| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.46490004649000466, | |
| "eval_steps": 500, | |
| "global_step": 100, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004649000464900047, | |
| "grad_norm": 0.32953426241874695, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 1.2004, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.009298000929800094, | |
| "grad_norm": 0.3239539563655853, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 1.2289, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.01394700139470014, | |
| "grad_norm": 0.3198412358760834, | |
| "learning_rate": 0.0002, | |
| "loss": 1.2456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.018596001859600187, | |
| "grad_norm": 0.3325466513633728, | |
| "learning_rate": 0.00019995280121409636, | |
| "loss": 1.2665, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.023245002324500233, | |
| "grad_norm": 0.24871456623077393, | |
| "learning_rate": 0.00019981125436139405, | |
| "loss": 1.2468, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02789400278940028, | |
| "grad_norm": 0.2815144658088684, | |
| "learning_rate": 0.00019957550790499526, | |
| "loss": 1.3639, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.032543003254300325, | |
| "grad_norm": 0.32101693749427795, | |
| "learning_rate": 0.00019924580911037827, | |
| "loss": 1.3038, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.037192003719200374, | |
| "grad_norm": 0.3729206919670105, | |
| "learning_rate": 0.00019882250378605015, | |
| "loss": 1.2968, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.04184100418410042, | |
| "grad_norm": 0.6571431159973145, | |
| "learning_rate": 0.0001983060359208415, | |
| "loss": 1.3009, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046490004649000466, | |
| "grad_norm": 0.7671701908111572, | |
| "learning_rate": 0.00019769694721822337, | |
| "loss": 1.3118, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05113900511390051, | |
| "grad_norm": 1.0644092559814453, | |
| "learning_rate": 0.00019699587652813503, | |
| "loss": 1.1329, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.05578800557880056, | |
| "grad_norm": 1.1345399618148804, | |
| "learning_rate": 0.00019620355917691884, | |
| "loss": 0.9978, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.06043700604370061, | |
| "grad_norm": 0.7588826417922974, | |
| "learning_rate": 0.00019532082619606436, | |
| "loss": 1.0705, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.06508600650860065, | |
| "grad_norm": 0.48238641023635864, | |
| "learning_rate": 0.00019434860345057096, | |
| "loss": 1.1014, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.0697350069735007, | |
| "grad_norm": 0.4875181317329407, | |
| "learning_rate": 0.0001932879106678434, | |
| "loss": 1.1474, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07438400743840075, | |
| "grad_norm": 0.4862312972545624, | |
| "learning_rate": 0.00019213986036813863, | |
| "loss": 1.1379, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.07903300790330078, | |
| "grad_norm": 0.3827863931655884, | |
| "learning_rate": 0.0001909056566976856, | |
| "loss": 1.184, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.08368200836820083, | |
| "grad_norm": 0.27560049295425415, | |
| "learning_rate": 0.00018958659416570212, | |
| "loss": 1.2394, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08833100883310088, | |
| "grad_norm": 0.2506018877029419, | |
| "learning_rate": 0.0001881840562866336, | |
| "loss": 1.2103, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.09298000929800093, | |
| "grad_norm": 0.27463746070861816, | |
