{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.25250227479526843, "eval_steps": 500, "global_step": 555, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00045495905368516835, "grad_norm": 9.424069126182447, "learning_rate": 5e-06, "loss": 0.1263, "step": 1 }, { "epoch": 0.0009099181073703367, "grad_norm": 10.713711803681479, "learning_rate": 4.999999897855645e-06, "loss": 0.1917, "step": 2 }, { "epoch": 0.001364877161055505, "grad_norm": 14.140338542227335, "learning_rate": 4.9999995914225884e-06, "loss": 0.1578, "step": 3 }, { "epoch": 0.0018198362147406734, "grad_norm": 3.597475372738082, "learning_rate": 4.999999080700855e-06, "loss": 0.1266, "step": 4 }, { "epoch": 0.0022747952684258415, "grad_norm": 6.105724745538744, "learning_rate": 4.999998365690486e-06, "loss": 0.1182, "step": 5 }, { "epoch": 0.00272975432211101, "grad_norm": 2.3169263707348047, "learning_rate": 4.999997446391542e-06, "loss": 0.0837, "step": 6 }, { "epoch": 0.0031847133757961785, "grad_norm": 1.5580577162131912, "learning_rate": 4.999996322804095e-06, "loss": 0.0761, "step": 7 }, { "epoch": 0.003639672429481347, "grad_norm": 7.8184917268265455, "learning_rate": 4.999994994928239e-06, "loss": 0.0922, "step": 8 }, { "epoch": 0.004094631483166515, "grad_norm": 1.0452365500769838, "learning_rate": 4.999993462764082e-06, "loss": 0.0478, "step": 9 }, { "epoch": 0.004549590536851683, "grad_norm": 13.965028712537013, "learning_rate": 4.999991726311749e-06, "loss": 0.0846, "step": 10 }, { "epoch": 0.005004549590536852, "grad_norm": 5.125925143296543, "learning_rate": 4.999989785571382e-06, "loss": 0.0881, "step": 11 }, { "epoch": 0.00545950864422202, "grad_norm": 2.2007100936893242, "learning_rate": 4.999987640543139e-06, "loss": 0.0896, "step": 12 }, { "epoch": 0.005914467697907188, "grad_norm": 1.4259973806728683, "learning_rate": 4.999985291227196e-06, "loss": 0.0707, "step": 13 }, { "epoch": 0.006369426751592357, "grad_norm": 2.5296942505090376, "learning_rate": 4.999982737623746e-06, "loss": 0.1089, "step": 14 }, { "epoch": 0.006824385805277525, "grad_norm": 1.9950751818037182, "learning_rate": 4.999979979732995e-06, "loss": 0.0868, "step": 15 }, { "epoch": 0.007279344858962694, "grad_norm": 1.3920340257758652, "learning_rate": 4.999977017555171e-06, "loss": 0.0667, "step": 16 }, { "epoch": 0.0077343039126478615, "grad_norm": 1.6901228042476675, "learning_rate": 4.999973851090514e-06, "loss": 0.1032, "step": 17 }, { "epoch": 0.00818926296633303, "grad_norm": 1.8139241575982044, "learning_rate": 4.999970480339284e-06, "loss": 0.0848, "step": 18 }, { "epoch": 0.008644222020018199, "grad_norm": 2.792209216647474, "learning_rate": 4.9999669053017564e-06, "loss": 0.0804, "step": 19 }, { "epoch": 0.009099181073703366, "grad_norm": 1.9016199513748882, "learning_rate": 4.9999631259782235e-06, "loss": 0.0612, "step": 20 }, { "epoch": 0.009554140127388535, "grad_norm": 1.9965871271660314, "learning_rate": 4.999959142368993e-06, "loss": 0.0969, "step": 21 }, { "epoch": 0.010009099181073703, "grad_norm": 2.0914009303085033, "learning_rate": 4.999954954474391e-06, "loss": 0.0697, "step": 22 }, { "epoch": 0.010464058234758872, "grad_norm": 1.4245797905814712, "learning_rate": 4.9999505622947594e-06, "loss": 0.0832, "step": 23 }, { "epoch": 0.01091901728844404, "grad_norm": 1.5918336957933508, "learning_rate": 4.999945965830458e-06, "loss": 0.0995, "step": 24 }, { "epoch": 0.011373976342129208, "grad_norm": 1.5479918567604505, "learning_rate": 4.999941165081863e-06, "loss": 0.0807, "step": 25 }, { "epoch": 0.011828935395814377, "grad_norm": 1.0230515440884096, "learning_rate": 4.999936160049364e-06, "loss": 0.0643, "step": 26 }, { "epoch": 0.012283894449499545, "grad_norm": 1.5686069800283207, "learning_rate": 4.999930950733373e-06, "loss": 0.0931, "step": 27 }, { "epoch": 0.012738853503184714, "grad_norm": 1.2554970571666952, "learning_rate": 4.999925537134312e-06, "loss": 0.0815, "step": 28 }, { "epoch": 0.013193812556869881, "grad_norm": 2.006239028459661, "learning_rate": 4.9999199192526286e-06, "loss": 0.1058, "step": 29 }, { "epoch": 0.01364877161055505, "grad_norm": 1.4436359414979703, "learning_rate": 4.9999140970887775e-06, "loss": 0.0869, "step": 30 }, { "epoch": 0.014103730664240218, "grad_norm": 1.9267705188401287, "learning_rate": 4.999908070643236e-06, "loss": 0.0781, "step": 31 }, { "epoch": 0.014558689717925387, "grad_norm": 1.4021843278575745, "learning_rate": 4.999901839916495e-06, "loss": 0.0623, "step": 32 }, { "epoch": 0.015013648771610554, "grad_norm": 1.208153452070421, "learning_rate": 4.999895404909067e-06, "loss": 0.063, "step": 33 }, { "epoch": 0.015468607825295723, "grad_norm": 2.273185304548797, "learning_rate": 4.999888765621476e-06, "loss": 0.0901, "step": 34 }, { "epoch": 0.01592356687898089, "grad_norm": 1.0383667898934177, "learning_rate": 4.999881922054264e-06, "loss": 0.0529, "step": 35 }, { "epoch": 0.01637852593266606, "grad_norm": 1.1537070720156926, "learning_rate": 4.999874874207991e-06, "loss": 0.0539, "step": 36 }, { "epoch": 0.01683348498635123, "grad_norm": 7.004645996036244, "learning_rate": 4.999867622083232e-06, "loss": 0.1028, "step": 37 }, { "epoch": 0.017288444040036398, "grad_norm": 2.6515111867419217, "learning_rate": 4.99986016568058e-06, "loss": 0.0958, "step": 38 }, { "epoch": 0.017743403093721567, "grad_norm": 1.5437471575403858, "learning_rate": 4.999852505000646e-06, "loss": 0.0738, "step": 39 }, { "epoch": 0.018198362147406732, "grad_norm": 1.4798019454902687, "learning_rate": 4.999844640044053e-06, "loss": 0.0695, "step": 40 }, { "epoch": 0.0186533212010919, "grad_norm": 1.3064785518172293, "learning_rate": 4.999836570811445e-06, "loss": 0.0738, "step": 41 }, { "epoch": 0.01910828025477707, "grad_norm": 2.6092308850144086, "learning_rate": 4.999828297303483e-06, "loss": 0.0854, "step": 42 }, { "epoch": 0.019563239308462238, "grad_norm": 1.1588535962376392, "learning_rate": 4.9998198195208405e-06, "loss": 0.0783, "step": 43 }, { "epoch": 0.020018198362147407, "grad_norm": 1.441993661454023, "learning_rate": 4.999811137464212e-06, "loss": 0.0826, "step": 44 }, { "epoch": 0.020473157415832575, "grad_norm": 1.6833012903770388, "learning_rate": 4.999802251134307e-06, "loss": 0.0932, "step": 45 }, { "epoch": 0.020928116469517744, "grad_norm": 1.061841465675538, "learning_rate": 4.99979316053185e-06, "loss": 0.0602, "step": 46 }, { "epoch": 0.021383075523202913, "grad_norm": 6.235552737213317, "learning_rate": 4.999783865657585e-06, "loss": 0.1756, "step": 47 }, { "epoch": 0.02183803457688808, "grad_norm": 4.150615789136632, "learning_rate": 4.999774366512272e-06, "loss": 0.1765, "step": 48 }, { "epoch": 0.022292993630573247, "grad_norm": 1.6544370579186418, "learning_rate": 4.9997646630966865e-06, "loss": 0.0841, "step": 49 }, { "epoch": 0.022747952684258416, "grad_norm": 1.3759378168890601, "learning_rate": 4.999754755411621e-06, "loss": 0.0669, "step": 50 }, { "epoch": 0.023202911737943584, "grad_norm": 1.182095773050476, "learning_rate": 4.9997446434578865e-06, "loss": 0.0653, "step": 51 }, { "epoch": 0.023657870791628753, "grad_norm": 1.035739970953985, "learning_rate": 4.999734327236307e-06, "loss": 0.0678, "step": 52 }, { "epoch": 0.024112829845313922, "grad_norm": 0.7085636728418604, "learning_rate": 4.999723806747728e-06, "loss": 0.0498, "step": 53 }, { "epoch": 0.02456778889899909, "grad_norm": 2.2722150874810185, "learning_rate": 4.99971308199301e-06, "loss": 0.0666, "step": 54 }, { "epoch": 0.02502274795268426, "grad_norm": 0.9420150282219443, "learning_rate": 4.999702152973025e-06, "loss": 0.0516, "step": 55 }, { "epoch": 0.025477707006369428, "grad_norm": 1.0929779986912587, "learning_rate": 4.9996910196886694e-06, "loss": 0.0593, "step": 56 }, { "epoch": 0.025932666060054597, "grad_norm": 0.783956655534044, "learning_rate": 4.999679682140852e-06, "loss": 0.0377, "step": 57 }, { "epoch": 0.026387625113739762, "grad_norm": 1.5218504285246661, "learning_rate": 4.999668140330499e-06, "loss": 0.1052, "step": 58 }, { "epoch": 0.02684258416742493, "grad_norm": 1.0791722855226673, "learning_rate": 4.999656394258555e-06, "loss": 0.0632, "step": 59 }, { "epoch": 0.0272975432211101, "grad_norm": 0.9557512868551324, "learning_rate": 4.999644443925978e-06, "loss": 0.0634, "step": 60 }, { "epoch": 0.027752502274795268, "grad_norm": 1.0667565930302423, "learning_rate": 4.999632289333746e-06, "loss": 0.0518, "step": 61 }, { "epoch": 0.028207461328480437, "grad_norm": 1.646318745184601, "learning_rate": 4.999619930482852e-06, "loss": 0.0766, "step": 62 }, { "epoch": 0.028662420382165606, "grad_norm": 1.2186400155674944, "learning_rate": 4.999607367374304e-06, "loss": 0.0741, "step": 63 }, { "epoch": 0.029117379435850774, "grad_norm": 1.0807362476000584, "learning_rate": 4.999594600009131e-06, "loss": 0.0553, "step": 64 }, { "epoch": 0.029572338489535943, "grad_norm": 1.3403222529377026, "learning_rate": 4.999581628388375e-06, "loss": 0.0886, "step": 65 }, { "epoch": 0.03002729754322111, "grad_norm": 1.5384085589580356, "learning_rate": 4.999568452513097e-06, "loss": 0.1371, "step": 66 }, { "epoch": 0.030482256596906277, "grad_norm": 1.3705617237121213, "learning_rate": 4.9995550723843726e-06, "loss": 0.0766, "step": 67 }, { "epoch": 0.030937215650591446, "grad_norm": 1.0692361538736996, "learning_rate": 4.999541488003295e-06, "loss": 0.0607, "step": 68 }, { "epoch": 0.03139217470427662, "grad_norm": 0.9190382606343962, "learning_rate": 