初始化项目,由ModelHub XC社区提供模型

Model: msurendra/slm125m-learning
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-05 15:25:17 +08:00
commit f97221b001
9 changed files with 81544 additions and 0 deletions

198
metrics.jsonl Normal file
View File

@@ -0,0 +1,198 @@
{"step": 20, "loss": 9.5647, "lr": 2.992125984251968e-05, "tokens": 10485760, "tok_per_sec": 417682, "elapsed_min": 0.4}
{"step": 20, "loss": 9.5123, "lr": 2.992125984251968e-05, "tokens": 10485760, "tok_per_sec": 448366, "elapsed_min": 0.4}
{"step": 40, "loss": 8.6566, "lr": 6.141732283464567e-05, "tokens": 20971520, "tok_per_sec": 591910, "elapsed_min": 0.6}
{"step": 60, "loss": 8.9365, "lr": 9.291338582677164e-05, "tokens": 31457280, "tok_per_sec": 665490, "elapsed_min": 0.8}
{"step": 80, "loss": 8.897, "lr": 0.00012440944881889762, "tokens": 41943040, "tok_per_sec": 711844, "elapsed_min": 1.0}
{"step": 100, "loss": 9.0608, "lr": 0.0001559055118110236, "tokens": 52428800, "tok_per_sec": 744766, "elapsed_min": 1.2}
{"step": 120, "loss": 8.9153, "lr": 0.0001874015748031496, "tokens": 62914560, "tok_per_sec": 767336, "elapsed_min": 1.4}
{"step": 140, "loss": 8.7668, "lr": 0.00021889763779527557, "tokens": 73400320, "tok_per_sec": 783348, "elapsed_min": 1.6}
{"step": 160, "loss": 8.67, "lr": 0.00025039370078740154, "tokens": 83886080, "tok_per_sec": 794543, "elapsed_min": 1.8}
{"step": 180, "loss": 8.5952, "lr": 0.00028188976377952754, "tokens": 94371840, "tok_per_sec": 804826, "elapsed_min": 2.0}
{"step": 200, "loss": 8.6435, "lr": 0.00031338582677165354, "tokens": 104857600, "tok_per_sec": 812474, "elapsed_min": 2.2}
{"step": 220, "loss": 8.5664, "lr": 0.0003448818897637795, "tokens": 115343360, "tok_per_sec": 818197, "elapsed_min": 2.3}
{"step": 240, "loss": 8.5027, "lr": 0.00037637795275590553, "tokens": 125829120, "tok_per_sec": 824172, "elapsed_min": 2.5}
{"step": 260, "loss": 8.4524, "lr": 0.0004078740157480314, "tokens": 136314880, "tok_per_sec": 829791, "elapsed_min": 2.7}
{"step": 280, "loss": 8.5133, "lr": 0.0004393700787401575, "tokens": 146800640, "tok_per_sec": 833711, "elapsed_min": 2.9}
{"step": 300, "loss": 8.5915, "lr": 0.0004708661417322834, "tokens": 157286400, "tok_per_sec": 835593, "elapsed_min": 3.1}
{"step": 320, "loss": 8.7146, "lr": 0.0005023622047244094, "tokens": 167772160, "tok_per_sec": 838800, "elapsed_min": 3.3}
{"step": 340, "loss": 8.6226, "lr": 0.0005338582677165354, "tokens": 178257920, "tok_per_sec": 841625, "elapsed_min": 3.5}
{"step": 360, "loss": 8.6281, "lr": 0.0005653543307086614, "tokens": 188743680, "tok_per_sec": 844156, "elapsed_min": 3.7}
{"step": 380, "loss": 8.7329, "lr": 0.0005968503937007874, "tokens": 199229440, "tok_per_sec": 846142, "elapsed_min": 3.9}
{"step": 400, "loss": 8.9025, "lr": 0.0005999649207782037, "tokens": 209715200, "tok_per_sec": 847570, "elapsed_min": 4.1}
{"step": 420, "loss": 9.0656, "lr": 0.0005998436709732521, "tokens": 220200960, "tok_per_sec": 849750, "elapsed_min": 4.3}
{"step": 440, "loss": 9.6427, "lr": 0.0005996358563955241, "tokens": 230686720, "tok_per_sec": 851741, "elapsed_min": 4.5}