| "learning_rate": 0.00018669951412903725, | |
| "loss": 1.1667, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09762900976290098, | |
| "grad_norm": 0.39848339557647705, | |
| "learning_rate": 0.0001851345247726344, | |
| "loss": 1.199, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10227801022780102, | |
| "grad_norm": 0.4772193729877472, | |
| "learning_rate": 0.00018349072967514896, | |
| "loss": 1.0961, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.10692701069270107, | |
| "grad_norm": 0.5459783673286438, | |
| "learning_rate": 0.00018176985295064487, | |
| "loss": 1.0476, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.11157601115760112, | |
| "grad_norm": 0.4945487082004547, | |
| "learning_rate": 0.00017997369956116845, | |
| "loss": 1.0457, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.11622501162250116, | |
| "grad_norm": 0.6709153652191162, | |
| "learning_rate": 0.00017810415342359257, | |
| "loss": 0.9617, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.12087401208740121, | |
| "grad_norm": 0.11191853880882263, | |
| "learning_rate": 0.00017616317543364804, | |
| "loss": 1.0668, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.12552301255230125, | |
| "grad_norm": 0.10844499617815018, | |
| "learning_rate": 0.00017415280140921463, | |
| "loss": 1.0769, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1301720130172013, | |
| "grad_norm": 0.10678815096616745, | |
| "learning_rate": 0.00017207513995502939, | |
| "loss": 1.1198, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.13482101348210135, | |
| "grad_norm": 0.12248999625444412, | |
| "learning_rate": 0.0001699323702510513, | |
| "loss": 1.1554, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.1394700139470014, | |
| "grad_norm": 0.17909854650497437, | |
| "learning_rate": 0.0001677267397668026, | |
| "loss": 1.1657, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.14411901441190145, | |
| "grad_norm": 0.268684446811676, | |
| "learning_rate": 0.0001654605619040835, | |
| "loss": 1.1791, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.1487680148768015, | |
| "grad_norm": 0.3540749251842499, | |
| "learning_rate": 0.00016313621357053306, | |
| "loss": 1.1892, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.15341701534170155, | |
| "grad_norm": 0.3607785999774933, | |
| "learning_rate": 0.00016075613268658157, | |
| "loss": 1.1991, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.15806601580660157, | |
| "grad_norm": 0.35358941555023193, | |
| "learning_rate": 0.00015832281562840856, | |
| "loss": 1.0899, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.16271501627150162, | |
| "grad_norm": 0.40458086133003235, | |
| "learning_rate": 0.00015583881460958868, | |
| "loss": 1.0584, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.16736401673640167, | |
| "grad_norm": 0.4372604191303253, | |
| "learning_rate": 0.0001533067350041725, | |
| "loss": 0.9016, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.17201301720130172, | |
| "grad_norm": 0.6177683472633362, | |
| "learning_rate": 0.0001507292326140085, | |
| "loss": 0.9031, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.17666201766620176, | |
| "grad_norm": 0.6434624791145325, | |
| "learning_rate": 0.00014810901088317414, | |
| "loss": 1.0235, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.18131101813110181, | |
| "grad_norm": 0.09565520286560059, | |
| "learning_rate": 0.00014544881806243583, | |
| "loss": 1.095, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.18596001859600186, | |
| "grad_norm": 0.10863650590181351, | |
| "learning_rate": 0.0001427514443267139, | |