4.999527699370975e-06, "loss": 0.0598, "step": 69 }, { "epoch": 0.03184713375796178, "grad_norm": 1.182484013540807, "learning_rate": 4.99951370648854e-06, "loss": 0.0583, "step": 70 }, { "epoch": 0.03230209281164695, "grad_norm": 1.0728084003134533, "learning_rate": 4.999499509357132e-06, "loss": 0.0595, "step": 71 }, { "epoch": 0.03275705186533212, "grad_norm": 4.354112851430141, "learning_rate": 4.999485107977912e-06, "loss": 0.063, "step": 72 }, { "epoch": 0.033212010919017286, "grad_norm": 1.5709570309947747, "learning_rate": 4.999470502352057e-06, "loss": 0.0511, "step": 73 }, { "epoch": 0.03366696997270246, "grad_norm": 5.936498302941106, "learning_rate": 4.999455692480759e-06, "loss": 0.0733, "step": 74 }, { "epoch": 0.034121929026387623, "grad_norm": 2.227018438923651, "learning_rate": 4.999440678365229e-06, "loss": 0.0504, "step": 75 }, { "epoch": 0.034576888080072796, "grad_norm": 1.7106603940792875, "learning_rate": 4.999425460006695e-06, "loss": 0.0672, "step": 76 }, { "epoch": 0.03503184713375796, "grad_norm": 3.603233120133456, "learning_rate": 4.9994100374063995e-06, "loss": 0.0605, "step": 77 }, { "epoch": 0.03548680618744313, "grad_norm": 1.3736083353388526, "learning_rate": 4.9993944105656035e-06, "loss": 0.0892, "step": 78 }, { "epoch": 0.0359417652411283, "grad_norm": 1.0823220835311542, "learning_rate": 4.999378579485582e-06, "loss": 0.0657, "step": 79 }, { "epoch": 0.036396724294813464, "grad_norm": 2.150924215229101, "learning_rate": 4.999362544167632e-06, "loss": 0.0787, "step": 80 }, { "epoch": 0.036851683348498636, "grad_norm": 1.7178625535843866, "learning_rate": 4.99934630461306e-06, "loss": 0.0428, "step": 81 }, { "epoch": 0.0373066424021838, "grad_norm": 1.3444344286672891, "learning_rate": 4.999329860823197e-06, "loss": 0.0683, "step": 82 }, { "epoch": 0.03776160145586897, "grad_norm": 0.9890758669005086, "learning_rate": 4.999313212799383e-06, "loss": 0.0684, "step": 83 }, { "epoch": 0.03821656050955414, "grad_norm": 1.341850788541947, "learning_rate": 4.99929636054298e-06, "loss": 0.0683, "step": 84 }, { "epoch": 0.03867151956323931, "grad_norm": 1.1425756088631416, "learning_rate": 4.999279304055366e-06, "loss": 0.0781, "step": 85 }, { "epoch": 0.039126478616924476, "grad_norm": 1.1872176417370066, "learning_rate": 4.999262043337933e-06, "loss": 0.0652, "step": 86 }, { "epoch": 0.03958143767060965, "grad_norm": 1.1143093977494338, "learning_rate": 4.999244578392094e-06, "loss": 0.0752, "step": 87 }, { "epoch": 0.040036396724294813, "grad_norm": 1.2369204202074342, "learning_rate": 4.9992269092192736e-06, "loss": 0.0822, "step": 88 }, { "epoch": 0.04049135577797998, "grad_norm": 1.1130108244588752, "learning_rate": 4.9992090358209166e-06, "loss": 0.0548, "step": 89 }, { "epoch": 0.04094631483166515, "grad_norm": 1.0691923631453497, "learning_rate": 4.9991909581984835e-06, "loss": 0.058, "step": 90 }, { "epoch": 0.041401273885350316, "grad_norm": 0.8020461125153492, "learning_rate": 4.999172676353451e-06, "loss": 0.0341, "step": 91 }, { "epoch": 0.04185623293903549, "grad_norm": 0.8729429986066347, "learning_rate": 4.999154190287314e-06, "loss": 0.0524, "step": 92 }, { "epoch": 0.042311191992720654, "grad_norm": 1.3186052508212676, "learning_rate": 4.999135500001583e-06, "loss": 0.1067, "step": 93 }, { "epoch": 0.042766151046405826, "grad_norm": 0.9402363215265714, "learning_rate": 4.9991166054977844e-06, "loss": 0.0631, "step": 94 }, { "epoch": 0.04322111010009099, "grad_norm": 1.8336904222617239, "learning_rate": 4.999097506777463e-06, "loss": 0.0897, "step": 95 }, { "epoch": 0.04367606915377616, "grad_norm": 1.0700343361679827, "learning_rate": 4.999078203842179e-06, "loss": 0.084, "step": 96 }, { "epoch": 0.04413102820746133, "grad_norm": 0.8783050881223096, "learning_rate": 4.999058696693511e-06, "loss": 0.0421, "step": 97 }, { "epoch": 0.044585987261146494, "grad_norm": 0.9801149440827129, "learning_rate": 4.99903898533305e-06, "loss": 0.0616, "step": 98 }, { "epoch": 0.045040946314831666, "grad_norm": 0.9471216563783236, "learning_rate": 4.99901906976241e-06, "loss": 0.0614, "step": 99 }, { "epoch": 0.04549590536851683, "grad_norm": 1.1616379193988644, "learning_rate": 4.998998949983217e-06, "loss": 0.0604, "step": 100 }, { "epoch": 0.045950864422202004, "grad_norm": 1.123688602696856, "learning_rate": 4.998978625997115e-06, "loss": 0.0831, "step": 101 }, { "epoch": 0.04640582347588717, "grad_norm": 1.1154387442545128, "learning_rate": 4.998958097805765e-06, "loss": 0.0686, "step": 102 }, { "epoch": 0.04686078252957234, "grad_norm": 0.9538196832365717, "learning_rate": 4.9989373654108445e-06, "loss": 0.0586, "step": 103 }, { "epoch": 0.047315741583257506, "grad_norm": 14.714854180857428, "learning_rate": 4.9989164288140465e-06, "loss": 0.2765, "step": 104 }, { "epoch": 0.04777070063694268, "grad_norm": 1.5310230722630254, "learning_rate": 4.998895288017085e-06, "loss": 0.1114, "step": 105 }, { "epoch": 0.048225659690627844, "grad_norm": 0.8704851988514942, "learning_rate": 4.998873943021684e-06, "loss": 0.0481, "step": 106 }, { "epoch": 0.04868061874431301, "grad_norm": 0.9229853294124807, "learning_rate": 4.998852393829589e-06, "loss": 0.0559, "step": 107 }, { "epoch": 0.04913557779799818, "grad_norm": 1.6890853415724327, "learning_rate": 4.9988306404425625e-06, "loss": 0.1104, "step": 108 }, { "epoch": 0.049590536851683346, "grad_norm": 0.9281407020626959, "learning_rate": 4.99880868286238e-06, "loss": 0.0636, "step": 109 }, { "epoch": 0.05004549590536852, "grad_norm": 1.2440415104108336, "learning_rate": 4.998786521090836e-06, "loss": 0.0522, "step": 110 }, { "epoch": 0.050500454959053684, "grad_norm": 1.06604652034606, "learning_rate": 4.9987641551297426e-06, "loss": 0.0916, "step": 111 }, { "epoch": 0.050955414012738856, "grad_norm": 0.9619782747004665, "learning_rate": 4.998741584980926e-06, "loss": 0.0822, "step": 112 }, { "epoch": 0.05141037306642402, "grad_norm": 1.0679619427370142, "learning_rate": 4.9987188106462314e-06, "loss": 0.0644, "step": 113 }, { "epoch": 0.051865332120109194, "grad_norm": 0.8424012677371406, "learning_rate": 4.99869583212752e-06, "loss": 0.0536, "step": 114 }, { "epoch": 0.05232029117379436, "grad_norm": 1.660603270099433, "learning_rate": 4.9986726494266694e-06, "loss": 0.1336, "step": 115 }, { "epoch": 0.052775250227479524, "grad_norm": 1.0314643506984187, "learning_rate": 4.998649262545574e-06, "loss": 0.0606, "step": 116 }, { "epoch": 0.053230209281164696, "grad_norm": 0.9468486095046134, "learning_rate": 4.998625671486144e-06, "loss": 0.0598, "step": 117 }, { "epoch": 0.05368516833484986, "grad_norm": 0.8800045267913842, "learning_rate": 4.998601876250308e-06, "loss": 0.06, "step": 118 }, { "epoch": 0.054140127388535034, "grad_norm": 1.0192910760666323, "learning_rate": 4.998577876840011e-06, "loss": 0.0601, "step": 119 }, { "epoch": 0.0545950864422202, "grad_norm": 0.9462635574827357, "learning_rate": 4.9985536732572124e-06, "loss": 0.06, "step": 120 }, { "epoch": 0.05505004549590537, "grad_norm": 0.7487116084320051, "learning_rate": 4.998529265503891e-06, "loss": 0.0458, "step": 121 }, { "epoch": 0.055505004549590536, "grad_norm": 1.0663282141956507, "learning_rate": 4.9985046535820416e-06, "loss": 0.0758, "step": 122 }, { "epoch": 0.05595996360327571, "grad_norm": 1.7476635252011261, "learning_rate": 4.998479837493675e-06, "loss": 0.0876, "step": 123 }, { "epoch": 0.056414922656960874, "grad_norm": 1.1513932571098853, "learning_rate": 4.9984548172408195e-06, "loss": 0.0475, "step": 124 }, { "epoch": 0.05686988171064604, "grad_norm": 97.54679492281674, "learning_rate": 4.998429592825519e-06, "loss": 0.2117, "step": 125 }, { "epoch": 0.05732484076433121, "grad_norm": 1.2146893500357796, "learning_rate": 4.998404164249835e-06, "loss": 0.0887, "step": 126 }, { "epoch": 0.05777979981801638, "grad_norm": 0.8319799978985719, "learning_rate": 4.998378531515845e-06, "loss": 0.0411, "step": 127 }, { "epoch": 0.05823475887170155, "grad_norm": 1.5818516008522756, "learning_rate": 4.998352694625645e-06, "loss": 0.068, "step": 128 }, { "epoch": 0.058689717925386714, "grad_norm": 0.883733186490376, "learning_rate": 4.998326653581343e-06, "loss": 0.0595, "step": 129 }, { "epoch": 0.059144676979071886, "grad_norm": 0.9357726879327158, "learning_rate": 4.998300408385072e-06, "loss": 0.0686, "step": 130 }, { "epoch": 0.05959963603275705, "grad_norm": 1.3606472296483436, "learning_rate": 4.998273959038972e-06, "loss": 0.0837, "step": 131 }, { "epoch": 0.06005459508644222, "grad_norm": 0.9597337111291308, "learning_rate": 4.998247305545207e-06, "loss": 0.0733, "step": 132 }, { "epoch": 0.06050955414012739, "grad_norm": 0.7271469650592398, "learning_rate": 4.998220447905953e-06, "loss": 0.0454, "step": 133 }, { "epoch": 0.060964513193812554, "grad_norm": 0.9630498239095886, "learning_rate": 4.998193386123408e-06, "loss": 0.074, "step": 134 }, { "epoch": 0.061419472247497726, "grad_norm": 1.133544314724227, "learning_rate": 4.99816612019978e-06, "loss": 0.077, "step": 135 }, { "epoch": 0.06187443130118289, "grad_norm": 4.162875613842665, "learning_rate": 4.998138650137298e-06, "loss": 0.1461, "step": 136 }, { "epoch": 0.062329390354868064, "grad_norm": 1.02851611153301, "learning_rate": 4.998110975938208e-06, "loss": 0.0883, "step": 137 }, { "epoch": 0.06278434940855324, "grad_norm": 1.4803017864082986, "learning_rate": 4.998083097604769e-06, "loss": 0.093, "step": 138 }, { "epoch": 0.0632393084622384, "grad_norm": 