit_z_loss": 100.59559631347656, "muon_lr": 0.05594616217476845, "adamw_lr": 0.0031969235528439112, "grad_norm": 0.36090517044067383, "tokens_per_second": 7921955.218737889, "eta_seconds": 2665.3332467794417, "data_wait_seconds": 1.8537044525146484e-05} {"step": 20080, "total_steps": 22439, "tokens": 178970951680, "source": "fineweb_hq", "phase": 2, "loss": 1.8612332940101624, "ce_loss": 1.8612332940101624, "logit_z_loss": 106.54780006408691, "muon_lr": 0.05568338815896912, "adamw_lr": 0.0031819078947982354, "grad_norm": 0.30154821276664734, "tokens_per_second": 8663289.282040535, "eta_seconds": 2426.967515397072, "data_wait_seconds": 1.8715858459472656e-05} {"step": 20090, "total_steps": 22439, "tokens": 179060080640, "source": "fineweb_hq", "phase": 2, "loss": 1.856196403503418, "ce_loss": 1.856196403503418, "logit_z_loss": 102.11246299743652, "muon_lr": 0.0554188102687623, "adamw_lr": 0.0031667891582149886, "grad_norm": 0.28575363755226135, "tokens_per_second": 9757163.273537377, "eta_seconds": 2145.7458604574203, "data_wait_seconds": 1.811981201171875e-05} {"step": 20100, "total_steps": 22439, "tokens": 179149209600, "source": "fineweb_hq", "phase": 2, "loss": 1.8791177868843079, "ce_loss": 1.8791177868843079, "logit_z_loss": 104.77649116516113, "muon_lr": 0.05515245157895957, "adamw_lr": 0.0031515686616548325, "grad_norm": 0.30561697483062744, "tokens_per_second": 8732173.920039145, "eta_seconds": 2387.408214139938, "data_wait_seconds": 1.9311904907226562e-05} {"step": 20110, "total_steps": 22439, "tokens": 179238338560, "source": "fineweb_hq", "phase": 2, "loss": 1.8546561896800995, "ce_loss": 1.8546561896800995, "logit_z_loss": 105.10050582885742, "muon_lr": 0.05488433531968263, "adamw_lr": 0.0031362477325532928, "grad_norm": 0.3312560021877289, "tokens_per_second": 9245451.324482035, "eta_seconds": 2245.226766705513, "data_wait_seconds": 1.9252300262451172e-05} {"step": 20120, "total_steps": 22439, "tokens": 179327467520, "source": "fineweb_hq", "phase": 2, "loss": 1.876363068819046, "ce_loss": 1.876363068819046, "logit_z_loss": 103.58477401733398, "muon_lr": 0.05461448487433723, "adamw_lr": 0.0031208277071049844, "grad_norm": 0.29391342401504517, "tokens_per_second": 9727232.970499212, "eta_seconds": 2124.8597506284714, "data_wait_seconds": 1.8894672393798828e-05} {"step": 20130, "total_steps": 22439, "tokens": 179416596480, "source": "fineweb_hq", "phase": 2, "loss": 1.8685232996940613, "ce_loss": 1.8685232996940613, "logit_z_loss": 103.49335098266602, "muon_lr": 0.05434292377757396, "adamw_lr": 0.003105309930147083, "grad_norm": 0.30132758617401123, "tokens_per_second": 8185050.319996767, "eta_seconds": 2514.3250266551972, "data_wait_seconds": 1.7762184143066406e-05} {"step": 20140, "total_steps": 22439, "tokens": 179505725440, "source": "fineweb_hq", "phase": 2, "loss": 1.8603698015213013, "ce_loss": 1.8603698015213013, "logit_z_loss": 105.01471710205078, "muon_lr": 0.054069675713235524, "adamw_lr": 0.0030896957550420297, "grad_norm": 0.29002025723457336, "tokens_per_second": 9732955.231270514, "eta_seconds": 2105.2956082820892, "data_wait_seconds": 1.817941665649414e-05} {"step": 20150, "total_steps": 22439, "tokens": 179594854400, "source": "fineweb_hq", "phase": 2, "loss": 1.8466525077819824, "ce_loss": 1.8466525077819824, "logit_z_loss": 103.0981616973877, "muon_lr": 0.053794764512291336, "adamw_lr": 0.0030739865435595046, "grad_norm": 0.2753201127052307, "tokens_per_second": 5952425.325244545, "eta_seconds": 3427.446432209015, "data_wait_seconds": 0.5249242186546326} {"step": 20160, "total_steps": 22439, "tokens": 179683983360, "source": "fineweb_hq", "phase": 2, "loss": 1.8820434212684631, "ce_loss": 1.8820434212684631, "logit_z_loss": 107.19742965698242, "muon_lr": 0.053518214150759046, "adamw_lr": 0.0030581836657576594, "grad_norm": 0.2873774766921997, "tokens_per_second": 9461497.907709168, "eta_seconds": 2146.8577367067337, "data_wait_seconds": 1.6033649444580078e-05} {"step": 20170, "total_steps": 22439, "tokens": 179773112320, "source": "fineweb_hq", "phase": 2, "loss": 1.8838628828525543, "ce_loss": 1.8838628828525543, "logit_z_loss": 100.98152160644531, "muon_lr": 0.05324004874761351, "adamw_lr": 0.003042288499863629, "grad_norm": 0.28046002984046936, "tokens_per_second": 8796993.627367357, "eta_seconds": 2298.894586110115, "data_wait_seconds": 1.9073486328125e-05} {"step": 20180, "total_steps": 22439, "tokens": 179862241280, "source": "fineweb_hq", "phase": 2, "loss": 1.9100408852100372, "ce_loss": 1.9100408852100372, "logit_z_loss": 104.36373710632324, "muon_lr": 0.05296029256268338, "adamw_lr": 0.0030263024321533355, "grad_norm": 0.2785077691078186, "tokens_per_second": 8765321.587364828, "eta_seconds": 2297.0328998565674, "data_wait_seconds": 1.704692840576172e-05} {"step": 20190, "total_steps": 22439, "tokens": 179951370240, "source": "fineweb_hq", "phase": 2, "loss": 1.9417555928230286, "ce_loss": 1.9417555928230286, "logit_z_loss": 102.40350532531738, "muon_lr": 0.05267896999453518, "adamw_lr": 0.0030102268568305817, "grad_norm": 0.30016791820526123, "tokens_per_second": 8925125.557419682, "eta_seconds": 2245.91833190918, "data_wait_seconds": 1.704692840576172e-05}