| "loss": 1.0956, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1906090190609019, | |
| "grad_norm": 0.09909647703170776, | |
| "learning_rate": 0.0001400197188485739, | |
| "loss": 1.1065, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.19525801952580196, | |
| "grad_norm": 0.09885207563638687, | |
| "learning_rate": 0.00013725650683081556, | |
| "loss": 1.1516, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.199907019990702, | |
| "grad_norm": 0.10642173141241074, | |
| "learning_rate": 0.0001344647065012709, | |
| "loss": 1.1673, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.20455602045560203, | |
| "grad_norm": 0.14314843714237213, | |
| "learning_rate": 0.00013164724607296285, | |
| "loss": 1.1498, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.20920502092050208, | |
| "grad_norm": 0.17045779526233673, | |
| "learning_rate": 0.00012880708067281477, | |
| "loss": 1.1511, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.21385402138540213, | |
| "grad_norm": 0.2381921112537384, | |
| "learning_rate": 0.00012594718924213008, | |
| "loss": 1.0835, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.21850302185030218, | |
| "grad_norm": 0.3426450192928314, | |
| "learning_rate": 0.00012307057141209415, | |
| "loss": 1.0434, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.22315202231520223, | |
| "grad_norm": 0.4425382912158966, | |
| "learning_rate": 0.0001201802443575756, | |
| "loss": 0.9782, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.22780102278010228, | |
| "grad_norm": 0.47294408082962036, | |
| "learning_rate": 0.0001172792396325264, | |
| "loss": 0.8836, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.23245002324500233, | |
| "grad_norm": 0.5693187713623047, | |
| "learning_rate": 0.00011437059999030035, | |
| "loss": 0.9676, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.23709902370990238, | |
| "grad_norm": 0.14201653003692627, | |
| "learning_rate": 0.00011145737619222516, | |
| "loss": 1.0578, | |
| "step": 51 | |
| }, | |
| { | |
| "epoch": 0.24174802417480243, | |
| "grad_norm": 0.15487229824066162, | |
| "learning_rate": 0.00010854262380777486, | |
| "loss": 1.0633, | |
| "step": 52 | |
| }, | |
| { | |
| "epoch": 0.24639702463970248, | |
| "grad_norm": 0.14283418655395508, | |
| "learning_rate": 0.0001056294000096997, | |
| "loss": 1.0856, | |
| "step": 53 | |
| }, | |
| { | |
| "epoch": 0.2510460251046025, | |
| "grad_norm": 0.14647558331489563, | |
| "learning_rate": 0.00010272076036747365, | |
| "loss": 1.123, | |
| "step": 54 | |
| }, | |
| { | |
| "epoch": 0.2556950255695026, | |
| "grad_norm": 0.16010554134845734, | |
| "learning_rate": 9.981975564242443e-05, | |
| "loss": 1.1116, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.2603440260344026, | |
| "grad_norm": 0.14617392420768738, | |
| "learning_rate": 9.692942858790591e-05, | |
| "loss": 1.1356, | |
| "step": 56 | |
| }, | |
| { | |
| "epoch": 0.2649930264993027, | |
| "grad_norm": 0.17232324182987213, | |
| "learning_rate": 9.405281075786995e-05, | |
| "loss": 1.112, | |
| "step": 57 | |
| }, | |
| { | |
| "epoch": 0.2696420269642027, | |
| "grad_norm": 0.18721264600753784, | |
| "learning_rate": 9.119291932718525e-05, | |
| "loss": 1.1253, | |
| "step": 58 | |
| }, | |
| { | |
| "epoch": 0.2742910274291027, | |
| "grad_norm": 0.23640522360801697, | |
| "learning_rate": 8.835275392703721e-05, | |
| "loss": 1.0711, | |
| "step": 59 | |
| }, | |
| { | |
| "epoch": 0.2789400278940028, | |
| "grad_norm": 0.29225069284439087, | |
| "learning_rate": 8.553529349872916e-05, | |