0.775173461523887, "learning_rate": 4.998055015139261e-06, "loss": 0.0446, "step": 139 }, { "epoch": 0.06369426751592357, "grad_norm": 0.9314427643573137, "learning_rate": 4.998026728543979e-06, "loss": 0.0627, "step": 140 }, { "epoch": 0.06414922656960874, "grad_norm": 0.8532842969957802, "learning_rate": 4.997998237821233e-06, "loss": 0.07, "step": 141 }, { "epoch": 0.0646041856232939, "grad_norm": 0.8003964270143441, "learning_rate": 4.997969542973352e-06, "loss": 0.0563, "step": 142 }, { "epoch": 0.06505914467697907, "grad_norm": 1.0449654693074535, "learning_rate": 4.997940644002681e-06, "loss": 0.0705, "step": 143 }, { "epoch": 0.06551410373066424, "grad_norm": 1.2317539206735935, "learning_rate": 4.997911540911581e-06, "loss": 0.0552, "step": 144 }, { "epoch": 0.06596906278434941, "grad_norm": 1.0170288864286834, "learning_rate": 4.99788223370243e-06, "loss": 0.075, "step": 145 }, { "epoch": 0.06642402183803457, "grad_norm": 2.1516221031707796, "learning_rate": 4.9978527223776245e-06, "loss": 0.1294, "step": 146 }, { "epoch": 0.06687898089171974, "grad_norm": 0.8159636795919125, "learning_rate": 4.9978230069395735e-06, "loss": 0.0512, "step": 147 }, { "epoch": 0.06733393994540492, "grad_norm": 1.0575473809333984, "learning_rate": 4.9977930873907065e-06, "loss": 0.0598, "step": 148 }, { "epoch": 0.06778889899909009, "grad_norm": 1.0958109016760909, "learning_rate": 4.997762963733468e-06, "loss": 0.074, "step": 149 }, { "epoch": 0.06824385805277525, "grad_norm": 1.047477211054204, "learning_rate": 4.997732635970321e-06, "loss": 0.0539, "step": 150 }, { "epoch": 0.06869881710646042, "grad_norm": 1.0301191819422422, "learning_rate": 4.9977021041037425e-06, "loss": 0.0686, "step": 151 }, { "epoch": 0.06915377616014559, "grad_norm": 1.225998339573777, "learning_rate": 4.9976713681362265e-06, "loss": 0.0859, "step": 152 }, { "epoch": 0.06960873521383075, "grad_norm": 1.416119617095304, "learning_rate": 4.997640428070286e-06, "loss": 0.1051, "step": 153 }, { "epoch": 0.07006369426751592, "grad_norm": 0.9227148160074169, "learning_rate": 4.99760928390845e-06, "loss": 0.0476, "step": 154 }, { "epoch": 0.0705186533212011, "grad_norm": 0.9417296172183, "learning_rate": 4.997577935653262e-06, "loss": 0.0546, "step": 155 }, { "epoch": 0.07097361237488627, "grad_norm": 0.7429922167271485, "learning_rate": 4.9975463833072835e-06, "loss": 0.0438, "step": 156 }, { "epoch": 0.07142857142857142, "grad_norm": 1.1317968054046752, "learning_rate": 4.997514626873093e-06, "loss": 0.0723, "step": 157 }, { "epoch": 0.0718835304822566, "grad_norm": 0.894309839547546, "learning_rate": 4.997482666353287e-06, "loss": 0.0484, "step": 158 }, { "epoch": 0.07233848953594177, "grad_norm": 1.2064896460901124, "learning_rate": 4.997450501750476e-06, "loss": 0.0686, "step": 159 }, { "epoch": 0.07279344858962693, "grad_norm": 1.0338993985106997, "learning_rate": 4.997418133067288e-06, "loss": 0.066, "step": 160 }, { "epoch": 0.0732484076433121, "grad_norm": 1.0854078217047458, "learning_rate": 4.997385560306368e-06, "loss": 0.075, "step": 161 }, { "epoch": 0.07370336669699727, "grad_norm": 0.9955556312708298, "learning_rate": 4.997352783470379e-06, "loss": 0.0693, "step": 162 }, { "epoch": 0.07415832575068244, "grad_norm": 1.1119344699280262, "learning_rate": 4.997319802561997e-06, "loss": 0.0687, "step": 163 }, { "epoch": 0.0746132848043676, "grad_norm": 0.8118992710097626, "learning_rate": 4.9972866175839196e-06, "loss": 0.061, "step": 164 }, { "epoch": 0.07506824385805277, "grad_norm": 1.0509201052861925, "learning_rate": 4.9972532285388575e-06, "loss": 0.0738, "step": 165 }, { "epoch": 0.07552320291173795, "grad_norm": 1.1660685920656126, "learning_rate": 4.997219635429538e-06, "loss": 0.1018, "step": 166 }, { "epoch": 0.07597816196542312, "grad_norm": 0.9894981496034668, "learning_rate": 4.997185838258709e-06, "loss": 0.0534, "step": 167 }, { "epoch": 0.07643312101910828, "grad_norm": 0.9397553289113793, "learning_rate": 4.997151837029129e-06, "loss": 0.0527, "step": 168 }, { "epoch": 0.07688808007279345, "grad_norm": 0.9368221512292729, "learning_rate": 4.997117631743579e-06, "loss": 0.0648, "step": 169 }, { "epoch": 0.07734303912647862, "grad_norm": 0.898690664067523, "learning_rate": 4.997083222404852e-06, "loss": 0.0479, "step": 170 }, { "epoch": 0.07779799818016378, "grad_norm": 0.835250569463016, "learning_rate": 4.997048609015762e-06, "loss": 0.0528, "step": 171 }, { "epoch": 0.07825295723384895, "grad_norm": 0.9098471940978452, "learning_rate": 4.997013791579136e-06, "loss": 0.0641, "step": 172 }, { "epoch": 0.07870791628753412, "grad_norm": 0.9538942863622895, "learning_rate": 4.996978770097819e-06, "loss": 0.0648, "step": 173 }, { "epoch": 0.0791628753412193, "grad_norm": 0.9163372515795332, "learning_rate": 4.996943544574673e-06, "loss": 0.0682, "step": 174 }, { "epoch": 0.07961783439490445, "grad_norm": 0.8193165634479148, "learning_rate": 4.996908115012576e-06, "loss": 0.0485, "step": 175 }, { "epoch": 0.08007279344858963, "grad_norm": 1.0278777387100766, "learning_rate": 4.996872481414425e-06, "loss": 0.0741, "step": 176 }, { "epoch": 0.0805277525022748, "grad_norm": 1.8323226365700802, "learning_rate": 4.9968366437831305e-06, "loss": 0.1107, "step": 177 }, { "epoch": 0.08098271155595996, "grad_norm": 0.5562843681536768, "learning_rate": 4.99680060212162e-06, "loss": 0.0379, "step": 178 }, { "epoch": 0.08143767060964513, "grad_norm": 0.6982410679992989, "learning_rate": 4.996764356432841e-06, "loss": 0.0576, "step": 179 }, { "epoch": 0.0818926296633303, "grad_norm": 0.9996693552976796, "learning_rate": 4.996727906719754e-06, "loss": 0.056, "step": 180 }, { "epoch": 0.08234758871701547, "grad_norm": 0.8092230365331524, "learning_rate": 4.9966912529853365e-06, "loss": 0.036, "step": 181 }, { "epoch": 0.08280254777070063, "grad_norm": 0.8856317784665715, "learning_rate": 4.996654395232585e-06, "loss": 0.0546, "step": 182 }, { "epoch": 0.0832575068243858, "grad_norm": 0.7648943084887926, "learning_rate": 4.996617333464512e-06, "loss": 0.0456, "step": 183 }, { "epoch": 0.08371246587807098, "grad_norm": 0.8896960831413809, "learning_rate": 4.996580067684145e-06, "loss": 0.0505, "step": 184 }, { "epoch": 0.08416742493175614, "grad_norm": 0.8819070603063018, "learning_rate": 4.996542597894528e-06, "loss": 0.0833, "step": 185 }, { "epoch": 0.08462238398544131, "grad_norm": 0.8756856388162975, "learning_rate": 4.996504924098726e-06, "loss": 0.0641, "step": 186 }, { "epoch": 0.08507734303912648, "grad_norm": 0.8527408544485862, "learning_rate": 4.9964670462998145e-06, "loss": 0.0553, "step": 187 }, { "epoch": 0.08553230209281165, "grad_norm": 0.9875356023767464, "learning_rate": 4.99642896450089e-06, "loss": 0.0874, "step": 188 }, { "epoch": 0.08598726114649681, "grad_norm": 2.0664437318649003, "learning_rate": 4.9963906787050656e-06, "loss": 0.0901, "step": 189 }, { "epoch": 0.08644222020018198, "grad_norm": 0.772276028123917, "learning_rate": 4.996352188915467e-06, "loss": 0.0457, "step": 190 }, { "epoch": 0.08689717925386715, "grad_norm": 1.5995533229184502, "learning_rate": 4.996313495135242e-06, "loss": 0.0902, "step": 191 }, { "epoch": 0.08735213830755233, "grad_norm": 1.14262643514501, "learning_rate": 4.9962745973675505e-06, "loss": 0.0887, "step": 192 }, { "epoch": 0.08780709736123748, "grad_norm": 0.653471766542576, "learning_rate": 4.996235495615572e-06, "loss": 0.0381, "step": 193 }, { "epoch": 0.08826205641492266, "grad_norm": 1.21800497391657, "learning_rate": 4.996196189882503e-06, "loss": 0.0859, "step": 194 }, { "epoch": 0.08871701546860783, "grad_norm": 1.2184077345088562, "learning_rate": 4.996156680171552e-06, "loss": 0.0858, "step": 195 }, { "epoch": 0.08917197452229299, "grad_norm": 0.8525171751383268, "learning_rate": 4.996116966485951e-06, "loss": 0.0542, "step": 196 }, { "epoch": 0.08962693357597816, "grad_norm": 1.0438941172842933, "learning_rate": 4.996077048828944e-06, "loss": 0.0735, "step": 197 }, { "epoch": 0.09008189262966333, "grad_norm": 0.9982779135093925, "learning_rate": 4.996036927203793e-06, "loss": 0.0773, "step": 198 }, { "epoch": 0.0905368516833485, "grad_norm": 1.5215875068980074, "learning_rate": 4.995996601613775e-06, "loss": 0.0814, "step": 199 }, { "epoch": 0.09099181073703366, "grad_norm": 0.9525593904667519, "learning_rate": 4.9959560720621875e-06, "loss": 0.0631, "step": 200 }, { "epoch": 0.09144676979071883, "grad_norm": 1.6658936796296464, "learning_rate": 4.995915338552341e-06, "loss": 0.0892, "step": 201 }, { "epoch": 0.09190172884440401, "grad_norm": 1.0100426736293826, "learning_rate": 4.995874401087565e-06, "loss": 0.0618, "step": 202 }, { "epoch": 0.09235668789808917, "grad_norm": 1.2729210933806279, "learning_rate": 4.9958332596712035e-06, "loss": 0.0808, "step": 203 }, { "epoch": 0.09281164695177434, "grad_norm": 1.0142800844722413, "learning_rate": 4.99579191430662e-06, "loss": 0.0715, "step": 204 }, { "epoch": 0.09326660600545951, "grad_norm": 4.237455676216414, "learning_rate": 4.995750364997192e-06, "loss": 0.062, "step": 205 }, { "epoch": 0.09372156505914468, "grad_norm": 7.872559330750363, "learning_rate": 4.995708611746314e-06, "loss": 0.0548, "step": 206 }, { "epoch": 0.09417652411282984, "grad_norm": 1.2028032815765721, "learning_rate": 4.995666654557399e-06, "loss": 0.0678, "step": 207 }, { "epoch": 0.09463148316651501, "grad_norm": 0.9911372243080299, "learning_rate": 4.995624493433876e-06, "loss": 0.0728, "step": 208 }, { "epoch": 