{"step": 460, "loss": 10.1005, "lr": 0.0005993415437111068, "tokens": 241172480, "tok_per_sec": 853914, "elapsed_min": 4.7}
{"step": 480, "loss": 10.7196, "lr": 0.0005989608273343351, "tokens": 251658240, "tok_per_sec": 855579, "elapsed_min": 4.9}
{"step": 500, "loss": 11.6291, "lr": 0.0005984938293975031, "tokens": 262144000, "tok_per_sec": 856431, "elapsed_min": 5.1}
{"step": 520, "loss": 12.085, "lr": 0.0005979406997116852, "tokens": 272629760, "tok_per_sec": 838661, "elapsed_min": 5.4}
{"step": 540, "loss": 12.6029, "lr": 0.0005973016157186776, "tokens": 283115520, "tok_per_sec": 840242, "elapsed_min": 5.6}
{"step": 560, "loss": 12.5544, "lr": 0.0005965767824340745, "tokens": 293601280, "tok_per_sec": 841769, "elapsed_min": 5.8}
{"step": 580, "loss": 11.944, "lr": 0.0005957664323815011, "tokens": 304087040, "tok_per_sec": 842828, "elapsed_min": 6.0}
{"step": 600, "loss": 11.5126, "lr": 0.0005948708255180204, "tokens": 314572800, "tok_per_sec": 843711, "elapsed_min": 6.2}
{"step": 620, "loss": 11.2213, "lr": 0.0005938902491507401, "tokens": 325058560, "tok_per_sec": 845042, "elapsed_min": 6.4}
{"step": 640, "loss": 11.109, "lr": 0.0005928250178446456, "tokens": 335544320, "tok_per_sec": 845974, "elapsed_min": 6.6}
{"step": 660, "loss": 11.0603, "lr": 0.0005916754733216889, "tokens": 346030080, "tok_per_sec": 846943, "elapsed_min": 6.8}
{"step": 680, "loss": 11.0302, "lr": 0.0005904419843511652, "tokens": 356515840, "tok_per_sec": 848390, "elapsed_min": 7.0}
{"step": 700, "loss": 11.058, "lr": 0.000589124946631414, "tokens": 367001600, "tok_per_sec": 849577, "elapsed_min": 7.2}
{"step": 720, "loss": 11.0259, "lr": 0.0005877247826628799, "tokens": 377487360, "tok_per_sec": 850319, "elapsed_min": 7.4}
{"step": 740, "loss": 10.9802, "lr": 0.000586241941612576, "tokens": 387973120, "tok_per_sec": 851619, "elapsed_min": 7.6}
{"step": 760, "loss": 10.929, "lr": 0.000584676899169994, "tokens": 398458880, "tok_per_sec": 852924, "elapsed_min": 7.8}
{"step": 780, "loss": 10.9143, "lr": 0.0005830301573945036, "tokens": 408944640, "tok_per_sec": 854406, "elapsed_min": 8.0}
{"step": 800, "loss": 10.7903, "lr": 0.0005813022445542947, "tokens": 419430400, "tok_per_sec": 856026, "elapsed_min": 8.2}
{"step": 820, "loss": 10.9018, "lr": 0.000579493714956911, "tokens": 429916160, "tok_per_sec": 857461, "elapsed_min": 8.4}
{"step": 840, "loss": 10.7786, "lr": 0.0005776051487714297, "tokens": 440401920, "tok_per_sec": 858807, "elapsed_min": 8.5}
{"step": 860, "loss": 10.7126, "lr": 0.0005756371518423467, "tokens": 450887680, "tok_per_sec": 859872, "elapsed_min": 8.7}
{"step": 880, "loss": 10.7538, "lr": 0.0005735903554952228, "tokens": 461373440, "tok_per_sec": 860926, "elapsed_min": 8.9}
{"step": 900, "loss": 10.6713, "lr": 0.0005714654163341581, "tokens": 471859200, "tok_per_sec": 862095, "elapsed_min": 9.1}
{"step": 920, "loss": 10.6538, "lr": 0.0005692630160311554, "tokens": 482344960, "tok_per_sec": 863201, "elapsed_min": 9.3}
{"step": 940, "loss": 10.6393, "lr": 0.0005669838611074428, "tokens": 492830720, "tok_per_sec": 864539, "elapsed_min": 9.5}
{"step": 960, "loss": 10.4905, "lr": 0.0005646286827068242, "tokens": 503316480, "tok_per_sec": 865569, "elapsed_min": 9.7}
{"step": 980, "loss": 10.5455, "lr": 0.0005621982363611318, "tokens": 513802240, "tok_per_sec": 866616, "elapsed_min": 9.9}
{"step": 1000, "loss": 10.4138, "lr": 0.000559693301747854, "tokens": 524288000, "tok_per_sec": 867417, "elapsed_min": 10.1}
{"step": 1000, "val_loss": 10.4696}
{"step": 1020, "loss": 10.4076, "lr": 0.0005571146824400183, "tokens": 534773760, "tok_per_sec": 849308, "elapsed_min": 10.5}
{"step": 1040, "loss": 10.4012, "lr": 0.0005544632056484079, "tokens": 545259520, "tok_per_sec": 850211, "elapsed_min": 10.7}
{"step": 1060, "loss": 10.3919, "lr": 0.0005517397219561964, "tokens": 555745280, "tok_per_sec": 851004, "elapsed_min": 10.9}
{"step": 1080, "loss": 10.3419, "lr": 0.0005489451050460835, "tokens": 566231040, "tok_per_sec": 851904, "elapsed_min": 11.1}
{"step": 1100, "loss": 10.3604, "lr": 0.0005460802514200215, "tokens": 576716800, "tok_per_sec": 852958, "elapsed_min": 11.3}
{"step": 1120, "loss": 10.4094, "lr": 0.0005431460801116208, "tokens": 587202560, "tok_per_sec": 853857, "elapsed_min": 11.5}
{"step": 1140, "loss": 10.4827, "lr": 0.0005401435323913276, "tokens": 597688320, "tok_per_sec": 854901, "elapsed_min": 11.7}
{"step": 1160, "loss": 10.3918, "lr": 0.0005370735714644682, "tokens": 608174080, "tok_per_sec": 855991, "elapsed_min": 11.8}
{"step": 1180, "loss": 10.3673, "lr": 0.0005339371821622567, "tokens": 618659840, "tok_per_sec": 857027, "elapsed_min": 12.0}
{"step": 1200, "loss": 10.3002, "lr": 0.0005307353706258647, "tokens": 629145600, "tok_per_sec": 857847, "elapsed_min": 12.2}
{"step": 1220, "loss": 10.3667, "lr": 0.0005274691639836555, "tokens": 639631360, "tok_per_sec": 858870, "elapsed_min": 12.4}
{"step": 1240, "loss": 10.1567, "lr": 0.0005241396100216855, "tokens": 650117120, "tok_per_sec": 859812, "elapsed_min": 12.6}
{"step": 1260, "loss": 10.0966, "lr": 0.0005207477768475781, "tokens": 660602880, "tok_per_sec": 860475, "elapsed_min": 12.8}
{"step": 1280, "loss": 10.0388, "lr": 0.00051729475254788, "tokens": 671088640, "tok_per_sec": 861321, "elapsed_min": 13.0}
{"step": 1300, "loss": 10.0118, "lr": 0.0005137816448390063, "tokens": 681574400, "tok_per_sec": 862006, "elapsed_min": 13.2}
{"step": 1320, "loss": 10.0468, "lr": 0.0005102095807118902, "tokens": 692060160, "tok_per_sec": 862805, "elapsed_min": 13.4}
{"step": 1340, "loss": 10.13, "lr": 0.0005065797060704486, "tokens": 702545920, "tok_per_sec": 863720, "elapsed_min": 13.6}
{"step": 1360, "loss": 10.1626, "lr": 0.0005028931853639806, "tokens": 713031680, "tok_per_sec": 864471, "elapsed_min": 13.7}
{"step": 1380, "loss": 10.1615, "lr": 0.0004991512012136169, "tokens": 723517440, "tok_per_sec": 865239, "elapsed_min": 13.9}
{"step": 1400, "loss": 9.985, "lr": 0.0004953549540329398, "tokens": 734003200, "tok_per_sec": 865954, "elapsed_min": 14.1}
{"step": 1420, "loss": 10.0895, "lr": 0.000491505661642895, "tokens": 744488960, "tok_per_sec": 866486, "elapsed_min": 14.3}
{"step": 1440, "loss": 10.1159, "lr": 0.00048760455888111976, "tokens": 754974720, "tok_per_sec": 866980, "elapsed_min": 14.5}
{"step": 1460, "loss": 10.0324, "lr": 0.0004836528972058119, "tokens": 765460480, "tok_per_sec": 867714, "elapsed_min": 14.7}
{"step": 1480, "loss": 10.2298, "lr": 0.0004796519442942669, "tokens": 775946240, "tok_per_sec": 868380, "elapsed_min": 14.9}
{"step": 1500, "loss": 10.2522, "lr": 0.00047560298363621197, "tokens": 786432000, "tok_per_sec": 869136, "elapsed_min": 15.1}
{"step": 1520, "loss": 10.1191, "lr": 0.00047150731412206795, "tokens": 796917760, "tok_per_sec": 864853, "elapsed_min": 15.4}
{"step": 1540, "loss": 10.0617, "lr": 0.0004673662496262704, "tokens": 807403520, "tok_per_sec": 865438, "elapsed_min": 15.5}
{"step": 1560, "loss": 9.9935, "lr": 0.0004631811185857835, "tokens": 817889280, "tok_per_sec": 865968, "elapsed_min": 15.7}
{"step": 1580, "loss": 10.0647, "lr": 0.00045895326357394355, "tokens": 828375040, "tok_per_sec": 866438, "elapsed_min": 15.9}
{"step": 1600, "loss": 10.0339, "lr": 0.00045468404086976597, "tokens": 838860800, "tok_per_sec": 866973, "elapsed_min": 16.1}
{"step": 1620, "loss": 10.0666, "lr": 0.00045037482002285715, "tokens": 849346560, "tok_per_sec": 867362, "elapsed_min": 16.3}
{"step": 1640, "loss": 10.1269, "lr": 0.00044602698341406776, "tokens": 859832320, "tok_per_sec": 867854, "elapsed_min": 16.5}
{"step": 1660, "loss": 10.0797, "lr": 0.0004416419258120308, "tokens": 870318080, "tok_per_sec": 868363, "elapsed_min": 16.7}
{"step": 1680, "loss": 10.1121, "lr": 0.00043722105392572565, "tokens": 880803840, "tok_per_sec": 868836, "elapsed_min": 16.9}
{"step": 1700, "loss": 10.1031, "lr": 0.0004327657859532107, "tokens": 891289600, "tok_per_sec": 869396, "elapsed_min": 17.1}
{"step": 1720, "loss": 10.0724, "lr": 0.0004282775511266721, "tokens": 901775360, "tok_per_sec": 869895, "elapsed_min": 17.3}
{"step": 1740, "loss": 10.2001, "lr": 0.0004237577892539306, "tokens": 912261120, "tok_per_sec": 870345, "elapsed_min": 17.5}
{"step": 1760, "loss": 10.1367, "lr": 0.00041920795025655807, "tokens": 922746880, "tok_per_sec": 870951, "elapsed_min": 17.7}
{"step": 1780, "loss": 9.9238, "lr": 0.00041462949370474746, "tokens": 933232640, "tok_per_sec": 871672, "elapsed_min": 17.8}
{"step": 1800, "loss": 10.0225, "lr": 0.0004100238883490894, "tokens": 943718400, "tok_per_sec": 872197, "elapsed_min": 18.0}
{"step": 1820, "loss": 10.0741, "lr": 0.0004053926116494024, "tokens": 954204160, "tok_per_sec": 872726, "elapsed_min": 18.2}
{"step": 1840, "loss": 10.0651, "lr": 0.00040073714930076936, "tokens": 964689920, "tok_per_sec": 873302, "elapsed_min": 18.4}
{"step": 1860, "loss": 10.0149, "lr": 0.0003960589947569331, "tokens": 975175680, "tok_per_sec": 873800, "elapsed_min": 18.6}
{"step": 1880, "loss": 10.1069, "lr": 0.0003913596487512021, "tokens": 985661440, "tok_per_sec": 874378, "elapsed_min": 18.8}
{"step": 1900, "loss": 10.0314, "lr": 0.00038664061881502114, "tokens": 996147200, "tok_per_sec": 874782, "elapsed_min": 19.0}
{"step": 1920, "loss": 10.0466, "lr": 0.00038190341879436155, "tokens": 1006632960, "tok_per_sec": 875336, "elapsed_min": 19.2}
{"step": 1940, "loss": 10.0189, "lr": 0.00037714956836408487, "tokens": 1017118720, "tok_per_sec": 875795, "elapsed_min": 19.4}
{"step": 1960, "loss": 10.032, "lr": 0.000372380592540438, "tokens": 1027604480, "tok_per_sec": 876117, "elapsed_min": 19.5}
{"step": 1980, "loss": 10.1322, "lr": 0.00036759802119183335, "tokens": 1038090240, "tok_per_sec": 876489, "elapsed_min": 19.7}
{"step": 2000, "loss": 9.9949, "lr": 0.00036280338854807384, "tokens": 1048576000, "tok_per_sec": 876750, "elapsed_min": 19.9}
{"step": 2000, "val_loss": 10.073}
{"step": 2020, "loss": 10.037, "lr": 0.0003579982327081774, "tokens": 1059061760, "tok_per_sec": 863662, "elapsed_min": 20.4}
{"step": 2040, "loss": 10.1105, "lr": 0.00035318409514696126, "tokens": 1069547520, "tok_per_sec": 864074, "elapsed_min": 20.6}
{"step": 2060, "loss": 10.0493, "lr": 0.0003483625202205434, "tokens": 1080033280, "tok_per_sec": 864472, "elapsed_min": 20.8}
{"step": 2080, "loss": 9.9906, "lr": 0.00034353505467091857, "tokens": 1090519040, "tok_per_sec": 864961, "elapsed_min": 21.0}
{"step": 2100, "loss": 10.0339, "lr": 0.00033870324712977003, "tokens": 1101004800, "tok_per_sec": 865498, "elapsed_min": 21.2}
{"step": 2120, "loss": 10.019, "lr": 0.0003338686476216744, "tokens": 1111490560, "tok_per_sec": 865960, "elapsed_min": 21.4}
{"step": 2140, "loss": 10.129, "lr": 0.0003290328070668606, "tokens": 1121976320, "tok_per_sec": 866447, "elapsed_min": 21.6}
{"step": 2160, "loss": 9.9612, "lr": 0.00032419727678367993, "tokens": 1132462080, "tok_per_sec": 866741, "elapsed_min": 21.8}
{"step": 2180, "loss": 10.0856, "lr": 0.0003193636079909499, "tokens": 1142947840, "tok_per_sec": 867120, "elapsed_min": 22.0}
{"step": 2200, "loss": 10.149, "lr": 0.00031453335131032955, "tokens": 1153433600, "tok_per_sec": 867477, "elapsed_min": 22.2}
{"step": 2220, "loss": 9.8877, "lr": 0.0003097080562688855, "tokens": 1163919360, "tok_per_sec": 867706, "elapsed_min": 22.4}
{"step": 2240, "loss": 10.1116, "lr": 0.00030488927080201105, "tokens": 1174405120, "tok_per_sec": 868028, "elapsed_min": 22.5}
{"step": 2260, "loss": 10.1016, "lr": 0.00030007854075685315, "tokens": 1184890880, "tok_per_sec": 868273, "elapsed_min": 22.7}
{"step": 2280, "loss": 10.0325, "lr": 0.0002952774093964123, "tokens": 1195376640, "tok_per_sec": 868602, "elapsed_min": 22.9}
{"step": 2300, "loss": 10.2054, "lr": 0.0002904874169044687, "tokens": 1205862400, "tok_per_sec": 868889, "elapsed_min": 23.1}
{"step": 2320, "loss": 10.1132, "lr": 0.0002857100998914983, "tokens": 1216348160, "tok_per_sec": 869185, "elapsed_min": 23.3}
{"step": 2340, "loss": 10.1715, "lr": 0.00028094699090173395, "tokens": 1226833920, "tok_per_sec": 869421, "elapsed_min": 23.5}
{"step": 2360, "loss": 10.0139, "lr": 0.0002761996179215312, "tokens": 1237319680, "tok_per_sec": 869785, "elapsed_min": 23.7}
{"step": 2380, "loss": 10.1733, "lr": 0.0002714695038891968, "tokens": 1247805440, "tok_per_sec": 870189, "elapsed_min": 23.9}
{"step": 2400, "loss": 10.0494, "lr": 0.0002667581662064356, "tokens": 1258291200, "tok_per_sec": 870577, "elapsed_min": 24.1}
{"step": 2420, "loss": 9.84, "lr": 0.00026206711625157455, "tokens": 1268776960, "tok_per_sec": 871017, "elapsed_min": 24.3}
{"step": 2440, "loss": 10.1214, "lr": 0.00025739785889471867, "tokens": 1279262720, "tok_per_sec": 871242, "elapsed_min": 24.5}
{"step": 2460, "loss": 9.9142, "lr": 0.00025275189201499416, "tokens": 1289748480, "tok_per_sec": 871532, "elapsed_min": 24.7}
{"step": 2480, "loss": 10.0839, "lr": 0.00024813070602003535, "tokens": 1300234240, "tok_per_sec": 871841, "elapsed_min": 24.9}
{"step": 2500, "loss": 10.0898, "lr": 0.0002435357833678674, "tokens": 1310720000, "tok_per_sec": 872083, "elapsed_min": 25.0}
{"step": 2520, "loss": 9.9973, "lr": 0.00023896859809134023, "tokens": 1321205760, "tok_per_sec": 869139, "elapsed_min": 25.3}
{"step": 2540, "loss": 10.1216, "lr": 0.00023443061532526404, "tokens": 1331691520, "tok_per_sec": 869400, "elapsed_min": 25.5}
{"step": 2560, "loss": 10.0374, "lr": 0.0002299232908364004, "tokens": 1342177280, "tok_per_sec": 869720, "elapsed_min": 25.7}
{"step": 2580, "loss": 10.0331, "lr": 0.0002254480705564579, "tokens": 1352663040, "tok_per_sec": 869993, "elapsed_min": 25.9}
{"step": 2600, "loss": 10.0498, "lr": 0.00022100639011824285, "tokens": 1363148800, "tok_per_sec": 870283, "elapsed_min": 26.1}
{"step": 2620, "loss": 10.1596, "lr": 0.00021659967439511442, "tokens": 1373634560, "tok_per_sec": 870636, "elapsed_min": 26.3}
{"step": 2640, "loss": 10.0317, "lr": 0.0002122293370438905, "tokens": 1384120320, "tok_per_sec": 870889, "elapsed_min": 26.5}
{"step": 2660, "loss": 9.9835, "lr": 0.00020789678005135264, "tokens": 1394606080, "tok_per_sec": 871255, "elapsed_min": 26.7}
{"step": 2680, "loss": 10.0095, "lr": 0.00020360339328449404, "tokens": 1405091840, "tok_per_sec": 871608, "elapsed_min": 26.9}
{"step": 2700, "loss": 10.0824, "lr": 0.00019935055404465563, "tokens": 1415577600, "tok_per_sec": 871948, "elapsed_min": 27.1}
{"step": 2720, "loss": 10.1738, "lr": 0.00019513962662569368, "tokens": 1426063360, "tok_per_sec": 872228, "elapsed_min": 27.2}
{"step": 2740, "loss": 9.9698, "lr": 0.00019097196187631963, "tokens": 1436549120, "tok_per_sec": 872611, "elapsed_min": 27.4}
{"step": 2760, "loss": 10.0741, "lr": 0.00018684889676675304, "tokens": 1447034880, "tok_per_sec": 872990, "elapsed_min": 27.6}
{"step": 2780, "loss": 10.067, "lr": 0.00018277175395982697, "tokens": 1457520640, "tok_per_sec": 873350, "elapsed_min": 27.8}
{"step": 2800, "loss": 10.1181, "lr": 0.00017874184138668326, "tokens": 1468006400, "tok_per_sec": 873798, "elapsed_min": 28.0}
{"step": 2820, "loss": 10.1015, "lr": 0.00017476045182719302, "tokens": 1478492160, "tok_per_sec": 874082, "elapsed_min": 28.2}
{"step": 2840, "loss": 10.0136, "lr": 0.0001708288624952383, "tokens": 1488977920, "tok_per_sec": 874372, "elapsed_min": 28.4}
{"step": 2860, "loss": 10.1082, "lr": 0.0001669483346289868, "tokens": 1499463680, "tok_per_sec": 874584, "elapsed_min": 28.6}
{"step": 2880, "loss": 10.1562, "lr": 0.00016312011308629206, "tokens": 1509949440, "tok_per_sec": 874867, "elapsed_min": 28.8}
{"step": 2900, "loss": 10.1641, "lr": 0.00015934542594534762, "tokens": 1520435200, "tok_per_sec": 875221, "elapsed_min": 29.0}
{"step": 2920, "loss": 10.0651, "lr": 0.00015562548411072446, "tokens": 1530920960, "tok_per_sec": 875481, "elapsed_min": 29.1}
{"step": 2940, "loss": 10.2182, "lr": 0.00015196148092491783, "tokens": 1541406720, "tok_per_sec": 875810, "elapsed_min": 29.3}
{"step": 2960, "loss": 10.0585, "lr": 0.00014835459178552787, "tokens": 1551892480, "tok_per_sec": 876055, "elapsed_min": 29.5}
{"step": 2980, "loss": 10.1609, "lr": 0.00014480597376819622, "tokens": 1562378240, "tok_per_sec": 876335, "elapsed_min": 29.7}
{"step": 3000, "loss": 10.1427, "lr": 0.00014131676525542131, "tokens": 1572864000, "tok_per_sec": 876553, "elapsed_min": 29.9}
{"step": 3000, "val_loss": 10.0732}
{"step": 3020, "loss": 9.9639, "lr": 0.0001378880855713697, "tokens": 1583349760, "tok_per_sec": 869561, "elapsed_min": 30.3}
{"step": 3040, "loss": 10.0794, "lr": 0.00013452103462280104, "tokens": 1593835520, "tok_per_sec": 869866, "elapsed_min": 30.5}
{"step": 3060, "loss": 9.9663, "lr": 0.0001312166925462226, "tokens": 1604321280, "tok_per_sec": 869998, "elapsed_min": 30.7}
{"step": 3080, "loss": 9.9905, "lr": 0.00012797611936138582, "tokens": 1614807040, "tok_per_sec": 870318, "elapsed_min": 30.9}
{"step": 3100, "loss": 10.1396, "lr": 0.0001248003546312363, "tokens": 1625292800, "tok_per_sec": 870662, "elapsed_min": 31.1}
{"step": 3120, "loss": 10.1068, "lr": 0.00012169041712842572, "tokens": 1635778560, "tok_per_sec": 871003, "elapsed_min": 31.3}
{"step": 3140, "loss": 10.0635, "lr": 0.00011864730450849411, "tokens": 1646264320, "tok_per_sec": 871377, "elapsed_min": 31.5}
{"step": 3160, "loss": 10.0068, "lr": 0.00011567199298982582, "tokens": 1656750080, "tok_per_sec": 871708, "elapsed_min": 31.7}
{"step": 3180, "loss": 10.0856, "lr": 0.0001127654370404823, "tokens": 1667235840, "tok_per_sec": 872127, "elapsed_min": 31.9}
{"step": 3200, "loss": 10.0755, "lr": 0.00010992856907201277, "tokens": 1677721600, "tok_per_sec": 872479, "elapsed_min": 32.0}
{"step": 3220, "loss": 10.0918, "lr": 0.00010716229914034054, "tokens": 1688207360, "tok_per_sec": 872860, "elapsed_min": 32.2}
{"step": 3240, "loss": 10.0097, "lr": 0.00010446751465382013, "tokens": 1698693120, "tok_per_sec": 873222, "elapsed_min": 32.4}
{"step": 3260, "loss": 10.0116, "lr": 0.00010184508008856074, "tokens": 1709178880, "tok_per_sec": 873443, "elapsed_min": 32.6}
{"step": 3280, "loss": 10.0733, "lr": 9.929583671110538e-05, "tokens": 1719664640, "tok_per_sec": 873741, "elapsed_min": 32.8}
{"step": 3300, "loss": 10.0548, "lr": 9.682060230855634e-05, "tokens": 1730150400, "tok_per_sec": 874060, "elapsed_min": 33.0}
{"step": 3320, "loss": 10.1223, "lr": 9.442017092623193e-05, "tokens": 1740636160, "tok_per_sec": 874429, "elapsed_min": 33.2}
{"step": 3340, "loss": 10.2395, "lr": 9.209531261294006e-05, "tokens": 1751121920, "tok_per_sec": 874784, "elapsed_min": 33.4}
{"step": 3360, "loss": 10.109, "lr": 8.98467731739499e-05, "tokens": 1761607680, "tok_per_sec": 875010, "elapsed_min": 33.6}
{"step": 3380, "loss": 10.0924, "lr": 8.767527393174014e-05, "tokens": 1772093440, "tok_per_sec": 875301, "elapsed_min": 33.7}
{"step": 3400, "loss": 10.0902, "lr": 8.558151149460178e-05, "tokens": 1782579200, "tok_per_sec": 875582, "elapsed_min": 33.9}
{"step": 3420, "loss": 10.1803, "lr": 8.356615753316901e-05, "tokens": 1793064960, "tok_per_sec": 875818, "elapsed_min": 34.1}
{"step": 3440, "loss": 10.039, "lr": 8.162985856494998e-05, "tokens": 1803550720, "tok_per_sec": 876031, "elapsed_min": 34.3}
{"step": 3460, "loss": 10.0521, "lr": 7.977323574692651e-05, "tokens": 1814036480, "tok_per_sec": 876299, "elapsed_min": 34.5}
{"step": 3480, "loss": 10.1144, "lr": 7.79968846762892e-05, "tokens": 1824522240, "tok_per_sec": 876525, "elapsed_min": 34.7}
{"step": 3500, "loss": 10.0728, "lr": 7.630137519937272e-05, "tokens": 1835008000, "tok_per_sec": 876892, "elapsed_min": 34.9}
{"step": 3520, "loss": 10.0279, "lr": 7.468725122885091e-05, "tokens": 1845493760, "tok_per_sec": 875260, "elapsed_min": 35.1}
{"step": 3540, "loss": 10.1127, "lr": 7.315503056925196e-05, "tokens": 1855979520, "tok_per_sec": 875520, "elapsed_min": 35.3}
{"step": 3560, "loss": 9.9793, "lr": 7.170520475084881e-05, "tokens": 1866465280, "tok_per_sec": 875767, "elapsed_min": 35.5}
{"step": 3580, "loss": 9.9268, "lr": 7.033823887197819e-05, "tokens": 1876951040, "tok_per_sec": 875944, "elapsed_min": 35.7}
{"step": 3600, "loss": 10.0192, "lr": 6.905457144983882e-05, "tokens": 1887436800, "tok_per_sec": 876129, "elapsed_min": 35.9}
{"step": 3620, "loss": 9.9373, "lr": 6.785461427981697e-05, "tokens": 1897922560, "tok_per_sec": 876377, "elapsed_min": 36.1}
{"step": 3640, "loss": 10.1905, "lr": 6.673875230338408e-05, "tokens": 1908408320, "tok_per_sec": 876600, "elapsed_min": 36.3}
{"step": 3660, "loss": 10.0512, "lr": 6.57073434846091e-05, "tokens": 1918894080, "tok_per_sec": 876881, "elapsed_min": 36.5}
{"step": 3680, "loss": 10.1951, "lr": 6.4760718695325e-05, "tokens": 1929379840, "tok_per_sec": 877064, "elapsed_min": 36.7}
{"step": 3700, "loss": 10.157, "lr": 6.389918160898647e-05, "tokens": 1939865600, "tok_per_sec": 877341, "elapsed_min": 36.9}
{"step": 3720, "loss": 10.0255, "lr": 6.312300860325267e-05, "tokens": 1950351360, "tok_per_sec": 877612, "elapsed_min": 37.0}
{"step": 3740, "loss": 9.8335, "lr": 6.243244867132638e-05, "tokens": 1960837120, "tok_per_sec": 877801, "elapsed_min": 37.2}
{"step": 3760, "loss": 10.2619, "lr": 6.182772334207782e-05, "tokens": 1971322880, "tok_per_sec": 877998, "elapsed_min": 37.4}
{"step": 3780, "loss": 10.0541, "lr": 6.130902660897943e-05, "tokens": 1981808640, "tok_per_sec": 878156, "elapsed_min": 37.6}
{"step": 3800, "loss": 10.1329, "lr": 6.087652486787315e-05, "tokens": 1992294400, "tok_per_sec": 878348, "elapsed_min": 37.8}
{"step": 3820, "loss": 10.0554, "lr": 6.0530356863591546e-05, "tokens": 2002780160, "tok_per_sec": 878544, "elapsed_min": 38.0}
{"step": 3840, "loss": 10.0823, "lr": 6.027063364544892e-05, "tokens": 2013265920, "tok_per_sec": 878798, "elapsed_min": 38.2}
{"step": 3860, "loss": 9.864, "lr": 6.00974385316172e-05, "tokens": 2023751680, "tok_per_sec": 879037, "elapsed_min": 38.4}
{"step": 3880, "loss": 10.0646, "lr": 6.00108270823977e-05, "tokens": 2034237440, "tok_per_sec": 879319, "elapsed_min": 38.6}