| "loss": 0.9971, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2835890283589028, | |
| "grad_norm": 0.36253005266189575, | |
| "learning_rate": 8.274349316918446e-05, | |
| "loss": 0.9234, | |
| "step": 61 | |
| }, | |
| { | |
| "epoch": 0.2882380288238029, | |
| "grad_norm": 0.38477060198783875, | |
| "learning_rate": 7.998028115142617e-05, | |
| "loss": 0.8265, | |
| "step": 62 | |
| }, | |
| { | |
| "epoch": 0.2928870292887029, | |
| "grad_norm": 0.49141454696655273, | |
| "learning_rate": 7.724855567328613e-05, | |
| "loss": 0.9709, | |
| "step": 63 | |
| }, | |
| { | |
| "epoch": 0.297536029753603, | |
| "grad_norm": 0.09308861941099167, | |
| "learning_rate": 7.455118193756419e-05, | |
| "loss": 1.0642, | |
| "step": 64 | |
| }, | |
| { | |
| "epoch": 0.302185030218503, | |
| "grad_norm": 0.11423233896493912, | |
| "learning_rate": 7.189098911682592e-05, | |
| "loss": 1.0881, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.3068340306834031, | |
| "grad_norm": 0.11385729163885117, | |
| "learning_rate": 6.927076738599152e-05, | |
| "loss": 1.0958, | |
| "step": 66 | |
| }, | |
| { | |
| "epoch": 0.3114830311483031, | |
| "grad_norm": 0.16382458806037903, | |
| "learning_rate": 6.669326499582755e-05, | |
| "loss": 1.1432, | |
| "step": 67 | |
| }, | |
| { | |
| "epoch": 0.31613203161320313, | |
| "grad_norm": 0.13493482768535614, | |
| "learning_rate": 6.416118539041135e-05, | |
| "loss": 1.1444, | |
| "step": 68 | |
| }, | |
| { | |
| "epoch": 0.3207810320781032, | |
| "grad_norm": 0.18623846769332886, | |
| "learning_rate": 6.167718437159147e-05, | |
| "loss": 1.1724, | |
| "step": 69 | |
| }, | |
| { | |
| "epoch": 0.32543003254300323, | |
| "grad_norm": 0.16176700592041016, | |
| "learning_rate": 5.924386731341842e-05, | |
| "loss": 1.0617, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.3300790330079033, | |
| "grad_norm": 0.20845215022563934, | |
| "learning_rate": 5.686378642946699e-05, | |
| "loss": 1.0322, | |
| "step": 71 | |
| }, | |
| { | |
| "epoch": 0.33472803347280333, | |
| "grad_norm": 0.22166885435581207, | |
| "learning_rate": 5.453943809591654e-05, | |
| "loss": 0.9453, | |
| "step": 72 | |
| }, | |
| { | |
| "epoch": 0.3393770339377034, | |
| "grad_norm": 0.349749356508255, | |
| "learning_rate": 5.227326023319743e-05, | |
| "loss": 0.9271, | |
| "step": 73 | |
| }, | |
| { | |
| "epoch": 0.34402603440260343, | |
| "grad_norm": 0.3437642753124237, | |
| "learning_rate": 5.006762974894872e-05, | |
| "loss": 0.874, | |
| "step": 74 | |
| }, | |
| { | |
| "epoch": 0.3486750348675035, | |
| "grad_norm": 0.4277116656303406, | |
| "learning_rate": 4.7924860044970615e-05, | |
| "loss": 0.8426, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.35332403533240353, | |
| "grad_norm": 0.0775565356016159, | |
| "learning_rate": 4.5847198590785394e-05, | |
| "loss": 1.0357, | |
| "step": 76 | |
| }, | |
| { | |
| "epoch": 0.3579730357973036, | |
| "grad_norm": 0.07587376981973648, | |
| "learning_rate": 4.383682456635199e-05, | |
| "loss": 1.0816, | |
| "step": 77 | |
| }, | |
| { | |
| "epoch": 0.36262203626220363, | |
| "grad_norm": 0.0855608880519867, | |
| "learning_rate": 4.1895846576407424e-05, | |
| "loss": 1.095, | |
| "step": 78 | |
| }, | |
| { | |
| "epoch": 0.36727103672710365, | |
| "grad_norm": 0.08497363328933716, | |
| "learning_rate": 4.002630043883159e-05, | |
| "loss": 1.1268, | |
| "step": 79 | |
| }, | |
| { | |
| "epoch": 0.3719200371920037, | |
| "grad_norm": 0.0938296765089035, | |
| "learning_rate": 3.8230147049355147e-05, | |
| "loss": 1.1187, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.37656903765690375, | |
| "grad_norm": 0.09680171310901642, | |