0.09508644222020018, "grad_norm": 2.5900155398471942, "learning_rate": 4.995582128379189e-06, "loss": 0.0822, "step": 209 }, { "epoch": 0.09554140127388536, "grad_norm": 1.4214627215980935, "learning_rate": 4.9955395593968e-06, "loss": 0.1096, "step": 210 }, { "epoch": 0.09599636032757052, "grad_norm": 11.75678149199321, "learning_rate": 4.99549678649019e-06, "loss": 0.0579, "step": 211 }, { "epoch": 0.09645131938125569, "grad_norm": 3.8898709501740747, "learning_rate": 4.99545380966285e-06, "loss": 0.0695, "step": 212 }, { "epoch": 0.09690627843494086, "grad_norm": 4.099783756040842, "learning_rate": 4.995410628918294e-06, "loss": 0.0711, "step": 213 }, { "epoch": 0.09736123748862602, "grad_norm": 3.9495811570453445, "learning_rate": 4.995367244260052e-06, "loss": 0.0871, "step": 214 }, { "epoch": 0.09781619654231119, "grad_norm": 0.7508672950199423, "learning_rate": 4.995323655691667e-06, "loss": 0.0369, "step": 215 }, { "epoch": 0.09827115559599636, "grad_norm": 1.3368080010868653, "learning_rate": 4.995279863216702e-06, "loss": 0.0752, "step": 216 }, { "epoch": 0.09872611464968153, "grad_norm": 0.8823975012529762, "learning_rate": 4.995235866838735e-06, "loss": 0.0695, "step": 217 }, { "epoch": 0.09918107370336669, "grad_norm": 0.8099194866460178, "learning_rate": 4.995191666561361e-06, "loss": 0.0561, "step": 218 }, { "epoch": 0.09963603275705187, "grad_norm": 0.6772333028080019, "learning_rate": 4.995147262388192e-06, "loss": 0.0441, "step": 219 }, { "epoch": 0.10009099181073704, "grad_norm": 0.9342067677666205, "learning_rate": 4.995102654322858e-06, "loss": 0.0613, "step": 220 }, { "epoch": 0.1005459508644222, "grad_norm": 0.7594825525973931, "learning_rate": 4.995057842369002e-06, "loss": 0.0349, "step": 221 }, { "epoch": 0.10100090991810737, "grad_norm": 0.8418616902443392, "learning_rate": 4.995012826530287e-06, "loss": 0.0693, "step": 222 }, { "epoch": 0.10145586897179254, "grad_norm": 1.4826966236644097, "learning_rate": 4.99496760681039e-06, "loss": 0.0971, "step": 223 }, { "epoch": 0.10191082802547771, "grad_norm": 1.3244278108579797, "learning_rate": 4.994922183213009e-06, "loss": 0.0963, "step": 224 }, { "epoch": 0.10236578707916287, "grad_norm": 0.5464933779715734, "learning_rate": 4.9948765557418535e-06, "loss": 0.0357, "step": 225 }, { "epoch": 0.10282074613284804, "grad_norm": 1.1325271027713097, "learning_rate": 4.994830724400653e-06, "loss": 0.0756, "step": 226 }, { "epoch": 0.10327570518653321, "grad_norm": 0.7823528354045581, "learning_rate": 4.994784689193151e-06, "loss": 0.0609, "step": 227 }, { "epoch": 0.10373066424021839, "grad_norm": 0.6599438687201707, "learning_rate": 4.994738450123111e-06, "loss": 0.046, "step": 228 }, { "epoch": 0.10418562329390355, "grad_norm": 0.9666854434475629, "learning_rate": 4.994692007194312e-06, "loss": 0.0743, "step": 229 }, { "epoch": 0.10464058234758872, "grad_norm": 0.7151615241659314, "learning_rate": 4.994645360410547e-06, "loss": 0.0583, "step": 230 }, { "epoch": 0.10509554140127389, "grad_norm": 0.7773674174360427, "learning_rate": 4.99459850977563e-06, "loss": 0.0618, "step": 231 }, { "epoch": 0.10555050045495905, "grad_norm": 0.8418236580272198, "learning_rate": 4.994551455293388e-06, "loss": 0.046, "step": 232 }, { "epoch": 0.10600545950864422, "grad_norm": 0.9714541810445473, "learning_rate": 4.9945041969676654e-06, "loss": 0.0634, "step": 233 }, { "epoch": 0.10646041856232939, "grad_norm": 1.0109494927023708, "learning_rate": 4.994456734802325e-06, "loss": 0.0551, "step": 234 }, { "epoch": 0.10691537761601456, "grad_norm": 0.714933750259254, "learning_rate": 4.994409068801247e-06, "loss": 0.0593, "step": 235 }, { "epoch": 0.10737033666969972, "grad_norm": 1.998280137227604, "learning_rate": 4.994361198968323e-06, "loss": 0.0632, "step": 236 }, { "epoch": 0.1078252957233849, "grad_norm": 1.2708633718893245, "learning_rate": 4.994313125307466e-06, "loss": 0.0909, "step": 237 }, { "epoch": 0.10828025477707007, "grad_norm": 0.7903038049799667, "learning_rate": 4.994264847822605e-06, "loss": 0.0579, "step": 238 }, { "epoch": 0.10873521383075523, "grad_norm": 0.7076795429019287, "learning_rate": 4.994216366517684e-06, "loss": 0.0419, "step": 239 }, { "epoch": 0.1091901728844404, "grad_norm": 0.9078047157633448, "learning_rate": 4.994167681396667e-06, "loss": 0.0631, "step": 240 }, { "epoch": 0.10964513193812557, "grad_norm": 1.122407784822992, "learning_rate": 4.994118792463529e-06, "loss": 0.0771, "step": 241 }, { "epoch": 0.11010009099181074, "grad_norm": 1.3544092697698327, "learning_rate": 4.994069699722267e-06, "loss": 0.1034, "step": 242 }, { "epoch": 0.1105550500454959, "grad_norm": 1.0823051140179736, "learning_rate": 4.994020403176893e-06, "loss": 0.0737, "step": 243 }, { "epoch": 0.11101000909918107, "grad_norm": 1.4097890081473512, "learning_rate": 4.9939709028314345e-06, "loss": 0.0882, "step": 244 }, { "epoch": 0.11146496815286625, "grad_norm": 3.3536954759034883, "learning_rate": 4.993921198689935e-06, "loss": 0.0448, "step": 245 }, { "epoch": 0.11191992720655142, "grad_norm": 0.8141751078988797, "learning_rate": 4.993871290756459e-06, "loss": 0.053, "step": 246 }, { "epoch": 0.11237488626023658, "grad_norm": 0.7556149519633891, "learning_rate": 4.9938211790350835e-06, "loss": 0.053, "step": 247 }, { "epoch": 0.11282984531392175, "grad_norm": 1.028865867099704, "learning_rate": 4.993770863529902e-06, "loss": 0.068, "step": 248 }, { "epoch": 0.11328480436760692, "grad_norm": 0.8709129466992336, "learning_rate": 4.993720344245029e-06, "loss": 0.0533, "step": 249 }, { "epoch": 0.11373976342129208, "grad_norm": 0.8992015471183187, "learning_rate": 4.99366962118459e-06, "loss": 0.0589, "step": 250 }, { "epoch": 0.11419472247497725, "grad_norm": 0.8276539094244998, "learning_rate": 4.99361869435273e-06, "loss": 0.0537, "step": 251 }, { "epoch": 0.11464968152866242, "grad_norm": 1.1164497627583263, "learning_rate": 4.993567563753613e-06, "loss": 0.0627, "step": 252 }, { "epoch": 0.1151046405823476, "grad_norm": 1.049662917063972, "learning_rate": 4.993516229391414e-06, "loss": 0.0708, "step": 253 }, { "epoch": 0.11555959963603275, "grad_norm": 0.8007012653446455, "learning_rate": 4.993464691270331e-06, "loss": 0.036, "step": 254 }, { "epoch": 0.11601455868971793, "grad_norm": 1.0491396902879628, "learning_rate": 4.993412949394572e-06, "loss": 0.0564, "step": 255 }, { "epoch": 0.1164695177434031, "grad_norm": 1.0461746265014504, "learning_rate": 4.993361003768369e-06, "loss": 0.0547, "step": 256 }, { "epoch": 0.11692447679708826, "grad_norm": 0.7167785855145479, "learning_rate": 4.993308854395963e-06, "loss": 0.0543, "step": 257 }, { "epoch": 0.11737943585077343, "grad_norm": 1.7377303264454829, "learning_rate": 4.993256501281618e-06, "loss": 0.0385, "step": 258 }, { "epoch": 0.1178343949044586, "grad_norm": 0.9843734560261626, "learning_rate": 4.993203944429611e-06, "loss": 0.0793, "step": 259 }, { "epoch": 0.11828935395814377, "grad_norm": 0.7687699158665893, "learning_rate": 4.993151183844236e-06, "loss": 0.0554, "step": 260 }, { "epoch": 0.11874431301182893, "grad_norm": 0.8273770606193852, "learning_rate": 4.9930982195298065e-06, "loss": 0.0485, "step": 261 }, { "epoch": 0.1191992720655141, "grad_norm": 0.8576587444889947, "learning_rate": 4.9930450514906484e-06, "loss": 0.0668, "step": 262 }, { "epoch": 0.11965423111919928, "grad_norm": 0.8611188803026584, "learning_rate": 4.9929916797311075e-06, "loss": 0.0511, "step": 263 }, { "epoch": 0.12010919017288443, "grad_norm": 1.5171570240611278, "learning_rate": 4.992938104255545e-06, "loss": 0.105, "step": 264 }, { "epoch": 0.1205641492265696, "grad_norm": 0.9293458324727663, "learning_rate": 4.992884325068339e-06, "loss": 0.0519, "step": 265 }, { "epoch": 0.12101910828025478, "grad_norm": 0.854174247687424, "learning_rate": 4.992830342173882e-06, "loss": 0.0739, "step": 266 }, { "epoch": 0.12147406733393995, "grad_norm": 1.185366954699452, "learning_rate": 4.992776155576589e-06, "loss": 0.088, "step": 267 }, { "epoch": 0.12192902638762511, "grad_norm": 0.8266584460330494, "learning_rate": 4.992721765280884e-06, "loss": 0.0766, "step": 268 }, { "epoch": 0.12238398544131028, "grad_norm": 1.4759867391060453, "learning_rate": 4.992667171291215e-06, "loss": 0.0935, "step": 269 }, { "epoch": 0.12283894449499545, "grad_norm": 0.7694789949011869, "learning_rate": 4.992612373612042e-06, "loss": 0.0444, "step": 270 }, { "epoch": 0.12329390354868063, "grad_norm": 1.3788521475642475, "learning_rate": 4.99255737224784e-06, "loss": 0.0686, "step": 271 }, { "epoch": 0.12374886260236578, "grad_norm": 0.6815172893718315, "learning_rate": 4.9925021672031075e-06, "loss": 0.0597, "step": 272 }, { "epoch": 0.12420382165605096, "grad_norm": 1.0361010622054052, "learning_rate": 4.992446758482353e-06, "loss": 0.0577, "step": 273 }, { "epoch": 0.12465878070973613, "grad_norm": 1.3644605952379871, "learning_rate": 4.992391146090106e-06, "loss": 0.1058, "step": 274 }, { "epoch": 0.1251137397634213, "grad_norm": 0.6194563221594529, "learning_rate": 4.99233533003091e-06, "loss": 0.0481, "step": 275 }, { "epoch": 0.12556869881710647, "grad_norm": 0.8571229878526591, "learning_rate": 4.992279310309326e-06, "loss": 0.0811, "step": 276 }, { "epoch": 0.12602365787079162, "grad_norm": 1.543151015857885, "learning_rate": 4.9922230869299316e-06, "loss": 0.1184, "step": 277 }, { "epoch": 0.1264786169244768, "grad_norm": 0.8807612446920655, "learning_rate": 4.992166659897321e-06, "loss": 0.0629, "step": 278 }, { "epoch": 0.12693357597816196, "grad_norm": 0.754844132552438, "learning_rate": 4.992110029216106e-06, "loss": 0.0488, "step": 279 }, { "epoch": 0.12738853503184713, "grad_norm": 0.8268029175550342, "learning_rate": 4.992053194890914e-06, "loss": 0.0463, "step": 280 }, { "epoch": 0.1278434940855323, "grad_norm": 3.022212928870756, "learning_rate": 4.991996156926388e-06, "loss": 0.0622, "step": 281 }, { "epoch": 0.12829845313921748, "grad_norm": 11.09472751599815, "learning_rate": 4.9919389153271904e-06, "loss": 0.0631, "step": 282 }, { "epoch": 0.12875341219290265, "grad_norm": 5.099079327460766, "learning_rate": 4.991881470097998e-06, "loss": 0.0666, "step": 283 }, { "epoch": 0.1292083712465878, "grad_norm": 27.36348462792037, "learning_rate": 4.991823821243505e-06, "loss": 0.0601, "step": 284 }, { "epoch": 0.12966333030027297, "grad_norm": 4.3922238380370375, "learning_rate": 4.991765968768422e-06, "loss": 0.0801, "step": 285 }, { "epoch": 0.13011828935395814, "grad_norm": 2.2745288954264855, "learning_rate": 4.991707912677477e-06, "loss": 0.0461, "step": 286 }, { "epoch": 0.1305732484076433, "grad_norm": 4.103515429733392, "learning_rate": 4.991649652975414e-06, "loss": 0.0464, "step": 287 }, { "epoch": 0.13102820746132848, "grad_norm": 8.218943562506432, "learning_rate": 4.991591189666994e-06, "loss": 0.048, "step": 288 }, { "epoch": 0.13148316651501366, "grad_norm": 2.4966842175341917, "learning_rate": 4.991532522756993e-06, "loss": 0.0635, "step": 289 }, { "epoch": 0.13193812556869883, "grad_norm": 2.714522360598833, "learning_rate": 4.991473652250207e-06, "loss": 0.0416, "step": 290 }, { "epoch": 0.13239308462238397, "grad_norm": 0.7496525159208725, "learning_rate": 4.991414578151445e-06, "loss": 0.0558, "step": 291 }, { "epoch": 0.13284804367606914, "grad_norm": 1.9010591397052237, "learning_rate": 4.991355300465535e-06, "loss": 0.1319, "step": 292 }, { "epoch": 0.13330300272975432, "grad_norm": 1.0962153747662344, "learning_rate": 4.99129581919732e-06, "loss": 0.0597, "step": 293 }, { "epoch": 0.1337579617834395, "grad_norm": 0.682643165278525, "learning_rate": 4.9912361343516616e-06, "loss": 0.0392, "step": 294 }, { "epoch": 0.13421292083712466, "grad_norm": 0.8036831706718465, "learning_rate": 4.991176245933437e-06, "loss": 0.0572, "step": 295 }, { "epoch": 0.13466787989080983, "grad_norm": 0.799489770852785, "learning_rate": 4.9911161539475385e-06, "loss": 0.0533, "step": 296 }, { "epoch": 0.135122838944495, "grad_norm": 1.5836938564798495, "learning_rate": 4.991055858398879e-06, "loss": 0.0875, "step": 297 }, { "epoch": 0.13557779799818018, "grad_norm": 1.1468269055025655, "learning_rate": 4.990995359292384e-06, "loss": 0.0843, "step": 298 }, { "epoch": 0.13603275705186532, "grad_norm": 1.025610687153708, "learning_rate": 4.990934656632997e-06, "loss": 0.0767, "step": 299 }, { "epoch": 0.1364877161055505, "grad_norm": 1.135419351562697, "learning_rate": 4.990873750425679e-06, "loss": 0.0521, "step": 300 }, { "epoch": 0.13694267515923567, "grad_norm": 0.7857019349684609, "learning_rate": 4.990812640675406e-06, "loss": 0.0577, "step": 301 }, { "epoch": 0.13739763421292084, "grad_norm": 0.6543121694694685, "learning_rate": 4.990751327387174e-06, "loss": 0.0408, "step": 302 }, { "epoch": 0.137852593266606, "grad_norm": 0.9867579368206506, "learning_rate": 4.99068981056599e-06, "loss": 0.0644, "step": 303 }, { "epoch": 0.13830755232029118, "grad_norm": 0.9387206564680207, "learning_rate": 4.990628090216885e-06, "loss": 0.0725, "step": 304 }, { "epoch": 0.13876251137397635, "grad_norm": 0.6895906486970027, "learning_rate": 4.990566166344898e-06, "loss": 0.0444, "step": 305 }, { "epoch": 0.1392174704276615, "grad_norm": 0.8627162803317235, "learning_rate": 4.990504038955092e-06, "loss": 0.0639, "step": 306 }, { "epoch": 0.13967242948134667, "grad_norm": 0.9832854011829437, "learning_rate": 4.990441708052542e-06, "loss": 0.067, "step": 307 }, { "epoch": 0.14012738853503184, "grad_norm": 0.6828895359949346, "learning_rate": 4.9903791736423435e-06, "loss": 0.0511, "step": 308 }, { "epoch": 0.14058234758871702, "grad_norm": 0.949508820368659, "learning_rate": 4.9903164357296044e-06, "loss": 0.0586, "step": 309 }, { "epoch": 0.1410373066424022, "grad_norm": 0.8262401805570133, "learning_rate": 4.990253494319453e-06, "loss": 0.072, "step": 310 }, { "epoch": 0.14149226569608736, "grad_norm": 0.7329455864605506, "learning_rate": 4.990190349417032e-06, "loss": 0.0659, "step": 311 }, { "epoch": 0.14194722474977253, "grad_norm": 1.008005243411958, "learning_rate": 4.990127001027501e-06, "loss": 0.0682, "step": 312 }, { "epoch": 0.14240218380345768, "grad_norm": 1.3159038760119786, "learning_rate": 4.990063449156037e-06, "loss": 0.0485, "step": 313 }, { "epoch": 0.14285714285714285, "grad_norm": 1.053132819530921, "learning_rate": 4.989999693807832e-06, "loss": 0.0736, "step": 314 }, { "epoch": 0.14331210191082802, "grad_norm": 1.2097384821970267, "learning_rate": 4.989935734988098e-06, "loss": 0.0752, "step": 315 }, { "epoch": 0.1437670609645132, "grad_norm": 0.8883071525106219, "learning_rate": 4.98987157270206e-06, "loss": 0.0614, "step": 316 }, { "epoch": 0.14422202001819837, "grad_norm": 1.3457063090752772, "learning_rate": 4.989807206954961e-06, "loss": 0.0896, "step": 317 }, { "epoch": 0.14467697907188354, "grad_norm": 0.6077627024555071, "learning_rate": 4.9897426377520605e-06, "loss": 0.0426, "step": 318 }, { "epoch": 0.1451319381255687, "grad_norm": 1.4177858466419022, "learning_rate": 4.989677865098636e-06, "loss": 0.0922, "step": 319 }, { "epoch": 0.14558689717925385, "grad_norm": 0.5838535924114719, "learning_rate": 4.989612888999978e-06, "loss": 0.04, "step": 320 }, { "epoch": 0.14604185623293903, "grad_norm": 0.7991836602542821, "learning_rate": 4.9895477094614e-06, "loss": 0.0644, "step": 321 }, { "epoch": 0.1464968152866242, "grad_norm": 0.6309987592236359, "learning_rate": 4.989482326488225e-06, "loss": 0.0457, "step": 322 }, { "epoch": 0.14695177434030937, "grad_norm": 0.850157804894001, "learning_rate": 4.989416740085796e-06, "loss": 0.0706, "step": 323 }, { "epoch": 0.14740673339399454, "grad_norm": 0.8703332109039406, "learning_rate": 4.9893509502594735e-06, "loss": 0.0503, "step": 324 }, { "epoch": 0.14786169244767972, "grad_norm": 0.9357603198363387, "learning_rate": 4.9892849570146335e-06, "loss": 0.0799, "step": 325 }, { "epoch": 0.1483166515013649, "grad_norm": 0.9508555727006773, "learning_rate": 4.989218760356668e-06, "loss": 0.0703, "step": 326 }, { "epoch": 0.14877161055505003, "grad_norm": 0.8548982254979315, "learning_rate": 4.989152360290987e-06, "loss": 0.0706, "step": 327 }, { "epoch": 0.1492265696087352, "grad_norm": 1.1548758627037845, "learning_rate": 4.989085756823015e-06, "loss": 0.0868, "step": 328 }, { "epoch": 0.14968152866242038, "grad_norm": 0.872011841531817, "learning_rate": 4.989018949958197e-06, "loss": 0.0642, "step": 329 }, { "epoch": 0.15013648771610555, "grad_norm": 0.7767447334589991, "learning_rate": 4.98895193970199e-06, "loss": 0.0428, "step": 330 }, { "epoch": 0.15059144676979072, "grad_norm": 0.9215786343037755, "learning_rate": 4.9888847260598705e-06, "loss": 0.0652, "step": 331 }, { "epoch": 0.1510464058234759, "grad_norm": 1.0293746869379716, "learning_rate": 4.98881730903733e-06, "loss": 0.0768, "step": 332 }, { "epoch": 0.15150136487716107, "grad_norm": 1.2190824076232663, "learning_rate": 4.98874968863988e-06, "loss": 0.0746, "step": 333 }, { "epoch": 0.15195632393084624, "grad_norm": 0.8899729802614444, "learning_rate": 4.988681864873044e-06, "loss": 0.0638, "step": 334 }, { "epoch": 0.15241128298453138, "grad_norm": 0.8009499929718743, "learning_rate": 4.988613837742364e-06, "loss": 0.0556, "step": 335 }, { "epoch": 0.15286624203821655, "grad_norm": 1.0942561304100769, "learning_rate": 4.9885456072534015e-06, "loss": 0.0685, "step": 336 }, { "epoch": 0.15332120109190173, "grad_norm": 1.1210686024600067, "learning_rate": 4.988477173411728e-06, "loss": 0.0649, "step": 337 }, { "epoch": 0.1537761601455869, "grad_norm": 0.713128381997935, "learning_rate": 4.988408536222939e-06, "loss": 0.043, "step": 338 }, { "epoch": 0.15423111919927207, "grad_norm": 0.8820810335281195, "learning_rate": 4.9883396956926416e-06, "loss": 0.0545, "step": 339 }, { "epoch": 0.15468607825295724, "grad_norm": 0.7198251112806523, "learning_rate": 4.988270651826462e-06, "loss": 0.0419, "step": 340 }, { "epoch": 0.15514103730664242, "grad_norm": 0.9319745452557298, "learning_rate": 4.988201404630041e-06, "loss": 0.0556, "step": 341 }, { "epoch": 0.15559599636032756, "grad_norm": 0.7744733545189804, "learning_rate": 4.988131954109038e-06, "loss": 0.0566, "step": 342 }, { "epoch": 0.15605095541401273, "grad_norm": 1.2609547822192495, "learning_rate": 4.988062300269128e-06, "loss": 0.0931, "step": 343 }, { "epoch": 0.1565059144676979, "grad_norm": 1.0356035457639365, "learning_rate": 4.987992443116003e-06, "loss": 0.0592, "step": 344 }, { "epoch": 0.15696087352138308, "grad_norm": 0.8613107982126194, "learning_rate": 4.987922382655372e-06, "loss": 0.0599, "step": 345 }, { "epoch": 0.15741583257506825, "grad_norm": 1.2274429381178749, "learning_rate": 4.987852118892958e-06, "loss": 0.104, "step": 346 }, { "epoch": 0.15787079162875342, "grad_norm": 0.8982827327342306, "learning_rate": 4.987781651834503e-06, "loss": 0.0777, "step": 347 }, { "epoch": 0.1583257506824386, "grad_norm": 1.124267218302162, "learning_rate": 4.987710981485768e-06, "loss": 0.0815, "step": 348 }, { "epoch": 0.15878070973612374, "grad_norm": 1.1417083606361687, "learning_rate": 4.987640107852525e-06, "loss": 0.0968, "step": 349 }, { "epoch": 0.1592356687898089, "grad_norm": 0.7137928465125194, "learning_rate": 4.987569030940567e-06, "loss": 0.0525, "step": 350 }, { "epoch": 0.15969062784349408, "grad_norm": 0.8074447940975472, "learning_rate": 4.987497750755702e-06, "loss": 0.0478, "step": 351 }, { "epoch": 0.16014558689717925, "grad_norm": 1.320795972993318, "learning_rate": 4.987426267303753e-06, "loss": 0.0814, "step": 352 }, { "epoch": 0.16060054595086443, "grad_norm": 0.956458465296858, "learning_rate": 4.987354580590563e-06, "loss": 0.0728, "step": 353 }, { "epoch": 0.1610555050045496, "grad_norm": 0.9487388071568301, "learning_rate": 4.987282690621991e-06, "loss": 0.0778, "step": 354 }, { "epoch": 0.16151046405823477, "grad_norm": 0.8111568286998416, "learning_rate": 4.987210597403907e-06, "loss": 0.0634, "step": 355 }, { "epoch": 0.16196542311191992, "grad_norm": 0.9291291865293426, "learning_rate": 4.987138300942208e-06, "loss": 0.057, "step": 356 }, { "epoch": 0.1624203821656051, "grad_norm": 0.7796831533037398, "learning_rate": 4.987065801242798e-06, "loss": 0.0591, "step": 357 }, { "epoch": 0.16287534121929026, "grad_norm": 1.0091637666603208, "learning_rate": 4.986993098311601e-06, "loss": 0.0712, "step": 358 }, { "epoch": 0.16333030027297543, "grad_norm": 0.9599752405823201, "learning_rate": 4.986920192154561e-06, "loss": 0.0712, "step": 359 }, { "epoch": 0.1637852593266606, "grad_norm": 0.6975593533750986, "learning_rate": 4.986847082777632e-06, "loss": 0.0489, "step": 360 }, { "epoch": 0.16424021838034578, "grad_norm": 0.8407792898194115, "learning_rate": 4.986773770186791e-06, "loss": 0.0687, "step": 361 }, { "epoch": 0.16469517743403095, "grad_norm": 1.16032280422667, "learning_rate": 4.986700254388027e-06, "loss": 0.0814, "step": 362 }, { "epoch": 0.1651501364877161, "grad_norm": 0.6789989236352713, "learning_rate": 4.986626535387349e-06, "loss": 0.0502, "step": 363 }, { "epoch": 0.16560509554140126, "grad_norm": 0.8858819178004838, "learning_rate": 4.9865526131907795e-06, "loss": 0.0584, "step": 364 }, { "epoch": 0.16606005459508644, "grad_norm": 1.0159257224317502, "learning_rate": 4.9864784878043595e-06, "loss": 0.0828, "step": 365 }, { "epoch": 0.1665150136487716, "grad_norm": 1.1632391007958518, "learning_rate": 4.986404159234146e-06, "loss": 0.0693, "step": 366 }, { "epoch": 0.16696997270245678, "grad_norm": 0.7286212082146628, "learning_rate": 4.986329627486213e-06, "loss": 0.048, "step": 367 }, { "epoch": 0.16742493175614195, "grad_norm": 1.1675091585135315, "learning_rate": 4.986254892566652e-06, "loss": 0.0831, "step": 368 }, { "epoch": 0.16787989080982713, "grad_norm": 0.7791126867293955, "learning_rate": 4.9861799544815684e-06, "loss": 0.0511, "step": 369 }, { "epoch": 0.16833484986351227, "grad_norm": 0.8594476885535768, "learning_rate": 4.986104813237086e-06, "loss": 0.0605, "step": 370 }, { "epoch": 0.16878980891719744, "grad_norm": 0.8510456749795352, "learning_rate": 4.986029468839346e-06, "loss": 0.0568, "step": 371 }, { "epoch": 0.16924476797088261, "grad_norm": 1.1617139473891909, "learning_rate": 4.985953921294505e-06, "loss": 0.09, "step": 372 }, { "epoch": 0.1696997270245678, "grad_norm": 0.6957569576277562, "learning_rate": 4.985878170608736e-06, "loss": 0.038, "step": 373 }, { "epoch": 0.17015468607825296, "grad_norm": 0.8584263131532073, "learning_rate": 4.985802216788228e-06, "loss": 0.0517, "step": 374 }, { "epoch": 0.17060964513193813, "grad_norm": 0.9366771679720911, "learning_rate": 4.98572605983919e-06, "loss": 0.063, "step": 375 }, { "epoch": 0.1710646041856233, "grad_norm": 0.5935251092125957, "learning_rate": 4.985649699767842e-06, "loss": 0.0399, "step": 376 }, { "epoch": 0.17151956323930848, "grad_norm": 0.7556873935071919, "learning_rate": 4.985573136580427e-06, "loss": 0.0606, "step": 377 }, { "epoch": 0.17197452229299362, "grad_norm": 0.723085424895094, "learning_rate": 4.9854963702832e-06, "loss": 0.0498, "step": 378 }, { "epoch": 0.1724294813466788, "grad_norm": 0.9057911616547558, "learning_rate": 4.985419400882433e-06, "loss": 0.0733, "step": 379 }, { "epoch": 0.17288444040036396, "grad_norm": 1.0911724774245748, "learning_rate": 4.985342228384418e-06, "loss": 0.0974, "step": 380 }, { "epoch": 0.17333939945404914, "grad_norm": 15.867955316807802, "learning_rate": 4.985264852795459e-06, "loss": 0.4597, "step": 381 }, { "epoch": 0.1737943585077343, "grad_norm": 0.8242169703714594, "learning_rate": 4.98518727412188e-06, "loss": 0.0592, "step": 382 }, { "epoch": 0.17424931756141948, "grad_norm": 1.189476180626615, "learning_rate": 4.98510949237002e-06, "loss": 0.0871, "step": 383 }, { "epoch": 0.17470427661510465, "grad_norm": 0.9035387689173863, "learning_rate": 4.985031507546234e-06, "loss": 0.0659, "step": 384 }, { "epoch": 0.1751592356687898, "grad_norm": 1.5548450607275692, "learning_rate": 4.984953319656896e-06, "loss": 0.102, "step": 385 }, { "epoch": 0.17561419472247497, "grad_norm": 0.9148861743530409, "learning_rate": 4.984874928708395e-06, "loss": 0.0621, "step": 386 }, { "epoch": 0.17606915377616014, "grad_norm": 1.0088623446062757, "learning_rate": 4.984796334707136e-06, "loss": 0.0801, "step": 387 }, { "epoch": 0.17652411282984531, "grad_norm": 7.099087459170151, "learning_rate": 4.984717537659542e-06, "loss": 0.1139, "step": 388 }, { "epoch": 0.1769790718835305, "grad_norm": 0.6271204554143699, "learning_rate": 4.984638537572052e-06, "loss": 0.0362, "step": 389 }, { "epoch": 0.17743403093721566, "grad_norm": 0.9099126199173307, "learning_rate": 4.984559334451121e-06, "loss": 0.0589, "step": 390 }, { "epoch": 0.17788898999090083, "grad_norm": 0.9635928903258919, "learning_rate": 4.984479928303221e-06, "loss": 0.0485, "step": 391 }, { "epoch": 0.17834394904458598, "grad_norm": 0.8684293064054923, "learning_rate": 4.984400319134841e-06, "loss": 0.0488, "step": 392 }, { "epoch": 0.17879890809827115, "grad_norm": 1.490825595774446, "learning_rate": 4.984320506952487e-06, "loss": 0.1164, "step": 393 }, { "epoch": 0.17925386715195632, "grad_norm": 1.0210666975638372, "learning_rate": 4.9842404917626796e-06, "loss": 0.0765, "step": 394 }, { "epoch": 0.1797088262056415, "grad_norm": 0.7827897024774737, "learning_rate": 4.984160273571959e-06, "loss": 0.0627, "step": 395 }, { "epoch": 0.18016378525932666, "grad_norm": 0.9460976796008799, "learning_rate": 4.9840798523868785e-06, "loss": 0.0802, "step": 396 }, { "epoch": 0.18061874431301184, "grad_norm": 0.6974747481172566, "learning_rate": 4.983999228214011e-06, "loss": 0.0483, "step": 397 }, { "epoch": 0.181073703366697, "grad_norm": 0.7442577439773002, "learning_rate": 4.983918401059943e-06, "loss": 0.0501, "step": 398 }, { "epoch": 0.18152866242038215, "grad_norm": 1.001863981150214, "learning_rate": 4.983837370931282e-06, "loss": 0.0866, "step": 399 }, { "epoch": 0.18198362147406733, "grad_norm": 1.258993794296855, "learning_rate": 4.983756137834647e-06, "loss": 0.1164, "step": 400 }, { "epoch": 0.1824385805277525, "grad_norm": 1.1296307149258726, "learning_rate": 4.9836747017766765e-06, "loss": 0.0698, "step": 401 }, { "epoch": 0.18289353958143767, "grad_norm": 0.9299919208142283, "learning_rate": 4.983593062764027e-06, "loss": 0.0767, "step": 402 }, { "epoch": 0.18334849863512284, "grad_norm": 1.6483380962062835, "learning_rate": 4.983511220803367e-06, "loss": 0.0982, "step": 403 }, { "epoch": 0.18380345768880801, "grad_norm": 0.7951232146562915, "learning_rate": 4.983429175901386e-06, "loss": 0.0621, "step": 404 }, { "epoch": 0.1842584167424932, "grad_norm": 0.7346583458526271, "learning_rate": 4.983346928064788e-06, "loss": 0.0485, "step": 405 }, { "epoch": 0.18471337579617833, "grad_norm": 0.8488964995265393, "learning_rate": 4.9832644773002935e-06, "loss": 0.0697, "step": 406 }, { "epoch": 0.1851683348498635, "grad_norm": 0.637978257841365, "learning_rate": 4.98318182361464e-06, "loss": 0.0578, "step": 407 }, { "epoch": 0.18562329390354868, "grad_norm": 1.006460769017827, "learning_rate": 4.9830989670145825e-06, "loss": 0.0741, "step": 408 }, { "epoch": 0.18607825295723385, "grad_norm": 1.0063850758607982, "learning_rate": 4.9830159075068905e-06, "loss": 0.0698, "step": 409 }, { "epoch": 0.18653321201091902, "grad_norm": 0.9365632618002147, "learning_rate": 4.9829326450983514e-06, "loss": 0.0779, "step": 410 }, { "epoch": 0.1869881710646042, "grad_norm": 0.8773564274313461, "learning_rate": 4.98284917979577e-06, "loss": 0.0608, "step": 411 }, { "epoch": 0.18744313011828936, "grad_norm": 0.9057984183185465, "learning_rate": 4.9827655116059656e-06, "loss": 0.0639, "step": 412 }, { "epoch": 0.18789808917197454, "grad_norm": 0.8657789325497686, "learning_rate": 4.9826816405357755e-06, "loss": 0.0749, "step": 413 }, { "epoch": 0.18835304822565968, "grad_norm": 0.5817294435867961, "learning_rate": 4.982597566592054e-06, "loss": 0.0353, "step": 414 }, { "epoch": 0.18880800727934485, "grad_norm": 1.2277963790590036, "learning_rate": 4.982513289781671e-06, "loss": 0.091, "step": 415 }, { "epoch": 0.18926296633303002, "grad_norm": 0.7616764372047586, "learning_rate": 4.982428810111512e-06, "loss": 0.0597, "step": 416 }, { "epoch": 0.1897179253867152, "grad_norm": 0.710019161677026, "learning_rate": 4.9823441275884814e-06, "loss": 0.0535, "step": 417 }, { "epoch": 0.19017288444040037, "grad_norm": 1.1202371935797844, "learning_rate": 4.982259242219499e-06, "loss": 0.0643, "step": 418 }, { "epoch": 0.19062784349408554, "grad_norm": 0.6803190221634923, "learning_rate": 4.9821741540115006e-06, "loss": 0.0483, "step": 419 }, { "epoch": 0.1910828025477707, "grad_norm": 0.8014131027464055, "learning_rate": 4.982088862971441e-06, "loss": 0.0703, "step": 420 }, { "epoch": 0.19153776160145586, "grad_norm": 0.960552266983122, "learning_rate": 4.982003369106287e-06, "loss": 0.0709, "step": 421 }, { "epoch": 0.19199272065514103, "grad_norm": 0.6179685927519944, "learning_rate": 4.981917672423028e-06, "loss": 0.0407, "step": 422 }, { "epoch": 0.1924476797088262, "grad_norm": 0.9538296833436659, "learning_rate": 4.981831772928664e-06, "loss": 0.0681, "step": 423 }, { "epoch": 0.19290263876251137, "grad_norm": 1.076872796407403, "learning_rate": 4.981745670630216e-06, "loss": 0.0918, "step": 424 }, { "epoch": 0.19335759781619655, "grad_norm": 0.8486267027177018, "learning_rate": 4.981659365534718e-06, "loss": 0.081, "step": 425 }, { "epoch": 0.19381255686988172, "grad_norm": 1.2668354345440433, "learning_rate": 4.981572857649225e-06, "loss": 0.0855, "step": 426 }, { "epoch": 0.1942675159235669, "grad_norm": 0.785685618330662, "learning_rate": 4.981486146980804e-06, "loss": 0.0525, "step": 427 }, { "epoch": 0.19472247497725204, "grad_norm": 0.9012661112199176, "learning_rate": 4.9813992335365415e-06, "loss": 0.0616, "step": 428 }, { "epoch": 0.1951774340309372, "grad_norm": 0.9140326707870835, "learning_rate": 4.98131211732354e-06, "loss": 0.0742, "step": 429 }, { "epoch": 0.19563239308462238, "grad_norm": 0.8802115121731895, "learning_rate": 4.981224798348917e-06, "loss": 0.0543, "step": 430 }, { "epoch": 0.19608735213830755, "grad_norm": 1.2263655680320666, "learning_rate": 4.981137276619809e-06, "loss": 0.1, "step": 431 }, { "epoch": 0.19654231119199272, "grad_norm": 0.7179258520773776, "learning_rate": 4.9810495521433675e-06, "loss": 0.0563, "step": 432 }, { "epoch": 0.1969972702456779, "grad_norm": 1.2006165727982114, "learning_rate": 4.9809616249267616e-06, "loss": 0.0919, "step": 433 }, { "epoch": 0.19745222929936307, "grad_norm": 1.0426641838922892, "learning_rate": 4.980873494977174e-06, "loss": 0.0845, "step": 434 }, { "epoch": 0.1979071883530482, "grad_norm": 0.8009974020959663, "learning_rate": 4.98078516230181e-06, "loss": 0.0495, "step": 435 }, { "epoch": 0.19836214740673339, "grad_norm": 0.8146116166212912, "learning_rate": 4.980696626907884e-06, "loss": 0.0656, "step": 436 }, { "epoch": 0.19881710646041856, "grad_norm": 0.8146964454257942, "learning_rate": 4.980607888802633e-06, "loss": 0.0717, "step": 437 }, { "epoch": 0.19927206551410373, "grad_norm": 0.8473418815819729, "learning_rate": 4.980518947993307e-06, "loss": 0.0701, "step": 438 }, { "epoch": 0.1997270245677889, "grad_norm": 0.8132123262524923, "learning_rate": 4.980429804487176e-06, "loss": 0.0657, "step": 439 }, { "epoch": 0.20018198362147407, "grad_norm": 0.7631308196097977, "learning_rate": 4.980340458291521e-06, "loss": 0.0519, "step": 440 }, { "epoch": 0.20063694267515925, "grad_norm": 0.7710009886187632, "learning_rate": 4.980250909413646e-06, "loss": 0.0668, "step": 441 }, { "epoch": 0.2010919017288444, "grad_norm": 0.8960590823111618, "learning_rate": 4.980161157860867e-06, "loss": 0.066, "step": 442 }, { "epoch": 0.20154686078252956, "grad_norm": 1.0148659081855533, "learning_rate": 4.980071203640519e-06, "loss": 0.0666, "step": 443 }, { "epoch": 0.20200181983621474, "grad_norm": 0.6157365971883945, "learning_rate": 4.979981046759952e-06, "loss": 0.0441, "step": 444 }, { "epoch": 0.2024567788898999, "grad_norm": 0.8862364575439057, "learning_rate": 4.979890687226533e-06, "loss": 0.0638, "step": 445 }, { "epoch": 0.20291173794358508, "grad_norm": 1.051789940808801, "learning_rate": 4.979800125047647e-06, "loss": 0.0571, "step": 446 }, { "epoch": 0.20336669699727025, "grad_norm": 0.8963335794848035, "learning_rate": 4.979709360230692e-06, "loss": 0.0706, "step": 447 }, { "epoch": 0.20382165605095542, "grad_norm": 0.8639092050645877, "learning_rate": 4.979618392783087e-06, "loss": 0.0535, "step": 448 }, { "epoch": 0.20427661510464057, "grad_norm": 0.630704913013139, "learning_rate": 4.979527222712266e-06, "loss": 0.0553, "step": 449 }, { "epoch": 0.20473157415832574, "grad_norm": 0.6653631844503811, "learning_rate": 4.9794358500256765e-06, "loss": 0.0438, "step": 450 }, { "epoch": 0.2051865332120109, "grad_norm": 0.8074584078493093, "learning_rate": 4.979344274730786e-06, "loss": 0.0607, "step": 451 }, { "epoch": 0.20564149226569609, "grad_norm": 1.1020725070982913, "learning_rate": 4.979252496835079e-06, "loss": 0.0812, "step": 452 }, { "epoch": 0.20609645131938126, "grad_norm": 1.2231182771798559, "learning_rate": 4.979160516346054e-06, "loss": 0.1074, "step": 453 }, { "epoch": 0.20655141037306643, "grad_norm": 26.716723850026153, "learning_rate": 4.979068333271227e-06, "loss": 0.8002, "step": 454 }, { "epoch": 0.2070063694267516, "grad_norm": 1.2123236026672213, "learning_rate": 4.978975947618131e-06, "loss": 0.0788, "step": 455 }, { "epoch": 0.20746132848043677, "grad_norm": 0.8671125203100531, "learning_rate": 4.978883359394316e-06, "loss": 0.0902, "step": 456 }, { "epoch": 0.20791628753412192, "grad_norm": 0.9848601155594614, "learning_rate": 4.978790568607347e-06, "loss": 0.0606, "step": 457 }, { "epoch": 0.2083712465878071, "grad_norm": 1.013839640652733, "learning_rate": 4.9786975752648076e-06, "loss": 0.0873, "step": 458 }, { "epoch": 0.20882620564149226, "grad_norm": 0.7483252407807567, "learning_rate": 4.978604379374295e-06, "loss": 0.0592, "step": 459 }, { "epoch": 0.20928116469517744, "grad_norm": 0.7178737508101655, "learning_rate": 4.978510980943427e-06, "loss": 0.0506, "step": 460 }, { "epoch": 0.2097361237488626, "grad_norm": 1.0919247632044238, "learning_rate": 4.978417379979834e-06, "loss": 0.0778, "step": 461 }, { "epoch": 0.21019108280254778, "grad_norm": 0.8331653357443332, "learning_rate": 4.978323576491165e-06, "loss": 0.0577, "step": 462 }, { "epoch": 0.21064604185623295, "grad_norm": 0.8152928496306786, "learning_rate": 4.978229570485085e-06, "loss": 0.072, "step": 463 }, { "epoch": 0.2111010009099181, "grad_norm": 0.751813285906743, "learning_rate": 4.978135361969276e-06, "loss": 0.0649, "step": 464 }, { "epoch": 0.21155595996360327, "grad_norm": 0.8232278152234197, "learning_rate": 4.9780409509514375e-06, "loss": 0.0642, "step": 465 }, { "epoch": 0.21201091901728844, "grad_norm": 1.5303665195432214, "learning_rate": 4.977946337439282e-06, "loss": 0.1217, "step": 466 }, { "epoch": 0.2124658780709736, "grad_norm": 0.9269370490140525, "learning_rate": 4.9778515214405436e-06, "loss": 0.081, "step": 467 }, { "epoch": 0.21292083712465878, "grad_norm": 0.8830556120481512, "learning_rate": 4.977756502962967e-06, "loss": 0.0684, "step": 468 }, { "epoch": 0.21337579617834396, "grad_norm": 0.6113061227600053, "learning_rate": 4.97766128201432e-06, "loss": 0.0446, "step": 469 }, { "epoch": 0.21383075523202913, "grad_norm": 0.6077789311617329, "learning_rate": 4.977565858602381e-06, "loss": 0.0554, "step": 470 }, { "epoch": 0.21428571428571427, "grad_norm": 0.8598515142264441, "learning_rate": 4.977470232734949e-06, "loss": 0.0727, "step": 471 }, { "epoch": 0.21474067333939945, "grad_norm": 0.8043286169945988, "learning_rate": 4.977374404419838e-06, "loss": 0.0592, "step": 472 }, { "epoch": 0.21519563239308462, "grad_norm": 0.7551382062036437, "learning_rate": 4.977278373664877e-06, "loss": 0.0571, "step": 473 }, { "epoch": 0.2156505914467698, "grad_norm": 1.8211283606473743, "learning_rate": 4.977182140477916e-06, "loss": 0.1033, "step": 474 }, { "epoch": 0.21610555050045496, "grad_norm": 0.7146087276289771, "learning_rate": 4.977085704866817e-06, "loss": 0.0462, "step": 475 }, { "epoch": 0.21656050955414013, "grad_norm": 0.6542895317184714, "learning_rate": 4.97698906683946e-06, "loss": 0.061, "step": 476 }, { "epoch": 0.2170154686078253, "grad_norm": 1.0732518420250663, "learning_rate": 4.9768922264037435e-06, "loss": 0.0845, "step": 477 }, { "epoch": 0.21747042766151045, "grad_norm": 0.6769767303273837, "learning_rate": 4.976795183567579e-06, "loss": 0.0484, "step": 478 }, { "epoch": 0.21792538671519562, "grad_norm": 0.6792925907901064, "learning_rate": 4.976697938338898e-06, "loss": 0.0479, "step": 479 }, { "epoch": 0.2183803457688808, "grad_norm": 0.550587338837319, "learning_rate": 4.976600490725645e-06, "loss": 0.0402, "step": 480 }, { "epoch": 0.21883530482256597, "grad_norm": 0.9934557115485821, "learning_rate": 4.976502840735785e-06, "loss": 0.1096, "step": 481 }, { "epoch": 0.21929026387625114, "grad_norm": 0.7026152824587227, "learning_rate": 4.976404988377297e-06, "loss": 0.0442, "step": 482 }, { "epoch": 0.2197452229299363, "grad_norm": 1.1796498075270252, "learning_rate": 4.976306933658176e-06, "loss": 0.0896, "step": 483 }, { "epoch": 0.22020018198362148, "grad_norm": 0.9196991108702705, "learning_rate": 4.976208676586435e-06, "loss": 0.0903, "step": 484 }, { "epoch": 0.22065514103730663, "grad_norm": 0.9221909008992407, "learning_rate": 4.976110217170104e-06, "loss": 0.061, "step": 485 }, { "epoch": 0.2211101000909918, "grad_norm": 0.8446946807888076, "learning_rate": 4.976011555417228e-06, "loss": 0.06, "step": 486 }, { "epoch": 0.22156505914467697, "grad_norm": 0.8008200895651435, "learning_rate": 4.975912691335869e-06, "loss": 0.0552, "step": 487 }, { "epoch": 0.22202001819836215, "grad_norm": 0.7897004108366357, "learning_rate": 4.975813624934106e-06, "loss": 0.0524, "step": 488 }, { "epoch": 0.22247497725204732, "grad_norm": 0.7656059256782066, "learning_rate": 4.975714356220035e-06, "loss": 0.0532, "step": 489 }, { "epoch": 0.2229299363057325, "grad_norm": 0.49990009073007735, "learning_rate": 4.975614885201766e-06, "loss": 0.0335, "step": 490 }, { "epoch": 0.22338489535941766, "grad_norm": 0.7764965839211172, "learning_rate": 4.975515211887429e-06, "loss": 0.0663, "step": 491 }, { "epoch": 0.22383985441310283, "grad_norm": 0.8335023150964008, "learning_rate": 4.9754153362851684e-06, "loss": 0.0635, "step": 492 }, { "epoch": 0.22429481346678798, "grad_norm": 1.362631121260362, "learning_rate": 4.975315258403145e-06, "loss": 0.1184, "step": 493 }, { "epoch": 0.22474977252047315, "grad_norm": 0.8072718888075444, "learning_rate": 4.975214978249537e-06, "loss": 0.0575, "step": 494 }, { "epoch": 0.22520473157415832, "grad_norm": 0.7237599062848806, "learning_rate": 4.975114495832539e-06, "loss": 0.0629, "step": 495 }, { "epoch": 0.2256596906278435, "grad_norm": 0.9013757169049615, "learning_rate": 4.975013811160362e-06, "loss": 0.0641, "step": 496 }, { "epoch": 0.22611464968152867, "grad_norm": 1.046688141426079, "learning_rate": 4.974912924241233e-06, "loss": 0.0679, "step": 497 }, { "epoch": 0.22656960873521384, "grad_norm": 0.7549334371309422, "learning_rate": 4.974811835083397e-06, "loss": 0.0619, "step": 498 }, { "epoch": 0.227024567788899, "grad_norm": 1.4092663615099252, "learning_rate": 4.974710543695114e-06, "loss": 0.0907, "step": 499 }, { "epoch": 0.22747952684258416, "grad_norm": 1.2767203765961839, "learning_rate": 4.974609050084661e-06, "loss": 0.1037, "step": 500 }, { "epoch": 0.22793448589626933, "grad_norm": 0.957265553607594, "learning_rate": 4.974507354260332e-06, "loss": 0.0841, "step": 501 }, { "epoch": 0.2283894449499545, "grad_norm": 1.0285318937850472, "learning_rate": 4.974405456230436e-06, "loss": 0.0876, "step": 502 }, { "epoch": 0.22884440400363967, "grad_norm": 0.9438000836090487, "learning_rate": 4.974303356003301e-06, "loss": 0.0618, "step": 503 }, { "epoch": 0.22929936305732485, "grad_norm": 0.7641433481492992, "learning_rate": 4.974201053587268e-06, "loss": 0.0623, "step": 504 }, { "epoch": 0.22975432211101002, "grad_norm": 0.7211862506979909, "learning_rate": 4.9740985489907005e-06, "loss": 0.0458, "step": 505 }, { "epoch": 0.2302092811646952, "grad_norm": 1.3113691041435898, "learning_rate": 4.973995842221971e-06, "loss": 0.0865, "step": 506 }, { "epoch": 0.23066424021838033, "grad_norm": 1.1027187330835053, "learning_rate": 4.973892933289476e-06, "loss": 0.0817, "step": 507 }, { "epoch": 0.2311191992720655, "grad_norm": 0.8000847819873458, "learning_rate": 4.97378982220162e-06, "loss": 0.0639, "step": 508 }, { "epoch": 0.23157415832575068, "grad_norm": 0.5709614643890362, "learning_rate": 4.973686508966832e-06, "loss": 0.0427, "step": 509 }, { "epoch": 0.23202911737943585, "grad_norm": 0.6348346044427912, "learning_rate": 4.973582993593554e-06, "loss": 0.0453, "step": 510 }, { "epoch": 0.23248407643312102, "grad_norm": 0.7080077445614887, "learning_rate": 4.973479276090244e-06, "loss": 0.0567, "step": 511 }, { "epoch": 0.2329390354868062, "grad_norm": 0.586722983901754, "learning_rate": 4.973375356465378e-06, "loss": 0.0398, "step": 512 }, { "epoch": 0.23339399454049137, "grad_norm": 0.9373759345632122, "learning_rate": 4.973271234727447e-06, "loss": 0.083, "step": 513 }, { "epoch": 0.2338489535941765, "grad_norm": 0.7290102387520916, "learning_rate": 4.97316691088496e-06, "loss": 0.0573, "step": 514 }, { "epoch": 0.23430391264786168, "grad_norm": 1.2047650698868653, "learning_rate": 4.973062384946442e-06, "loss": 0.0979, "step": 515 }, { "epoch": 0.23475887170154686, "grad_norm": 0.5553854533375087, "learning_rate": 4.9729576569204345e-06, "loss": 0.0493, "step": 516 }, { "epoch": 0.23521383075523203, "grad_norm": 0.966683679171784, "learning_rate": 4.972852726815495e-06, "loss": 0.0744, "step": 517 }, { "epoch": 0.2356687898089172, "grad_norm": 0.8972567842292303, "learning_rate": 4.972747594640197e-06, "loss": 0.0822, "step": 518 }, { "epoch": 0.23612374886260237, "grad_norm": 0.9532248896529997, "learning_rate": 4.9726422604031335e-06, "loss": 0.0628, "step": 519 }, { "epoch": 0.23657870791628755, "grad_norm": 0.5831731409388041, "learning_rate": 4.97253672411291e-06, "loss": 0.0499, "step": 520 }, { "epoch": 0.2370336669699727, "grad_norm": 0.7629148584956371, "learning_rate": 4.972430985778152e-06, "loss": 0.0502, "step": 521 }, { "epoch": 0.23748862602365786, "grad_norm": 0.8867114815888714, "learning_rate": 4.972325045407499e-06, "loss": 0.0551, "step": 522 }, { "epoch": 0.23794358507734303, "grad_norm": 1.2463480840549028, "learning_rate": 4.972218903009608e-06, "loss": 0.0715, "step": 523 }, { "epoch": 0.2383985441310282, "grad_norm": 0.782156462915191, "learning_rate": 4.972112558593153e-06, "loss": 0.0658, "step": 524 }, { "epoch": 0.23885350318471338, "grad_norm": 0.5674610459457798, "learning_rate": 4.972006012166823e-06, "loss": 0.0443, "step": 525 }, { "epoch": 0.23930846223839855, "grad_norm": 0.6676557313621811, "learning_rate": 4.971899263739326e-06, "loss": 0.052, "step": 526 }, { "epoch": 0.23976342129208372, "grad_norm": 0.8996461781463584, "learning_rate": 4.971792313319384e-06, "loss": 0.0761, "step": 527 }, { "epoch": 0.24021838034576887, "grad_norm": 0.7869388715576839, "learning_rate": 4.971685160915737e-06, "loss": 0.059, "step": 528 }, { "epoch": 0.24067333939945404, "grad_norm": 0.8601250360554993, "learning_rate": 4.971577806537139e-06, "loss": 0.058, "step": 529 }, { "epoch": 0.2411282984531392, "grad_norm": 0.860384363291072, "learning_rate": 4.971470250192366e-06, "loss": 0.0746, "step": 530 }, { "epoch": 0.24158325750682438, "grad_norm": 17.481585256275345, "learning_rate": 4.9713624918902045e-06, "loss": 0.3357, "step": 531 }, { "epoch": 0.24203821656050956, "grad_norm": 1.3228769141545746, "learning_rate": 4.971254531639461e-06, "loss": 0.0978, "step": 532 }, { "epoch": 0.24249317561419473, "grad_norm": 0.9022991420443233, "learning_rate": 4.971146369448957e-06, "loss": 0.073, "step": 533 }, { "epoch": 0.2429481346678799, "grad_norm": 0.8487996347147105, "learning_rate": 4.971038005327532e-06, "loss": 0.0772, "step": 534 }, { "epoch": 0.24340309372156507, "grad_norm": 1.0939700661439853, "learning_rate": 4.970929439284039e-06, "loss": 0.1052, "step": 535 }, { "epoch": 0.24385805277525022, "grad_norm": 1.1117793169544092, "learning_rate": 4.970820671327351e-06, "loss": 0.0838, "step": 536 }, { "epoch": 0.2443130118289354, "grad_norm": 0.5711568883528185, "learning_rate": 4.9707117014663565e-06, "loss": 0.0477, "step": 537 }, { "epoch": 0.24476797088262056, "grad_norm": 0.9911963887990124, "learning_rate": 4.97060252970996e-06, "loss": 0.0859, "step": 538 }, { "epoch": 0.24522292993630573, "grad_norm": 0.8786877928757788, "learning_rate": 4.970493156067081e-06, "loss": 0.0672, "step": 539 }, { "epoch": 0.2456778889899909, "grad_norm": 0.6358718673962386, "learning_rate": 4.970383580546658e-06, "loss": 0.049, "step": 540 }, { "epoch": 0.24613284804367608, "grad_norm": 0.9673038276315246, "learning_rate": 4.970273803157645e-06, "loss": 0.0789, "step": 541 }, { "epoch": 0.24658780709736125, "grad_norm": 0.7896663626576268, "learning_rate": 4.970163823909013e-06, "loss": 0.0636, "step": 542 }, { "epoch": 0.2470427661510464, "grad_norm": 0.7725841407720596, "learning_rate": 4.970053642809748e-06, "loss": 0.0591, "step": 543 }, { "epoch": 0.24749772520473157, "grad_norm": 0.8834486709832678, "learning_rate": 4.969943259868853e-06, "loss": 0.0741, "step": 544 }, { "epoch": 0.24795268425841674, "grad_norm": 0.9862513700188255, "learning_rate": 4.969832675095351e-06, "loss": 0.0733, "step": 545 }, { "epoch": 0.2484076433121019, "grad_norm": 0.9230048911450578, "learning_rate": 4.969721888498275e-06, "loss": 0.0784, "step": 546 }, { "epoch": 0.24886260236578708, "grad_norm": 0.678321429576158, "learning_rate": 4.96961090008668e-06, "loss": 0.0548, "step": 547 }, { "epoch": 0.24931756141947226, "grad_norm": 1.0377618196684284, "learning_rate": 4.969499709869635e-06, "loss": 0.0972, "step": 548 }, { "epoch": 0.24977252047315743, "grad_norm": 1.0401408232919482, "learning_rate": 4.969388317856225e-06, "loss": 0.0803, "step": 549 }, { "epoch": 0.2502274795268426, "grad_norm": 1.1187089275098543, "learning_rate": 4.969276724055554e-06, "loss": 0.0959, "step": 550 }, { "epoch": 0.25068243858052774, "grad_norm": 0.955462869329459, "learning_rate": 4.969164928476741e-06, "loss": 0.0676, "step": 551 }, { "epoch": 0.25113739763421294, "grad_norm": 0.8046461909524141, "learning_rate": 4.969052931128919e-06, "loss": 0.0648, "step": 552 }, { "epoch": 0.2515923566878981, "grad_norm": 0.7081920862352523, "learning_rate": 4.968940732021243e-06, "loss": 0.0603, "step": 553 }, { "epoch": 0.25204731574158323, "grad_norm": 0.9857688144173427, "learning_rate": 4.9688283311628795e-06, "loss": 0.0918, "step": 554 }, { "epoch": 0.25250227479526843, "grad_norm": 0.8534813080817202, "learning_rate": 4.968715728563014e-06, "loss": 0.0679, "step": 555 } ], "logging_steps": 1, "max_steps": 10990, "num_input_tokens_seen": 0, "num_train_epochs": 5, "save_steps": 555, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 3666645319680.0, "train_batch_size": 1, "trial_name": null, "trial_params": null }