| "learning_rate": 3.650927032485101e-05, | |
| "loss": 1.1838, | |
| "step": 81 | |
| }, | |
| { | |
| "epoch": 0.3812180381218038, | |
| "grad_norm": 0.11150510609149933, | |
| "learning_rate": 3.486547522736562e-05, | |
| "loss": 1.1177, | |
| "step": 82 | |
| }, | |
| { | |
| "epoch": 0.38586703858670385, | |
| "grad_norm": 0.13839669525623322, | |
| "learning_rate": 3.3300485870962776e-05, | |
| "loss": 1.087, | |
| "step": 83 | |
| }, | |
| { | |
| "epoch": 0.3905160390516039, | |
| "grad_norm": 0.1885904222726822, | |
| "learning_rate": 3.1815943713366404e-05, | |
| "loss": 1.0186, | |
| "step": 84 | |
| }, | |
| { | |
| "epoch": 0.39516503951650395, | |
| "grad_norm": 0.243554025888443, | |
| "learning_rate": 3.041340583429789e-05, | |
| "loss": 0.8965, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.399814039981404, | |
| "grad_norm": 0.27477556467056274, | |
| "learning_rate": 2.9094343302314432e-05, | |
| "loss": 0.918, | |
| "step": 86 | |
| }, | |
| { | |
| "epoch": 0.40446304044630405, | |
| "grad_norm": 0.31194981932640076, | |
| "learning_rate": 2.78601396318614e-05, | |
| "loss": 0.7524, | |
| "step": 87 | |
| }, | |
| { | |
| "epoch": 0.40911204091120407, | |
| "grad_norm": 0.3639957308769226, | |
| "learning_rate": 2.6712089332156633e-05, | |
| "loss": 0.9365, | |
| "step": 88 | |
| }, | |
| { | |
| "epoch": 0.41376104137610414, | |
| "grad_norm": 0.08689970523118973, | |
| "learning_rate": 2.5651396549429086e-05, | |
| "loss": 1.0602, | |
| "step": 89 | |
| }, | |
| { | |
| "epoch": 0.41841004184100417, | |
| "grad_norm": 0.08937124907970428, | |
| "learning_rate": 2.4679173803935662e-05, | |
| "loss": 1.0554, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.42305904230590424, | |
| "grad_norm": 0.09696152806282043, | |
| "learning_rate": 2.3796440823081167e-05, | |
| "loss": 1.1068, | |
| "step": 91 | |
| }, | |
| { | |
| "epoch": 0.42770804277080426, | |
| "grad_norm": 0.09235560148954391, | |
| "learning_rate": 2.3004123471865e-05, | |
| "loss": 1.1125, | |
| "step": 92 | |
| }, | |
| { | |
| "epoch": 0.43235704323570434, | |
| "grad_norm": 0.10225149989128113, | |
| "learning_rate": 2.2303052781776664e-05, | |
| "loss": 1.1077, | |
| "step": 93 | |
| }, | |
| { | |
| "epoch": 0.43700604370060436, | |
| "grad_norm": 0.11181271821260452, | |
| "learning_rate": 2.169396407915849e-05, | |
| "loss": 1.1302, | |
| "step": 94 | |
| }, | |
| { | |
| "epoch": 0.44165504416550444, | |
| "grad_norm": 0.14333005249500275, | |
| "learning_rate": 2.1177496213949837e-05, | |
| "loss": 1.1268, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.44630404463040446, | |
| "grad_norm": 0.19770824909210205, | |
| "learning_rate": 2.0754190889621745e-05, | |
| "loss": 1.0529, | |
| "step": 96 | |
| }, | |
| { | |
| "epoch": 0.4509530450953045, | |
| "grad_norm": 0.2224006950855255, | |
| "learning_rate": 2.0424492095004746e-05, | |
| "loss": 0.9715, | |
| "step": 97 | |
| }, | |
| { | |
| "epoch": 0.45560204556020456, | |
| "grad_norm": 0.26830530166625977, | |
| "learning_rate": 2.0188745638605954e-05, | |
| "loss": 0.8829, | |
| "step": 98 | |
| }, | |
| { | |
| "epoch": 0.4602510460251046, | |
| "grad_norm": 0.2952977120876312, | |
| "learning_rate": 2.0047198785903658e-05, | |
| "loss": 0.8337, | |
| "step": 99 | |
| }, | |
| { | |
| "epoch": 0.46490004649000466, | |
| "grad_norm": 0.5423007607460022, | |
| "learning_rate": 2e-05, | |
| "loss": 0.8743, | |
| "step": 100 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8.384528854810624e+17, | |
| "train_batch_size": 6, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |