{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 987, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0010139416983523447, "grad_norm": 5.121658802032471, "learning_rate": 0.0, "loss": 3.0637, "step": 1 }, { "epoch": 0.0020278833967046894, "grad_norm": 4.709918022155762, "learning_rate": 4.0000000000000003e-07, "loss": 2.9503, "step": 2 }, { "epoch": 0.003041825095057034, "grad_norm": 4.30893611907959, "learning_rate": 8.000000000000001e-07, "loss": 2.925, "step": 3 }, { "epoch": 0.004055766793409379, "grad_norm": 4.957603931427002, "learning_rate": 1.2000000000000002e-06, "loss": 2.6827, "step": 4 }, { "epoch": 0.005069708491761723, "grad_norm": 3.963380813598633, "learning_rate": 1.6000000000000001e-06, "loss": 2.8648, "step": 5 }, { "epoch": 0.006083650190114068, "grad_norm": 3.815199136734009, "learning_rate": 2.0000000000000003e-06, "loss": 2.8512, "step": 6 }, { "epoch": 0.007097591888466414, "grad_norm": 3.235830783843994, "learning_rate": 2.4000000000000003e-06, "loss": 3.0078, "step": 7 }, { "epoch": 0.008111533586818757, "grad_norm": 3.193497896194458, "learning_rate": 2.8000000000000003e-06, "loss": 2.9759, "step": 8 }, { "epoch": 0.009125475285171103, "grad_norm": 3.743866205215454, "learning_rate": 3.2000000000000003e-06, "loss": 2.6373, "step": 9 }, { "epoch": 0.010139416983523447, "grad_norm": 3.758028745651245, "learning_rate": 3.6000000000000003e-06, "loss": 3.0804, "step": 10 }, { "epoch": 0.011153358681875792, "grad_norm": 4.36395788192749, "learning_rate": 4.000000000000001e-06, "loss": 2.7003, "step": 11 }, { "epoch": 0.012167300380228136, "grad_norm": 3.525747776031494, "learning_rate": 4.4e-06, "loss": 2.9755, "step": 12 }, { "epoch": 0.013181242078580482, "grad_norm": 4.282515525817871, "learning_rate": 4.800000000000001e-06, "loss": 2.6715, "step": 13 }, { "epoch": 0.014195183776932827, "grad_norm": 3.668238639831543, "learning_rate": 5.2e-06, "loss": 2.8512, "step": 14 }, { "epoch": 0.015209125475285171, "grad_norm": 3.9769890308380127, "learning_rate": 5.600000000000001e-06, "loss": 2.8992, "step": 15 }, { "epoch": 0.016223067173637515, "grad_norm": 3.9157707691192627, "learning_rate": 6e-06, "loss": 2.7106, "step": 16 }, { "epoch": 0.01723700887198986, "grad_norm": 3.3258984088897705, "learning_rate": 6.4000000000000006e-06, "loss": 2.6878, "step": 17 }, { "epoch": 0.018250950570342206, "grad_norm": 3.4669008255004883, "learning_rate": 6.800000000000001e-06, "loss": 2.8272, "step": 18 }, { "epoch": 0.01926489226869455, "grad_norm": 3.363856077194214, "learning_rate": 7.2000000000000005e-06, "loss": 2.9048, "step": 19 }, { "epoch": 0.020278833967046894, "grad_norm": 3.460812568664551, "learning_rate": 7.600000000000001e-06, "loss": 2.8649, "step": 20 }, { "epoch": 0.02129277566539924, "grad_norm": 3.656041383743286, "learning_rate": 8.000000000000001e-06, "loss": 2.8138, "step": 21 }, { "epoch": 0.022306717363751585, "grad_norm": 3.098552942276001, "learning_rate": 8.400000000000001e-06, "loss": 2.9701, "step": 22 }, { "epoch": 0.02332065906210393, "grad_norm": 3.047813892364502, "learning_rate": 8.8e-06, "loss": 2.9061, "step": 23 }, { "epoch": 0.024334600760456272, "grad_norm": 3.0990796089172363, "learning_rate": 9.200000000000002e-06, "loss": 2.8978, "step": 24 }, { "epoch": 0.025348542458808618, "grad_norm": 3.116218090057373, "learning_rate": 9.600000000000001e-06, "loss": 2.7761, "step": 25 }, { "epoch": 0.026362484157160963, "grad_norm": 3.4951255321502686, "learning_rate": 1e-05, "loss": 3.0193, "step": 26 }, { "epoch": 0.02737642585551331, "grad_norm": 3.5713748931884766, "learning_rate": 1.04e-05, "loss": 2.6956, "step": 27 }, { "epoch": 0.028390367553865654, "grad_norm": 3.284576654434204, "learning_rate": 1.0800000000000002e-05, "loss": 2.8543, "step": 28 }, { "epoch": 0.029404309252217996, "grad_norm": 3.5328757762908936, "learning_rate": 1.1200000000000001e-05, "loss": 2.7354, "step": 29 }, { "epoch": 0.030418250950570342, "grad_norm": 3.407898187637329, "learning_rate": 1.16e-05, "loss": 2.8508, "step": 30 }, { "epoch": 0.031432192648922684, "grad_norm": 3.326301097869873, "learning_rate": 1.2e-05, "loss": 2.6679, "step": 31 }, { "epoch": 0.03244613434727503, "grad_norm": 3.08138370513916, "learning_rate": 1.2400000000000002e-05, "loss": 2.7425, "step": 32 }, { "epoch": 0.033460076045627375, "grad_norm": 3.3986353874206543, "learning_rate": 1.2800000000000001e-05, "loss": 3.036, "step": 33 }, { "epoch": 0.03447401774397972, "grad_norm": 3.1248598098754883, "learning_rate": 1.3200000000000002e-05, "loss": 2.6935, "step": 34 }, { "epoch": 0.035487959442332066, "grad_norm": 3.4256432056427, "learning_rate": 1.3600000000000002e-05, "loss": 2.9109, "step": 35 }, { "epoch": 0.03650190114068441, "grad_norm": 3.3504834175109863, "learning_rate": 1.4e-05, "loss": 2.8338, "step": 36 }, { "epoch": 0.03751584283903676, "grad_norm": 3.3927106857299805, "learning_rate": 1.4400000000000001e-05, "loss": 2.7091, "step": 37 }, { "epoch": 0.0385297845373891, "grad_norm": 3.278294086456299, "learning_rate": 1.48e-05, "loss": 2.8115, "step": 38 }, { "epoch": 0.03954372623574144, "grad_norm": 3.1749770641326904, "learning_rate": 1.5200000000000002e-05, "loss": 2.9376, "step": 39 }, { "epoch": 0.04055766793409379, "grad_norm": 3.4760537147521973, "learning_rate": 1.5600000000000003e-05, "loss": 2.626, "step": 40 }, { "epoch": 0.04157160963244613, "grad_norm": 3.464676856994629, "learning_rate": 1.6000000000000003e-05, "loss": 2.6685, "step": 41 }, { "epoch": 0.04258555133079848, "grad_norm": 3.4770150184631348, "learning_rate": 1.64e-05, "loss": 2.6069, "step": 42 }, { "epoch": 0.043599493029150824, "grad_norm": 3.5418553352355957, "learning_rate": 1.6800000000000002e-05, "loss": 2.7534, "step": 43 }, { "epoch": 0.04461343472750317, "grad_norm": 3.355006456375122, "learning_rate": 1.72e-05, "loss": 2.8957, "step": 44 }, { "epoch": 0.045627376425855515, "grad_norm": 3.518998861312866, "learning_rate": 1.76e-05, "loss": 2.9025, "step": 45 }, { "epoch": 0.04664131812420786, "grad_norm": 3.455519199371338, "learning_rate": 1.8e-05, "loss": 2.9387, "step": 46 }, { "epoch": 0.047655259822560206, "grad_norm": 3.3320729732513428, "learning_rate": 1.8400000000000003e-05, "loss": 2.7342, "step": 47 }, { "epoch": 0.048669201520912544, "grad_norm": 3.492351531982422, "learning_rate": 1.88e-05, "loss": 2.6889, "step": 48 }, { "epoch": 0.04968314321926489, "grad_norm": 3.527967929840088, "learning_rate": 1.9200000000000003e-05, "loss": 2.9035, "step": 49 }, { "epoch": 0.050697084917617236, "grad_norm": 3.1041579246520996, "learning_rate": 1.9600000000000002e-05, "loss": 3.0125, "step": 50 }, { "epoch": 0.05171102661596958, "grad_norm": 3.240447998046875, "learning_rate": 2e-05, "loss": 2.9446, "step": 51 }, { "epoch": 0.05272496831432193, "grad_norm": 3.3307602405548096, "learning_rate": 1.9999943793031672e-05, "loss": 2.8274, "step": 52 }, { "epoch": 0.05373891001267427, "grad_norm": 3.235234498977661, "learning_rate": 1.999977517275853e-05, "loss": 2.9267, "step": 53 }, { "epoch": 0.05475285171102662, "grad_norm": 3.756901502609253, "learning_rate": 1.99994941410761e-05, "loss": 2.9217, "step": 54 }, { "epoch": 0.05576679340937896, "grad_norm": 3.2789499759674072, "learning_rate": 1.999910070114357e-05, "loss": 2.8089, "step": 55 }, { "epoch": 0.05678073510773131, "grad_norm": 3.3086624145507812, "learning_rate": 1.9998594857383756e-05, "loss": 2.7262, "step": 56 }, { "epoch": 0.05779467680608365, "grad_norm": 3.289076089859009, "learning_rate": 1.9997976615483042e-05, "loss": 2.7543, "step": 57 }, { "epoch": 0.05880861850443599, "grad_norm": 3.6002161502838135, "learning_rate": 1.9997245982391335e-05, "loss": 3.1664, "step": 58 }, { "epoch": 0.05982256020278834, "grad_norm": 3.1306004524230957, "learning_rate": 1.9996402966321962e-05, "loss": 2.7802, "step": 59 }, { "epoch": 0.060836501901140684, "grad_norm": 3.0634193420410156, "learning_rate": 1.9995447576751605e-05, "loss": 2.9049, "step": 60 }, { "epoch": 0.06185044359949303, "grad_norm": 3.2394661903381348, "learning_rate": 1.999437982442017e-05, "loss": 2.6699, "step": 61 }, { "epoch": 0.06286438529784537, "grad_norm": 3.115633487701416, "learning_rate": 1.9993199721330684e-05, "loss": 2.8081, "step": 62 }, { "epoch": 0.06387832699619772, "grad_norm": 3.0398242473602295, "learning_rate": 1.9991907280749148e-05, "loss": 2.7188, "step": 63 }, { "epoch": 0.06489226869455006, "grad_norm": 3.1383628845214844, "learning_rate": 1.99905025172044e-05, "loss": 2.8215, "step": 64 }, { "epoch": 0.06590621039290241, "grad_norm": 2.999265670776367, "learning_rate": 1.998898544648793e-05, "loss": 2.7608, "step": 65 }, { "epoch": 0.06692015209125475, "grad_norm": 3.1938254833221436, "learning_rate": 1.9987356085653738e-05, "loss": 2.9058, "step": 66 }, { "epoch": 0.0679340937896071, "grad_norm": 3.3138041496276855, "learning_rate": 1.99856144530181e-05, "loss": 2.7962, "step": 67 }, { "epoch": 0.06894803548795944, "grad_norm": 3.443120002746582, "learning_rate": 1.998376056815941e-05, "loss": 2.8264, "step": 68 }, { "epoch": 0.0699619771863118, "grad_norm": 3.0764691829681396, "learning_rate": 1.99817944519179e-05, "loss": 3.0068, "step": 69 }, { "epoch": 0.07097591888466413, "grad_norm": 3.1897008419036865, "learning_rate": 1.997971612639547e-05, "loss": 2.8515, "step": 70 }, { "epoch": 0.07198986058301647, "grad_norm": 3.391533613204956, "learning_rate": 1.9977525614955388e-05, "loss": 3.0471, "step": 71 }, { "epoch": 0.07300380228136882, "grad_norm": 3.4642486572265625, "learning_rate": 1.9975222942222054e-05, "loss": 2.6579, "step": 72 }, { "epoch": 0.07401774397972116, "grad_norm": 3.1187565326690674, "learning_rate": 1.9972808134080726e-05, "loss": 2.6668, "step": 73 }, { "epoch": 0.07503168567807351, "grad_norm": 3.5440473556518555, "learning_rate": 1.9970281217677207e-05, "loss": 2.6528, "step": 74 }, { "epoch": 0.07604562737642585, "grad_norm": 3.1511693000793457, "learning_rate": 1.996764222141756e-05, "loss": 2.809, "step": 75 }, { "epoch": 0.0770595690747782, "grad_norm": 3.2542364597320557, "learning_rate": 1.9964891174967786e-05, "loss": 2.8991, "step": 76 }, { "epoch": 0.07807351077313054, "grad_norm": 3.112870693206787, "learning_rate": 1.9962028109253474e-05, "loss": 2.8619, "step": 77 }, { "epoch": 0.07908745247148288, "grad_norm": 3.0254783630371094, "learning_rate": 1.9959053056459474e-05, "loss": 2.8254, "step": 78 }, { "epoch": 0.08010139416983524, "grad_norm": 3.1325619220733643, "learning_rate": 1.995596605002953e-05, "loss": 3.1019, "step": 79 }, { "epoch": 0.08111533586818757, "grad_norm": 3.5266387462615967, "learning_rate": 1.9952767124665892e-05, "loss": 2.7379, "step": 80 }, { "epoch": 0.08212927756653993, "grad_norm": 3.245556116104126, "learning_rate": 1.9949456316328942e-05, "loss": 2.8923, "step": 81 }, { "epoch": 0.08314321926489227, "grad_norm": 3.3015191555023193, "learning_rate": 1.9946033662236778e-05, "loss": 2.7714, "step": 82 }, { "epoch": 0.08415716096324462, "grad_norm": 3.5391364097595215, "learning_rate": 1.9942499200864805e-05, "loss": 2.7163, "step": 83 }, { "epoch": 0.08517110266159696, "grad_norm": 3.1607401371002197, "learning_rate": 1.993885297194529e-05, "loss": 2.8144, "step": 84 }, { "epoch": 0.08618504435994931, "grad_norm": 3.0026676654815674, "learning_rate": 1.993509501646693e-05, "loss": 2.9125, "step": 85 }, { "epoch": 0.08719898605830165, "grad_norm": 3.2028753757476807, "learning_rate": 1.9931225376674388e-05, "loss": 2.8126, "step": 86 }, { "epoch": 0.08821292775665399, "grad_norm": 3.233186960220337, "learning_rate": 1.99272440960678e-05, "loss": 2.6726, "step": 87 }, { "epoch": 0.08922686945500634, "grad_norm": 3.0833544731140137, "learning_rate": 1.9923151219402308e-05, "loss": 2.6719, "step": 88 }, { "epoch": 0.09024081115335868, "grad_norm": 3.059297561645508, "learning_rate": 1.9918946792687553e-05, "loss": 2.7005, "step": 89 }, { "epoch": 0.09125475285171103, "grad_norm": 3.261103868484497, "learning_rate": 1.9914630863187156e-05, "loss": 2.5295, "step": 90 }, { "epoch": 0.09226869455006337, "grad_norm": 3.4985969066619873, "learning_rate": 1.991020347941817e-05, "loss": 2.7838, "step": 91 }, { "epoch": 0.09328263624841572, "grad_norm": 3.427159309387207, "learning_rate": 1.9905664691150567e-05, "loss": 2.6065, "step": 92 }, { "epoch": 0.09429657794676806, "grad_norm": 3.205653429031372, "learning_rate": 1.9901014549406647e-05, "loss": 2.854, "step": 93 }, { "epoch": 0.09531051964512041, "grad_norm": 3.1949386596679688, "learning_rate": 1.9896253106460484e-05, "loss": 2.7194, "step": 94 }, { "epoch": 0.09632446134347275, "grad_norm": 3.4181830883026123, "learning_rate": 1.9891380415837333e-05, "loss": 2.916, "step": 95 }, { "epoch": 0.09733840304182509, "grad_norm": 3.4856419563293457, "learning_rate": 1.9886396532313033e-05, "loss": 2.7623, "step": 96 }, { "epoch": 0.09835234474017744, "grad_norm": 3.247903823852539, "learning_rate": 1.9881301511913372e-05, "loss": 2.9527, "step": 97 }, { "epoch": 0.09936628643852978, "grad_norm": 3.5031447410583496, "learning_rate": 1.9876095411913492e-05, "loss": 2.7794, "step": 98 }, { "epoch": 0.10038022813688213, "grad_norm": 3.3715412616729736, "learning_rate": 1.9870778290837198e-05, "loss": 2.9483, "step": 99 }, { "epoch": 0.10139416983523447, "grad_norm": 3.354491949081421, "learning_rate": 1.9865350208456354e-05, "loss": 2.7876, "step": 100 }, { "epoch": 0.10240811153358682, "grad_norm": 3.0715112686157227, "learning_rate": 1.9859811225790164e-05, "loss": 2.7182, "step": 101 }, { "epoch": 0.10342205323193916, "grad_norm": 3.059152364730835, "learning_rate": 1.9854161405104512e-05, "loss": 2.6625, "step": 102 }, { "epoch": 0.10443599493029151, "grad_norm": 3.0856645107269287, "learning_rate": 1.9848400809911255e-05, "loss": 2.7493, "step": 103 }, { "epoch": 0.10544993662864385, "grad_norm": 3.523483991622925, "learning_rate": 1.9842529504967522e-05, "loss": 2.696, "step": 104 }, { "epoch": 0.10646387832699619, "grad_norm": 3.5456182956695557, "learning_rate": 1.9836547556274954e-05, "loss": 2.7098, "step": 105 }, { "epoch": 0.10747782002534854, "grad_norm": 3.539569616317749, "learning_rate": 1.9830455031078994e-05, "loss": 2.7044, "step": 106 }, { "epoch": 0.10849176172370088, "grad_norm": 3.270253896713257, "learning_rate": 1.982425199786811e-05, "loss": 2.7607, "step": 107 }, { "epoch": 0.10950570342205324, "grad_norm": 3.0167229175567627, "learning_rate": 1.981793852637305e-05, "loss": 2.6388, "step": 108 }, { "epoch": 0.11051964512040557, "grad_norm": 3.2504289150238037, "learning_rate": 1.981151468756603e-05, "loss": 2.7782, "step": 109 }, { "epoch": 0.11153358681875793, "grad_norm": 3.174086809158325, "learning_rate": 1.980498055365994e-05, "loss": 2.875, "step": 110 }, { "epoch": 0.11254752851711027, "grad_norm": 3.3104934692382812, "learning_rate": 1.9798336198107567e-05, "loss": 2.8241, "step": 111 }, { "epoch": 0.11356147021546262, "grad_norm": 3.000248908996582, "learning_rate": 1.9791581695600722e-05, "loss": 2.8913, "step": 112 }, { "epoch": 0.11457541191381496, "grad_norm": 3.089625597000122, "learning_rate": 1.9784717122069425e-05, "loss": 2.7071, "step": 113 }, { "epoch": 0.1155893536121673, "grad_norm": 3.0423169136047363, "learning_rate": 1.9777742554681044e-05, "loss": 2.7411, "step": 114 }, { "epoch": 0.11660329531051965, "grad_norm": 3.0240306854248047, "learning_rate": 1.9770658071839448e-05, "loss": 2.9403, "step": 115 }, { "epoch": 0.11761723700887199, "grad_norm": 3.2751612663269043, "learning_rate": 1.9763463753184092e-05, "loss": 2.8083, "step": 116 }, { "epoch": 0.11863117870722434, "grad_norm": 3.2764761447906494, "learning_rate": 1.9756159679589143e-05, "loss": 2.7055, "step": 117 }, { "epoch": 0.11964512040557668, "grad_norm": 3.3007071018218994, "learning_rate": 1.974874593316257e-05, "loss": 2.8231, "step": 118 }, { "epoch": 0.12065906210392903, "grad_norm": 3.1403753757476807, "learning_rate": 1.974122259724521e-05, "loss": 2.7642, "step": 119 }, { "epoch": 0.12167300380228137, "grad_norm": 3.297636032104492, "learning_rate": 1.973358975640985e-05, "loss": 2.7253, "step": 120 }, { "epoch": 0.1226869455006337, "grad_norm": 3.160066604614258, "learning_rate": 1.9725847496460256e-05, "loss": 2.7361, "step": 121 }, { "epoch": 0.12370088719898606, "grad_norm": 3.448756217956543, "learning_rate": 1.9717995904430224e-05, "loss": 2.6938, "step": 122 }, { "epoch": 0.1247148288973384, "grad_norm": 3.196122884750366, "learning_rate": 1.9710035068582586e-05, "loss": 2.881, "step": 123 }, { "epoch": 0.12572877059569074, "grad_norm": 2.8908872604370117, "learning_rate": 1.970196507840823e-05, "loss": 2.764, "step": 124 }, { "epoch": 0.1267427122940431, "grad_norm": 3.0789546966552734, "learning_rate": 1.9693786024625097e-05, "loss": 2.8602, "step": 125 }, { "epoch": 0.12775665399239544, "grad_norm": 3.1777265071868896, "learning_rate": 1.968549799917715e-05, "loss": 2.7955, "step": 126 }, { "epoch": 0.12877059569074778, "grad_norm": 3.3578367233276367, "learning_rate": 1.9677101095233342e-05, "loss": 2.8042, "step": 127 }, { "epoch": 0.12978453738910012, "grad_norm": 3.195127487182617, "learning_rate": 1.966859540718658e-05, "loss": 2.6936, "step": 128 }, { "epoch": 0.13079847908745248, "grad_norm": 3.3365399837493896, "learning_rate": 1.9659981030652648e-05, "loss": 2.8029, "step": 129 }, { "epoch": 0.13181242078580482, "grad_norm": 2.9787654876708984, "learning_rate": 1.965125806246915e-05, "loss": 2.6843, "step": 130 }, { "epoch": 0.13282636248415716, "grad_norm": 3.062211751937866, "learning_rate": 1.9642426600694395e-05, "loss": 2.8227, "step": 131 }, { "epoch": 0.1338403041825095, "grad_norm": 3.1210687160491943, "learning_rate": 1.963348674460633e-05, "loss": 2.9978, "step": 132 }, { "epoch": 0.13485424588086184, "grad_norm": 3.349961757659912, "learning_rate": 1.9624438594701397e-05, "loss": 2.6609, "step": 133 }, { "epoch": 0.1358681875792142, "grad_norm": 2.9804890155792236, "learning_rate": 1.9615282252693407e-05, "loss": 2.7305, "step": 134 }, { "epoch": 0.13688212927756654, "grad_norm": 3.0483453273773193, "learning_rate": 1.9606017821512405e-05, "loss": 2.8606, "step": 135 }, { "epoch": 0.13789607097591888, "grad_norm": 2.8871631622314453, "learning_rate": 1.9596645405303508e-05, "loss": 2.959, "step": 136 }, { "epoch": 0.13891001267427122, "grad_norm": 2.925555944442749, "learning_rate": 1.9587165109425746e-05, "loss": 2.7799, "step": 137 }, { "epoch": 0.1399239543726236, "grad_norm": 3.3795876502990723, "learning_rate": 1.9577577040450842e-05, "loss": 2.4838, "step": 138 }, { "epoch": 0.14093789607097593, "grad_norm": 2.9723339080810547, "learning_rate": 1.9567881306162065e-05, "loss": 2.5472, "step": 139 }, { "epoch": 0.14195183776932827, "grad_norm": 3.181236505508423, "learning_rate": 1.9558078015552973e-05, "loss": 2.7748, "step": 140 }, { "epoch": 0.1429657794676806, "grad_norm": 3.5478413105010986, "learning_rate": 1.9548167278826224e-05, "loss": 2.5927, "step": 141 }, { "epoch": 0.14397972116603294, "grad_norm": 3.1357247829437256, "learning_rate": 1.9538149207392306e-05, "loss": 2.8367, "step": 142 }, { "epoch": 0.1449936628643853, "grad_norm": 2.7414956092834473, "learning_rate": 1.9528023913868305e-05, "loss": 2.7574, "step": 143 }, { "epoch": 0.14600760456273765, "grad_norm": 2.9295525550842285, "learning_rate": 1.9517791512076628e-05, "loss": 2.7733, "step": 144 }, { "epoch": 0.14702154626108999, "grad_norm": 3.1006598472595215, "learning_rate": 1.9507452117043736e-05, "loss": 2.7275, "step": 145 }, { "epoch": 0.14803548795944232, "grad_norm": 2.8998913764953613, "learning_rate": 1.9497005844998835e-05, "loss": 2.9219, "step": 146 }, { "epoch": 0.14904942965779466, "grad_norm": 3.2651214599609375, "learning_rate": 1.9486452813372586e-05, "loss": 2.7337, "step": 147 }, { "epoch": 0.15006337135614703, "grad_norm": 3.1806275844573975, "learning_rate": 1.947579314079577e-05, "loss": 2.7466, "step": 148 }, { "epoch": 0.15107731305449937, "grad_norm": 3.137009859085083, "learning_rate": 1.946502694709796e-05, "loss": 2.8247, "step": 149 }, { "epoch": 0.1520912547528517, "grad_norm": 3.00809645652771, "learning_rate": 1.945415435330618e-05, "loss": 2.6825, "step": 150 }, { "epoch": 0.15310519645120405, "grad_norm": 3.1236531734466553, "learning_rate": 1.9443175481643536e-05, "loss": 2.85, "step": 151 }, { "epoch": 0.1541191381495564, "grad_norm": 2.8082268238067627, "learning_rate": 1.9432090455527847e-05, "loss": 2.8106, "step": 152 }, { "epoch": 0.15513307984790875, "grad_norm": 3.262784957885742, "learning_rate": 1.942089939957026e-05, "loss": 2.5627, "step": 153 }, { "epoch": 0.1561470215462611, "grad_norm": 3.1046485900878906, "learning_rate": 1.940960243957383e-05, "loss": 2.8634, "step": 154 }, { "epoch": 0.15716096324461343, "grad_norm": 3.412945508956909, "learning_rate": 1.9398199702532143e-05, "loss": 2.6015, "step": 155 }, { "epoch": 0.15817490494296577, "grad_norm": 3.2352962493896484, "learning_rate": 1.9386691316627845e-05, "loss": 2.5903, "step": 156 }, { "epoch": 0.15918884664131813, "grad_norm": 3.3233420848846436, "learning_rate": 1.937507741123124e-05, "loss": 2.7309, "step": 157 }, { "epoch": 0.16020278833967047, "grad_norm": 3.314918279647827, "learning_rate": 1.9363358116898804e-05, "loss": 2.4656, "step": 158 }, { "epoch": 0.1612167300380228, "grad_norm": 3.487234354019165, "learning_rate": 1.9351533565371747e-05, "loss": 2.7646, "step": 159 }, { "epoch": 0.16223067173637515, "grad_norm": 3.012712001800537, "learning_rate": 1.9339603889574498e-05, "loss": 2.6756, "step": 160 }, { "epoch": 0.16324461343472751, "grad_norm": 3.2188124656677246, "learning_rate": 1.932756922361325e-05, "loss": 2.6434, "step": 161 }, { "epoch": 0.16425855513307985, "grad_norm": 3.085340738296509, "learning_rate": 1.9315429702774408e-05, "loss": 2.7135, "step": 162 }, { "epoch": 0.1652724968314322, "grad_norm": 3.1618096828460693, "learning_rate": 1.9303185463523108e-05, "loss": 2.916, "step": 163 }, { "epoch": 0.16628643852978453, "grad_norm": 2.805600881576538, "learning_rate": 1.929083664350167e-05, "loss": 2.8468, "step": 164 }, { "epoch": 0.16730038022813687, "grad_norm": 3.0501015186309814, "learning_rate": 1.9278383381528036e-05, "loss": 2.5067, "step": 165 }, { "epoch": 0.16831432192648924, "grad_norm": 3.0693836212158203, "learning_rate": 1.9265825817594232e-05, "loss": 2.7927, "step": 166 }, { "epoch": 0.16932826362484157, "grad_norm": 3.132962226867676, "learning_rate": 1.9253164092864768e-05, "loss": 2.7414, "step": 167 }, { "epoch": 0.1703422053231939, "grad_norm": 2.9955735206604004, "learning_rate": 1.9240398349675083e-05, "loss": 2.8164, "step": 168 }, { "epoch": 0.17135614702154625, "grad_norm": 2.998502254486084, "learning_rate": 1.922752873152992e-05, "loss": 2.895, "step": 169 }, { "epoch": 0.17237008871989862, "grad_norm": 2.969083786010742, "learning_rate": 1.9214555383101724e-05, "loss": 2.9225, "step": 170 }, { "epoch": 0.17338403041825096, "grad_norm": 3.307370901107788, "learning_rate": 1.9201478450229012e-05, "loss": 2.4807, "step": 171 }, { "epoch": 0.1743979721166033, "grad_norm": 2.9617295265197754, "learning_rate": 1.918829807991473e-05, "loss": 2.6784, "step": 172 }, { "epoch": 0.17541191381495563, "grad_norm": 3.0904929637908936, "learning_rate": 1.9175014420324613e-05, "loss": 2.644, "step": 173 }, { "epoch": 0.17642585551330797, "grad_norm": 3.1362547874450684, "learning_rate": 1.916162762078551e-05, "loss": 2.9906, "step": 174 }, { "epoch": 0.17743979721166034, "grad_norm": 3.120621681213379, "learning_rate": 1.91481378317837e-05, "loss": 2.7463, "step": 175 }, { "epoch": 0.17845373891001268, "grad_norm": 2.8338675498962402, "learning_rate": 1.9134545204963214e-05, "loss": 2.663, "step": 176 }, { "epoch": 0.17946768060836502, "grad_norm": 3.007894515991211, "learning_rate": 1.912084989312412e-05, "loss": 2.5924, "step": 177 }, { "epoch": 0.18048162230671735, "grad_norm": 3.334587812423706, "learning_rate": 1.9107052050220808e-05, "loss": 2.668, "step": 178 }, { "epoch": 0.18149556400506972, "grad_norm": 3.349618911743164, "learning_rate": 1.9093151831360268e-05, "loss": 2.3898, "step": 179 }, { "epoch": 0.18250950570342206, "grad_norm": 3.2005631923675537, "learning_rate": 1.907914939280033e-05, "loss": 2.7596, "step": 180 }, { "epoch": 0.1835234474017744, "grad_norm": 2.9870338439941406, "learning_rate": 1.906504489194791e-05, "loss": 2.6952, "step": 181 }, { "epoch": 0.18453738910012674, "grad_norm": 3.391935110092163, "learning_rate": 1.9050838487357267e-05, "loss": 2.8396, "step": 182 }, { "epoch": 0.18555133079847907, "grad_norm": 3.0437772274017334, "learning_rate": 1.903653033872818e-05, "loss": 2.7672, "step": 183 }, { "epoch": 0.18656527249683144, "grad_norm": 3.137467384338379, "learning_rate": 1.902212060690418e-05, "loss": 2.5997, "step": 184 }, { "epoch": 0.18757921419518378, "grad_norm": 3.1098976135253906, "learning_rate": 1.9007609453870738e-05, "loss": 2.5968, "step": 185 }, { "epoch": 0.18859315589353612, "grad_norm": 2.889174461364746, "learning_rate": 1.8992997042753437e-05, "loss": 2.8723, "step": 186 }, { "epoch": 0.18960709759188846, "grad_norm": 2.9620108604431152, "learning_rate": 1.897828353781614e-05, "loss": 2.8452, "step": 187 }, { "epoch": 0.19062103929024082, "grad_norm": 3.097540855407715, "learning_rate": 1.8963469104459157e-05, "loss": 2.6636, "step": 188 }, { "epoch": 0.19163498098859316, "grad_norm": 3.580857753753662, "learning_rate": 1.8948553909217354e-05, "loss": 2.9052, "step": 189 }, { "epoch": 0.1926489226869455, "grad_norm": 3.1843173503875732, "learning_rate": 1.893353811975832e-05, "loss": 2.6518, "step": 190 }, { "epoch": 0.19366286438529784, "grad_norm": 3.3880133628845215, "learning_rate": 1.891842190488045e-05, "loss": 2.6159, "step": 191 }, { "epoch": 0.19467680608365018, "grad_norm": 3.032352924346924, "learning_rate": 1.8903205434511072e-05, "loss": 2.7976, "step": 192 }, { "epoch": 0.19569074778200254, "grad_norm": 3.150266647338867, "learning_rate": 1.888788887970452e-05, "loss": 2.6576, "step": 193 }, { "epoch": 0.19670468948035488, "grad_norm": 3.5360684394836426, "learning_rate": 1.8872472412640207e-05, "loss": 2.6702, "step": 194 }, { "epoch": 0.19771863117870722, "grad_norm": 3.3476462364196777, "learning_rate": 1.8856956206620717e-05, "loss": 2.7005, "step": 195 }, { "epoch": 0.19873257287705956, "grad_norm": 3.220618963241577, "learning_rate": 1.8841340436069825e-05, "loss": 2.9062, "step": 196 }, { "epoch": 0.19974651457541193, "grad_norm": 3.2296738624572754, "learning_rate": 1.8825625276530558e-05, "loss": 2.6451, "step": 197 }, { "epoch": 0.20076045627376427, "grad_norm": 2.9868884086608887, "learning_rate": 1.880981090466321e-05, "loss": 2.9176, "step": 198 }, { "epoch": 0.2017743979721166, "grad_norm": 2.976165771484375, "learning_rate": 1.879389749824336e-05, "loss": 2.7571, "step": 199 }, { "epoch": 0.20278833967046894, "grad_norm": 3.1209869384765625, "learning_rate": 1.877788523615988e-05, "loss": 2.7242, "step": 200 }, { "epoch": 0.20380228136882128, "grad_norm": 2.7696938514709473, "learning_rate": 1.8761774298412905e-05, "loss": 2.8417, "step": 201 }, { "epoch": 0.20481622306717365, "grad_norm": 3.3098506927490234, "learning_rate": 1.874556486611183e-05, "loss": 2.72, "step": 202 }, { "epoch": 0.20583016476552599, "grad_norm": 3.050853967666626, "learning_rate": 1.8729257121473262e-05, "loss": 2.6551, "step": 203 }, { "epoch": 0.20684410646387832, "grad_norm": 2.8224573135375977, "learning_rate": 1.8712851247818985e-05, "loss": 2.7885, "step": 204 }, { "epoch": 0.20785804816223066, "grad_norm": 3.180731773376465, "learning_rate": 1.869634742957388e-05, "loss": 2.6939, "step": 205 }, { "epoch": 0.20887198986058303, "grad_norm": 3.3162038326263428, "learning_rate": 1.867974585226386e-05, "loss": 2.687, "step": 206 }, { "epoch": 0.20988593155893537, "grad_norm": 2.7698941230773926, "learning_rate": 1.8663046702513795e-05, "loss": 2.6386, "step": 207 }, { "epoch": 0.2108998732572877, "grad_norm": 2.8454737663269043, "learning_rate": 1.8646250168045402e-05, "loss": 2.6816, "step": 208 }, { "epoch": 0.21191381495564005, "grad_norm": 3.039781332015991, "learning_rate": 1.862935643767514e-05, "loss": 2.6857, "step": 209 }, { "epoch": 0.21292775665399238, "grad_norm": 2.972322463989258, "learning_rate": 1.8612365701312075e-05, "loss": 2.7863, "step": 210 }, { "epoch": 0.21394169835234475, "grad_norm": 3.0482544898986816, "learning_rate": 1.859527814995577e-05, "loss": 2.5569, "step": 211 }, { "epoch": 0.2149556400506971, "grad_norm": 3.240053653717041, "learning_rate": 1.8578093975694116e-05, "loss": 2.6481, "step": 212 }, { "epoch": 0.21596958174904943, "grad_norm": 3.193847179412842, "learning_rate": 1.8560813371701174e-05, "loss": 2.7145, "step": 213 }, { "epoch": 0.21698352344740177, "grad_norm": 3.1215016841888428, "learning_rate": 1.8543436532235024e-05, "loss": 2.8692, "step": 214 }, { "epoch": 0.21799746514575413, "grad_norm": 2.8203959465026855, "learning_rate": 1.8525963652635556e-05, "loss": 2.8702, "step": 215 }, { "epoch": 0.21901140684410647, "grad_norm": 3.0731961727142334, "learning_rate": 1.8508394929322287e-05, "loss": 2.6172, "step": 216 }, { "epoch": 0.2200253485424588, "grad_norm": 2.7819225788116455, "learning_rate": 1.8490730559792153e-05, "loss": 2.6681, "step": 217 }, { "epoch": 0.22103929024081115, "grad_norm": 2.939059019088745, "learning_rate": 1.8472970742617284e-05, "loss": 2.538, "step": 218 }, { "epoch": 0.2220532319391635, "grad_norm": 3.051414728164673, "learning_rate": 1.8455115677442782e-05, "loss": 2.969, "step": 219 }, { "epoch": 0.22306717363751585, "grad_norm": 3.1464333534240723, "learning_rate": 1.8437165564984455e-05, "loss": 2.8688, "step": 220 }, { "epoch": 0.2240811153358682, "grad_norm": 2.8206515312194824, "learning_rate": 1.841912060702659e-05, "loss": 2.662, "step": 221 }, { "epoch": 0.22509505703422053, "grad_norm": 3.0998098850250244, "learning_rate": 1.8400981006419663e-05, "loss": 2.657, "step": 222 }, { "epoch": 0.22610899873257287, "grad_norm": 3.293029308319092, "learning_rate": 1.8382746967078063e-05, "loss": 2.5864, "step": 223 }, { "epoch": 0.22712294043092524, "grad_norm": 3.0117993354797363, "learning_rate": 1.8364418693977803e-05, "loss": 2.7637, "step": 224 }, { "epoch": 0.22813688212927757, "grad_norm": 3.1829309463500977, "learning_rate": 1.834599639315422e-05, "loss": 2.7799, "step": 225 }, { "epoch": 0.2291508238276299, "grad_norm": 2.91520619392395, "learning_rate": 1.8327480271699647e-05, "loss": 2.678, "step": 226 }, { "epoch": 0.23016476552598225, "grad_norm": 2.9226183891296387, "learning_rate": 1.8308870537761094e-05, "loss": 2.5984, "step": 227 }, { "epoch": 0.2311787072243346, "grad_norm": 3.276668071746826, "learning_rate": 1.829016740053791e-05, "loss": 2.7147, "step": 228 }, { "epoch": 0.23219264892268696, "grad_norm": 2.882828950881958, "learning_rate": 1.8271371070279418e-05, "loss": 2.7388, "step": 229 }, { "epoch": 0.2332065906210393, "grad_norm": 2.8925859928131104, "learning_rate": 1.8252481758282573e-05, "loss": 2.9969, "step": 230 }, { "epoch": 0.23422053231939163, "grad_norm": 2.904247760772705, "learning_rate": 1.8233499676889556e-05, "loss": 2.7041, "step": 231 }, { "epoch": 0.23523447401774397, "grad_norm": 2.9626731872558594, "learning_rate": 1.8214425039485428e-05, "loss": 2.7114, "step": 232 }, { "epoch": 0.23624841571609634, "grad_norm": 3.2437496185302734, "learning_rate": 1.8195258060495693e-05, "loss": 2.6311, "step": 233 }, { "epoch": 0.23726235741444868, "grad_norm": 2.8737614154815674, "learning_rate": 1.8175998955383906e-05, "loss": 2.7573, "step": 234 }, { "epoch": 0.23827629911280102, "grad_norm": 2.9143168926239014, "learning_rate": 1.815664794064925e-05, "loss": 2.4661, "step": 235 }, { "epoch": 0.23929024081115335, "grad_norm": 3.0798699855804443, "learning_rate": 1.81372052338241e-05, "loss": 2.9082, "step": 236 }, { "epoch": 0.2403041825095057, "grad_norm": 2.7913010120391846, "learning_rate": 1.8117671053471576e-05, "loss": 2.7929, "step": 237 }, { "epoch": 0.24131812420785806, "grad_norm": 3.1236677169799805, "learning_rate": 1.8098045619183092e-05, "loss": 2.7495, "step": 238 }, { "epoch": 0.2423320659062104, "grad_norm": 2.8255903720855713, "learning_rate": 1.8078329151575874e-05, "loss": 2.7466, "step": 239 }, { "epoch": 0.24334600760456274, "grad_norm": 2.974113702774048, "learning_rate": 1.8058521872290505e-05, "loss": 2.904, "step": 240 }, { "epoch": 0.24435994930291507, "grad_norm": 3.112579107284546, "learning_rate": 1.8038624003988406e-05, "loss": 2.4985, "step": 241 }, { "epoch": 0.2453738910012674, "grad_norm": 2.8516876697540283, "learning_rate": 1.8018635770349343e-05, "loss": 2.6785, "step": 242 }, { "epoch": 0.24638783269961978, "grad_norm": 2.862663745880127, "learning_rate": 1.7998557396068923e-05, "loss": 2.7665, "step": 243 }, { "epoch": 0.24740177439797212, "grad_norm": 2.899121046066284, "learning_rate": 1.7978389106856056e-05, "loss": 2.5681, "step": 244 }, { "epoch": 0.24841571609632446, "grad_norm": 2.860578775405884, "learning_rate": 1.7958131129430417e-05, "loss": 2.5012, "step": 245 }, { "epoch": 0.2494296577946768, "grad_norm": 2.837778091430664, "learning_rate": 1.793778369151991e-05, "loss": 2.4009, "step": 246 }, { "epoch": 0.25044359949302913, "grad_norm": 2.9025585651397705, "learning_rate": 1.7917347021858092e-05, "loss": 2.7712, "step": 247 }, { "epoch": 0.2514575411913815, "grad_norm": 2.781691074371338, "learning_rate": 1.7896821350181613e-05, "loss": 2.7241, "step": 248 }, { "epoch": 0.25247148288973387, "grad_norm": 3.0579018592834473, "learning_rate": 1.7876206907227628e-05, "loss": 2.7345, "step": 249 }, { "epoch": 0.2534854245880862, "grad_norm": 3.0960402488708496, "learning_rate": 1.7855503924731205e-05, "loss": 2.8208, "step": 250 }, { "epoch": 0.25449936628643854, "grad_norm": 2.78804349899292, "learning_rate": 1.7834712635422718e-05, "loss": 2.8634, "step": 251 }, { "epoch": 0.2555133079847909, "grad_norm": 3.100924491882324, "learning_rate": 1.7813833273025237e-05, "loss": 2.6371, "step": 252 }, { "epoch": 0.2565272496831432, "grad_norm": 2.7627742290496826, "learning_rate": 1.77928660722519e-05, "loss": 2.5151, "step": 253 }, { "epoch": 0.25754119138149556, "grad_norm": 3.0632212162017822, "learning_rate": 1.7771811268803258e-05, "loss": 2.8475, "step": 254 }, { "epoch": 0.2585551330798479, "grad_norm": 3.1408166885375977, "learning_rate": 1.7750669099364643e-05, "loss": 2.7642, "step": 255 }, { "epoch": 0.25956907477820024, "grad_norm": 2.8695948123931885, "learning_rate": 1.772943980160351e-05, "loss": 2.6326, "step": 256 }, { "epoch": 0.2605830164765526, "grad_norm": 2.7842013835906982, "learning_rate": 1.770812361416675e-05, "loss": 2.6616, "step": 257 }, { "epoch": 0.26159695817490497, "grad_norm": 2.9320297241210938, "learning_rate": 1.768672077667802e-05, "loss": 2.559, "step": 258 }, { "epoch": 0.2626108998732573, "grad_norm": 3.1390798091888428, "learning_rate": 1.7665231529735042e-05, "loss": 2.6741, "step": 259 }, { "epoch": 0.26362484157160965, "grad_norm": 2.9545533657073975, "learning_rate": 1.7643656114906895e-05, "loss": 2.9671, "step": 260 }, { "epoch": 0.264638783269962, "grad_norm": 2.8401505947113037, "learning_rate": 1.762199477473131e-05, "loss": 3.0152, "step": 261 }, { "epoch": 0.2656527249683143, "grad_norm": 3.3156533241271973, "learning_rate": 1.7600247752711952e-05, "loss": 2.6879, "step": 262 }, { "epoch": 0.26666666666666666, "grad_norm": 3.1197516918182373, "learning_rate": 1.7578415293315646e-05, "loss": 2.6275, "step": 263 }, { "epoch": 0.267680608365019, "grad_norm": 3.0614259243011475, "learning_rate": 1.7556497641969658e-05, "loss": 2.52, "step": 264 }, { "epoch": 0.26869455006337134, "grad_norm": 3.004460573196411, "learning_rate": 1.7534495045058947e-05, "loss": 2.5844, "step": 265 }, { "epoch": 0.2697084917617237, "grad_norm": 2.928093433380127, "learning_rate": 1.751240774992336e-05, "loss": 2.6644, "step": 266 }, { "epoch": 0.2707224334600761, "grad_norm": 2.934621572494507, "learning_rate": 1.749023600485488e-05, "loss": 2.4901, "step": 267 }, { "epoch": 0.2717363751584284, "grad_norm": 2.828896999359131, "learning_rate": 1.7467980059094817e-05, "loss": 2.5597, "step": 268 }, { "epoch": 0.27275031685678075, "grad_norm": 3.0283548831939697, "learning_rate": 1.744564016283102e-05, "loss": 2.7064, "step": 269 }, { "epoch": 0.2737642585551331, "grad_norm": 2.7558844089508057, "learning_rate": 1.742321656719506e-05, "loss": 2.7417, "step": 270 }, { "epoch": 0.2747782002534854, "grad_norm": 2.749242067337036, "learning_rate": 1.74007095242594e-05, "loss": 2.7896, "step": 271 }, { "epoch": 0.27579214195183777, "grad_norm": 2.8161332607269287, "learning_rate": 1.737811928703457e-05, "loss": 2.6507, "step": 272 }, { "epoch": 0.2768060836501901, "grad_norm": 3.237185001373291, "learning_rate": 1.7355446109466326e-05, "loss": 2.4539, "step": 273 }, { "epoch": 0.27782002534854244, "grad_norm": 2.7998554706573486, "learning_rate": 1.7332690246432774e-05, "loss": 2.6713, "step": 274 }, { "epoch": 0.2788339670468948, "grad_norm": 3.0803017616271973, "learning_rate": 1.7309851953741532e-05, "loss": 2.816, "step": 275 }, { "epoch": 0.2798479087452472, "grad_norm": 2.995108127593994, "learning_rate": 1.728693148812684e-05, "loss": 2.6192, "step": 276 }, { "epoch": 0.2808618504435995, "grad_norm": 3.189038038253784, "learning_rate": 1.7263929107246672e-05, "loss": 2.7477, "step": 277 }, { "epoch": 0.28187579214195185, "grad_norm": 3.0140798091888428, "learning_rate": 1.724084506967985e-05, "loss": 2.5284, "step": 278 }, { "epoch": 0.2828897338403042, "grad_norm": 3.156503438949585, "learning_rate": 1.721767963492313e-05, "loss": 2.8121, "step": 279 }, { "epoch": 0.28390367553865653, "grad_norm": 2.9829587936401367, "learning_rate": 1.7194433063388273e-05, "loss": 2.833, "step": 280 }, { "epoch": 0.28491761723700887, "grad_norm": 2.734154224395752, "learning_rate": 1.7171105616399153e-05, "loss": 2.934, "step": 281 }, { "epoch": 0.2859315589353612, "grad_norm": 3.1216416358947754, "learning_rate": 1.714769755618878e-05, "loss": 2.5699, "step": 282 }, { "epoch": 0.28694550063371355, "grad_norm": 2.832775592803955, "learning_rate": 1.712420914589637e-05, "loss": 2.6746, "step": 283 }, { "epoch": 0.2879594423320659, "grad_norm": 2.7044105529785156, "learning_rate": 1.7100640649564396e-05, "loss": 2.8415, "step": 284 }, { "epoch": 0.2889733840304182, "grad_norm": 2.996109962463379, "learning_rate": 1.7076992332135595e-05, "loss": 2.6205, "step": 285 }, { "epoch": 0.2899873257287706, "grad_norm": 2.9617865085601807, "learning_rate": 1.7053264459450023e-05, "loss": 2.4976, "step": 286 }, { "epoch": 0.29100126742712296, "grad_norm": 2.9564125537872314, "learning_rate": 1.7029457298242035e-05, "loss": 2.6155, "step": 287 }, { "epoch": 0.2920152091254753, "grad_norm": 3.1350152492523193, "learning_rate": 1.70055711161373e-05, "loss": 2.829, "step": 288 }, { "epoch": 0.29302915082382763, "grad_norm": 3.3603250980377197, "learning_rate": 1.698160618164979e-05, "loss": 2.7119, "step": 289 }, { "epoch": 0.29404309252217997, "grad_norm": 2.923590898513794, "learning_rate": 1.6957562764178774e-05, "loss": 2.6255, "step": 290 }, { "epoch": 0.2950570342205323, "grad_norm": 3.131751537322998, "learning_rate": 1.6933441134005774e-05, "loss": 2.7487, "step": 291 }, { "epoch": 0.29607097591888465, "grad_norm": 3.136584758758545, "learning_rate": 1.6909241562291522e-05, "loss": 2.6563, "step": 292 }, { "epoch": 0.297084917617237, "grad_norm": 2.8328192234039307, "learning_rate": 1.6884964321072938e-05, "loss": 2.801, "step": 293 }, { "epoch": 0.2980988593155893, "grad_norm": 3.432396173477173, "learning_rate": 1.686060968326005e-05, "loss": 2.5774, "step": 294 }, { "epoch": 0.2991128010139417, "grad_norm": 3.122170925140381, "learning_rate": 1.6836177922632918e-05, "loss": 2.6086, "step": 295 }, { "epoch": 0.30012674271229406, "grad_norm": 2.932734489440918, "learning_rate": 1.681166931383859e-05, "loss": 2.6581, "step": 296 }, { "epoch": 0.3011406844106464, "grad_norm": 3.0569913387298584, "learning_rate": 1.6787084132387987e-05, "loss": 2.7375, "step": 297 }, { "epoch": 0.30215462610899874, "grad_norm": 3.207404613494873, "learning_rate": 1.6762422654652806e-05, "loss": 2.9635, "step": 298 }, { "epoch": 0.3031685678073511, "grad_norm": 3.0299222469329834, "learning_rate": 1.6737685157862428e-05, "loss": 2.7321, "step": 299 }, { "epoch": 0.3041825095057034, "grad_norm": 3.0222506523132324, "learning_rate": 1.6712871920100796e-05, "loss": 2.8171, "step": 300 }, { "epoch": 0.30519645120405575, "grad_norm": 2.854688882827759, "learning_rate": 1.668798322030328e-05, "loss": 2.5802, "step": 301 }, { "epoch": 0.3062103929024081, "grad_norm": 2.8383164405822754, "learning_rate": 1.6663019338253556e-05, "loss": 2.7979, "step": 302 }, { "epoch": 0.30722433460076043, "grad_norm": 3.0571515560150146, "learning_rate": 1.6637980554580447e-05, "loss": 2.7113, "step": 303 }, { "epoch": 0.3082382762991128, "grad_norm": 3.032212018966675, "learning_rate": 1.6612867150754776e-05, "loss": 2.7551, "step": 304 }, { "epoch": 0.30925221799746516, "grad_norm": 3.250274896621704, "learning_rate": 1.6587679409086207e-05, "loss": 2.6444, "step": 305 }, { "epoch": 0.3102661596958175, "grad_norm": 2.826704740524292, "learning_rate": 1.6562417612720055e-05, "loss": 2.6877, "step": 306 }, { "epoch": 0.31128010139416984, "grad_norm": 3.150624990463257, "learning_rate": 1.6537082045634116e-05, "loss": 2.7872, "step": 307 }, { "epoch": 0.3122940430925222, "grad_norm": 3.249372959136963, "learning_rate": 1.6511672992635478e-05, "loss": 2.8034, "step": 308 }, { "epoch": 0.3133079847908745, "grad_norm": 2.992123603820801, "learning_rate": 1.6486190739357307e-05, "loss": 2.7451, "step": 309 }, { "epoch": 0.31432192648922685, "grad_norm": 2.8580946922302246, "learning_rate": 1.6460635572255644e-05, "loss": 2.5405, "step": 310 }, { "epoch": 0.3153358681875792, "grad_norm": 2.7302498817443848, "learning_rate": 1.6435007778606177e-05, "loss": 2.5465, "step": 311 }, { "epoch": 0.31634980988593153, "grad_norm": 2.9869136810302734, "learning_rate": 1.6409307646501032e-05, "loss": 2.852, "step": 312 }, { "epoch": 0.3173637515842839, "grad_norm": 2.967942237854004, "learning_rate": 1.6383535464845507e-05, "loss": 2.4507, "step": 313 }, { "epoch": 0.31837769328263626, "grad_norm": 3.0977964401245117, "learning_rate": 1.635769152335484e-05, "loss": 2.5726, "step": 314 }, { "epoch": 0.3193916349809886, "grad_norm": 2.805619955062866, "learning_rate": 1.6331776112550956e-05, "loss": 2.6916, "step": 315 }, { "epoch": 0.32040557667934094, "grad_norm": 2.807981014251709, "learning_rate": 1.6305789523759186e-05, "loss": 2.6778, "step": 316 }, { "epoch": 0.3214195183776933, "grad_norm": 3.1002237796783447, "learning_rate": 1.6279732049105e-05, "loss": 2.5728, "step": 317 }, { "epoch": 0.3224334600760456, "grad_norm": 3.0552313327789307, "learning_rate": 1.6253603981510742e-05, "loss": 2.7891, "step": 318 }, { "epoch": 0.32344740177439796, "grad_norm": 3.123044013977051, "learning_rate": 1.6227405614692295e-05, "loss": 2.5147, "step": 319 }, { "epoch": 0.3244613434727503, "grad_norm": 3.1019504070281982, "learning_rate": 1.6201137243155815e-05, "loss": 2.6905, "step": 320 }, { "epoch": 0.32547528517110264, "grad_norm": 2.9532058238983154, "learning_rate": 1.617479916219441e-05, "loss": 2.9354, "step": 321 }, { "epoch": 0.32648922686945503, "grad_norm": 2.9724395275115967, "learning_rate": 1.614839166788481e-05, "loss": 2.3712, "step": 322 }, { "epoch": 0.32750316856780737, "grad_norm": 3.3524832725524902, "learning_rate": 1.6121915057084064e-05, "loss": 2.8975, "step": 323 }, { "epoch": 0.3285171102661597, "grad_norm": 3.259046792984009, "learning_rate": 1.609536962742617e-05, "loss": 2.6001, "step": 324 }, { "epoch": 0.32953105196451205, "grad_norm": 2.8253602981567383, "learning_rate": 1.606875567731876e-05, "loss": 2.794, "step": 325 }, { "epoch": 0.3305449936628644, "grad_norm": 2.986966609954834, "learning_rate": 1.6042073505939718e-05, "loss": 2.6207, "step": 326 }, { "epoch": 0.3315589353612167, "grad_norm": 2.9867730140686035, "learning_rate": 1.6015323413233838e-05, "loss": 2.8266, "step": 327 }, { "epoch": 0.33257287705956906, "grad_norm": 2.8082540035247803, "learning_rate": 1.598850569990944e-05, "loss": 2.5946, "step": 328 }, { "epoch": 0.3335868187579214, "grad_norm": 2.93464732170105, "learning_rate": 1.5961620667434997e-05, "loss": 2.6015, "step": 329 }, { "epoch": 0.33460076045627374, "grad_norm": 2.888319969177246, "learning_rate": 1.593466861803575e-05, "loss": 2.6121, "step": 330 }, { "epoch": 0.33561470215462613, "grad_norm": 2.75567889213562, "learning_rate": 1.5907649854690292e-05, "loss": 2.716, "step": 331 }, { "epoch": 0.33662864385297847, "grad_norm": 2.6718239784240723, "learning_rate": 1.5880564681127172e-05, "loss": 2.6195, "step": 332 }, { "epoch": 0.3376425855513308, "grad_norm": 2.933192253112793, "learning_rate": 1.58534134018215e-05, "loss": 2.8557, "step": 333 }, { "epoch": 0.33865652724968315, "grad_norm": 4.560988903045654, "learning_rate": 1.5826196321991484e-05, "loss": 2.7728, "step": 334 }, { "epoch": 0.3396704689480355, "grad_norm": 2.9383349418640137, "learning_rate": 1.5798913747595038e-05, "loss": 2.5062, "step": 335 }, { "epoch": 0.3406844106463878, "grad_norm": 3.134274482727051, "learning_rate": 1.5771565985326323e-05, "loss": 2.5433, "step": 336 }, { "epoch": 0.34169835234474016, "grad_norm": 2.9582736492156982, "learning_rate": 1.57441533426123e-05, "loss": 2.777, "step": 337 }, { "epoch": 0.3427122940430925, "grad_norm": 3.3106932640075684, "learning_rate": 1.5716676127609277e-05, "loss": 2.5834, "step": 338 }, { "epoch": 0.34372623574144484, "grad_norm": 2.8983476161956787, "learning_rate": 1.568913464919944e-05, "loss": 2.5572, "step": 339 }, { "epoch": 0.34474017743979724, "grad_norm": 3.2694075107574463, "learning_rate": 1.5661529216987393e-05, "loss": 2.4801, "step": 340 }, { "epoch": 0.3457541191381496, "grad_norm": 3.032731056213379, "learning_rate": 1.563386014129667e-05, "loss": 2.8144, "step": 341 }, { "epoch": 0.3467680608365019, "grad_norm": 2.8788082599639893, "learning_rate": 1.5606127733166237e-05, "loss": 2.7998, "step": 342 }, { "epoch": 0.34778200253485425, "grad_norm": 2.8466122150421143, "learning_rate": 1.5578332304347016e-05, "loss": 2.7319, "step": 343 }, { "epoch": 0.3487959442332066, "grad_norm": 3.006892442703247, "learning_rate": 1.5550474167298364e-05, "loss": 2.7248, "step": 344 }, { "epoch": 0.34980988593155893, "grad_norm": 2.8438527584075928, "learning_rate": 1.5522553635184567e-05, "loss": 2.7117, "step": 345 }, { "epoch": 0.35082382762991127, "grad_norm": 3.038827896118164, "learning_rate": 1.549457102187131e-05, "loss": 2.6968, "step": 346 }, { "epoch": 0.3518377693282636, "grad_norm": 3.1003973484039307, "learning_rate": 1.5466526641922174e-05, "loss": 2.5117, "step": 347 }, { "epoch": 0.35285171102661594, "grad_norm": 2.9051380157470703, "learning_rate": 1.5438420810595073e-05, "loss": 2.5873, "step": 348 }, { "epoch": 0.35386565272496834, "grad_norm": 2.885514259338379, "learning_rate": 1.5410253843838717e-05, "loss": 3.1226, "step": 349 }, { "epoch": 0.3548795944233207, "grad_norm": 2.6996588706970215, "learning_rate": 1.538202605828907e-05, "loss": 2.7712, "step": 350 }, { "epoch": 0.355893536121673, "grad_norm": 2.927683115005493, "learning_rate": 1.5353737771265785e-05, "loss": 2.5532, "step": 351 }, { "epoch": 0.35690747782002535, "grad_norm": 3.2832837104797363, "learning_rate": 1.532538930076863e-05, "loss": 2.753, "step": 352 }, { "epoch": 0.3579214195183777, "grad_norm": 3.019700765609741, "learning_rate": 1.5296980965473918e-05, "loss": 2.7967, "step": 353 }, { "epoch": 0.35893536121673003, "grad_norm": 2.9347846508026123, "learning_rate": 1.5268513084730935e-05, "loss": 2.7381, "step": 354 }, { "epoch": 0.35994930291508237, "grad_norm": 3.088667392730713, "learning_rate": 1.5239985978558333e-05, "loss": 2.5695, "step": 355 }, { "epoch": 0.3609632446134347, "grad_norm": 2.810241460800171, "learning_rate": 1.521139996764054e-05, "loss": 2.7083, "step": 356 }, { "epoch": 0.36197718631178705, "grad_norm": 2.9103872776031494, "learning_rate": 1.5182755373324162e-05, "loss": 2.7304, "step": 357 }, { "epoch": 0.36299112801013944, "grad_norm": 2.860936403274536, "learning_rate": 1.5154052517614361e-05, "loss": 2.7048, "step": 358 }, { "epoch": 0.3640050697084918, "grad_norm": 2.7018895149230957, "learning_rate": 1.512529172317123e-05, "loss": 2.7032, "step": 359 }, { "epoch": 0.3650190114068441, "grad_norm": 2.985334873199463, "learning_rate": 1.509647331330619e-05, "loss": 2.6939, "step": 360 }, { "epoch": 0.36603295310519646, "grad_norm": 2.89749813079834, "learning_rate": 1.506759761197833e-05, "loss": 2.6779, "step": 361 }, { "epoch": 0.3670468948035488, "grad_norm": 3.2000341415405273, "learning_rate": 1.5038664943790768e-05, "loss": 2.6007, "step": 362 }, { "epoch": 0.36806083650190113, "grad_norm": 2.913217544555664, "learning_rate": 1.5009675633987027e-05, "loss": 2.3883, "step": 363 }, { "epoch": 0.3690747782002535, "grad_norm": 3.0969278812408447, "learning_rate": 1.4980630008447343e-05, "loss": 2.7225, "step": 364 }, { "epoch": 0.3700887198986058, "grad_norm": 2.8502883911132812, "learning_rate": 1.4951528393685033e-05, "loss": 2.7935, "step": 365 }, { "epoch": 0.37110266159695815, "grad_norm": 3.0395283699035645, "learning_rate": 1.49223711168428e-05, "loss": 2.6212, "step": 366 }, { "epoch": 0.37211660329531054, "grad_norm": 2.8926784992218018, "learning_rate": 1.4893158505689071e-05, "loss": 2.7873, "step": 367 }, { "epoch": 0.3731305449936629, "grad_norm": 3.2163937091827393, "learning_rate": 1.4863890888614314e-05, "loss": 2.7154, "step": 368 }, { "epoch": 0.3741444866920152, "grad_norm": 2.7381045818328857, "learning_rate": 1.483456859462733e-05, "loss": 2.6874, "step": 369 }, { "epoch": 0.37515842839036756, "grad_norm": 2.733754873275757, "learning_rate": 1.480519195335157e-05, "loss": 2.5197, "step": 370 }, { "epoch": 0.3761723700887199, "grad_norm": 2.765723705291748, "learning_rate": 1.4775761295021418e-05, "loss": 2.6769, "step": 371 }, { "epoch": 0.37718631178707224, "grad_norm": 2.723877191543579, "learning_rate": 1.47462769504785e-05, "loss": 2.9282, "step": 372 }, { "epoch": 0.3782002534854246, "grad_norm": 3.054982900619507, "learning_rate": 1.4716739251167931e-05, "loss": 2.9797, "step": 373 }, { "epoch": 0.3792141951837769, "grad_norm": 2.886594295501709, "learning_rate": 1.4687148529134621e-05, "loss": 2.806, "step": 374 }, { "epoch": 0.38022813688212925, "grad_norm": 3.0350804328918457, "learning_rate": 1.4657505117019523e-05, "loss": 2.6211, "step": 375 }, { "epoch": 0.38124207858048165, "grad_norm": 2.7764170169830322, "learning_rate": 1.4627809348055908e-05, "loss": 2.7099, "step": 376 }, { "epoch": 0.382256020278834, "grad_norm": 2.9754507541656494, "learning_rate": 1.4598061556065598e-05, "loss": 2.6209, "step": 377 }, { "epoch": 0.3832699619771863, "grad_norm": 3.0619449615478516, "learning_rate": 1.4568262075455237e-05, "loss": 2.6551, "step": 378 }, { "epoch": 0.38428390367553866, "grad_norm": 2.7044217586517334, "learning_rate": 1.4538411241212518e-05, "loss": 2.529, "step": 379 }, { "epoch": 0.385297845373891, "grad_norm": 2.4933485984802246, "learning_rate": 1.4508509388902421e-05, "loss": 2.6247, "step": 380 }, { "epoch": 0.38631178707224334, "grad_norm": 2.8276021480560303, "learning_rate": 1.4478556854663435e-05, "loss": 2.6108, "step": 381 }, { "epoch": 0.3873257287705957, "grad_norm": 2.8554747104644775, "learning_rate": 1.444855397520379e-05, "loss": 2.7067, "step": 382 }, { "epoch": 0.388339670468948, "grad_norm": 2.901643753051758, "learning_rate": 1.4418501087797667e-05, "loss": 2.5073, "step": 383 }, { "epoch": 0.38935361216730036, "grad_norm": 2.9580893516540527, "learning_rate": 1.4388398530281403e-05, "loss": 2.7195, "step": 384 }, { "epoch": 0.39036755386565275, "grad_norm": 2.950740337371826, "learning_rate": 1.4358246641049696e-05, "loss": 2.5772, "step": 385 }, { "epoch": 0.3913814955640051, "grad_norm": 2.9490175247192383, "learning_rate": 1.4328045759051805e-05, "loss": 2.7675, "step": 386 }, { "epoch": 0.3923954372623574, "grad_norm": 2.7582757472991943, "learning_rate": 1.4297796223787734e-05, "loss": 2.8246, "step": 387 }, { "epoch": 0.39340937896070977, "grad_norm": 3.29480242729187, "learning_rate": 1.4267498375304417e-05, "loss": 2.5724, "step": 388 }, { "epoch": 0.3944233206590621, "grad_norm": 2.785078287124634, "learning_rate": 1.4237152554191889e-05, "loss": 2.7085, "step": 389 }, { "epoch": 0.39543726235741444, "grad_norm": 2.72640323638916, "learning_rate": 1.4206759101579481e-05, "loss": 2.8608, "step": 390 }, { "epoch": 0.3964512040557668, "grad_norm": 2.696939706802368, "learning_rate": 1.4176318359131955e-05, "loss": 2.7745, "step": 391 }, { "epoch": 0.3974651457541191, "grad_norm": 3.107379674911499, "learning_rate": 1.414583066904568e-05, "loss": 2.529, "step": 392 }, { "epoch": 0.39847908745247146, "grad_norm": 2.836038589477539, "learning_rate": 1.411529637404478e-05, "loss": 2.5382, "step": 393 }, { "epoch": 0.39949302915082385, "grad_norm": 2.7665674686431885, "learning_rate": 1.4084715817377292e-05, "loss": 2.7435, "step": 394 }, { "epoch": 0.4005069708491762, "grad_norm": 3.098053455352783, "learning_rate": 1.4054089342811286e-05, "loss": 2.728, "step": 395 }, { "epoch": 0.40152091254752853, "grad_norm": 3.359023332595825, "learning_rate": 1.4023417294631019e-05, "loss": 2.4446, "step": 396 }, { "epoch": 0.40253485424588087, "grad_norm": 2.905782461166382, "learning_rate": 1.3992700017633063e-05, "loss": 2.5065, "step": 397 }, { "epoch": 0.4035487959442332, "grad_norm": 3.0287387371063232, "learning_rate": 1.3961937857122418e-05, "loss": 2.7894, "step": 398 }, { "epoch": 0.40456273764258555, "grad_norm": 2.878178358078003, "learning_rate": 1.3931131158908644e-05, "loss": 2.758, "step": 399 }, { "epoch": 0.4055766793409379, "grad_norm": 2.683164596557617, "learning_rate": 1.3900280269301957e-05, "loss": 2.7725, "step": 400 }, { "epoch": 0.4065906210392902, "grad_norm": 2.802175521850586, "learning_rate": 1.3869385535109358e-05, "loss": 2.8893, "step": 401 }, { "epoch": 0.40760456273764256, "grad_norm": 2.7916531562805176, "learning_rate": 1.3838447303630713e-05, "loss": 2.9633, "step": 402 }, { "epoch": 0.40861850443599496, "grad_norm": 3.0303285121917725, "learning_rate": 1.3807465922654863e-05, "loss": 2.5742, "step": 403 }, { "epoch": 0.4096324461343473, "grad_norm": 2.9529471397399902, "learning_rate": 1.3776441740455706e-05, "loss": 2.6557, "step": 404 }, { "epoch": 0.41064638783269963, "grad_norm": 2.719038486480713, "learning_rate": 1.374537510578829e-05, "loss": 2.6693, "step": 405 }, { "epoch": 0.41166032953105197, "grad_norm": 2.768009901046753, "learning_rate": 1.3714266367884883e-05, "loss": 2.8518, "step": 406 }, { "epoch": 0.4126742712294043, "grad_norm": 2.946180582046509, "learning_rate": 1.3683115876451054e-05, "loss": 2.5067, "step": 407 }, { "epoch": 0.41368821292775665, "grad_norm": 3.0021729469299316, "learning_rate": 1.3651923981661741e-05, "loss": 2.8727, "step": 408 }, { "epoch": 0.414702154626109, "grad_norm": 3.17314076423645, "learning_rate": 1.3620691034157314e-05, "loss": 2.4562, "step": 409 }, { "epoch": 0.4157160963244613, "grad_norm": 2.908395528793335, "learning_rate": 1.358941738503963e-05, "loss": 2.7654, "step": 410 }, { "epoch": 0.41673003802281366, "grad_norm": 3.0189144611358643, "learning_rate": 1.3558103385868087e-05, "loss": 2.8481, "step": 411 }, { "epoch": 0.41774397972116606, "grad_norm": 2.8879098892211914, "learning_rate": 1.352674938865568e-05, "loss": 2.629, "step": 412 }, { "epoch": 0.4187579214195184, "grad_norm": 2.8246898651123047, "learning_rate": 1.3495355745865038e-05, "loss": 2.6649, "step": 413 }, { "epoch": 0.41977186311787074, "grad_norm": 2.962284564971924, "learning_rate": 1.3463922810404448e-05, "loss": 2.5616, "step": 414 }, { "epoch": 0.4207858048162231, "grad_norm": 2.845741033554077, "learning_rate": 1.3432450935623922e-05, "loss": 2.7799, "step": 415 }, { "epoch": 0.4217997465145754, "grad_norm": 2.6955134868621826, "learning_rate": 1.3400940475311193e-05, "loss": 2.7114, "step": 416 }, { "epoch": 0.42281368821292775, "grad_norm": 2.7694082260131836, "learning_rate": 1.3369391783687742e-05, "loss": 2.6646, "step": 417 }, { "epoch": 0.4238276299112801, "grad_norm": 3.0028157234191895, "learning_rate": 1.3337805215404837e-05, "loss": 2.7271, "step": 418 }, { "epoch": 0.42484157160963243, "grad_norm": 3.1340060234069824, "learning_rate": 1.3306181125539528e-05, "loss": 2.7531, "step": 419 }, { "epoch": 0.42585551330798477, "grad_norm": 3.0588529109954834, "learning_rate": 1.3274519869590656e-05, "loss": 2.629, "step": 420 }, { "epoch": 0.42686945500633716, "grad_norm": 2.9157087802886963, "learning_rate": 1.3242821803474861e-05, "loss": 2.5446, "step": 421 }, { "epoch": 0.4278833967046895, "grad_norm": 3.051769256591797, "learning_rate": 1.3211087283522586e-05, "loss": 2.7211, "step": 422 }, { "epoch": 0.42889733840304184, "grad_norm": 2.8915231227874756, "learning_rate": 1.3179316666474063e-05, "loss": 2.5781, "step": 423 }, { "epoch": 0.4299112801013942, "grad_norm": 3.18194842338562, "learning_rate": 1.3147510309475301e-05, "loss": 2.8725, "step": 424 }, { "epoch": 0.4309252217997465, "grad_norm": 3.0383052825927734, "learning_rate": 1.3115668570074083e-05, "loss": 2.6157, "step": 425 }, { "epoch": 0.43193916349809885, "grad_norm": 3.316793203353882, "learning_rate": 1.308379180621594e-05, "loss": 2.5316, "step": 426 }, { "epoch": 0.4329531051964512, "grad_norm": 2.822645664215088, "learning_rate": 1.3051880376240117e-05, "loss": 2.471, "step": 427 }, { "epoch": 0.43396704689480353, "grad_norm": 2.7731168270111084, "learning_rate": 1.3019934638875565e-05, "loss": 2.4718, "step": 428 }, { "epoch": 0.43498098859315587, "grad_norm": 2.7981114387512207, "learning_rate": 1.298795495323689e-05, "loss": 2.6722, "step": 429 }, { "epoch": 0.43599493029150826, "grad_norm": 2.8708651065826416, "learning_rate": 1.2955941678820332e-05, "loss": 2.8799, "step": 430 }, { "epoch": 0.4370088719898606, "grad_norm": 2.806706666946411, "learning_rate": 1.292389517549971e-05, "loss": 2.6245, "step": 431 }, { "epoch": 0.43802281368821294, "grad_norm": 2.9992716312408447, "learning_rate": 1.2891815803522378e-05, "loss": 2.6867, "step": 432 }, { "epoch": 0.4390367553865653, "grad_norm": 2.9060275554656982, "learning_rate": 1.2859703923505194e-05, "loss": 2.5628, "step": 433 }, { "epoch": 0.4400506970849176, "grad_norm": 2.9179909229278564, "learning_rate": 1.2827559896430437e-05, "loss": 2.7091, "step": 434 }, { "epoch": 0.44106463878326996, "grad_norm": 2.7098734378814697, "learning_rate": 1.279538408364177e-05, "loss": 2.6439, "step": 435 }, { "epoch": 0.4420785804816223, "grad_norm": 2.9812943935394287, "learning_rate": 1.276317684684017e-05, "loss": 2.8656, "step": 436 }, { "epoch": 0.44309252217997463, "grad_norm": 2.730379581451416, "learning_rate": 1.2730938548079873e-05, "loss": 2.7245, "step": 437 }, { "epoch": 0.444106463878327, "grad_norm": 2.8220674991607666, "learning_rate": 1.2698669549764272e-05, "loss": 2.7681, "step": 438 }, { "epoch": 0.44512040557667937, "grad_norm": 2.7935733795166016, "learning_rate": 1.266637021464189e-05, "loss": 2.581, "step": 439 }, { "epoch": 0.4461343472750317, "grad_norm": 2.727238178253174, "learning_rate": 1.2634040905802267e-05, "loss": 2.4567, "step": 440 }, { "epoch": 0.44714828897338404, "grad_norm": 3.0209293365478516, "learning_rate": 1.260168198667189e-05, "loss": 2.5923, "step": 441 }, { "epoch": 0.4481622306717364, "grad_norm": 3.109890937805176, "learning_rate": 1.2569293821010109e-05, "loss": 2.546, "step": 442 }, { "epoch": 0.4491761723700887, "grad_norm": 2.8236355781555176, "learning_rate": 1.253687677290504e-05, "loss": 2.7402, "step": 443 }, { "epoch": 0.45019011406844106, "grad_norm": 2.7868268489837646, "learning_rate": 1.2504431206769487e-05, "loss": 2.561, "step": 444 }, { "epoch": 0.4512040557667934, "grad_norm": 3.127213954925537, "learning_rate": 1.247195748733683e-05, "loss": 2.6075, "step": 445 }, { "epoch": 0.45221799746514574, "grad_norm": 2.916252374649048, "learning_rate": 1.2439455979656931e-05, "loss": 2.6565, "step": 446 }, { "epoch": 0.4532319391634981, "grad_norm": 2.737009286880493, "learning_rate": 1.2406927049092034e-05, "loss": 2.565, "step": 447 }, { "epoch": 0.45424588086185047, "grad_norm": 3.0931363105773926, "learning_rate": 1.2374371061312655e-05, "loss": 2.6302, "step": 448 }, { "epoch": 0.4552598225602028, "grad_norm": 2.862377166748047, "learning_rate": 1.2341788382293467e-05, "loss": 2.8832, "step": 449 }, { "epoch": 0.45627376425855515, "grad_norm": 2.9104745388031006, "learning_rate": 1.2309179378309188e-05, "loss": 2.4398, "step": 450 }, { "epoch": 0.4572877059569075, "grad_norm": 2.879220485687256, "learning_rate": 1.2276544415930476e-05, "loss": 2.733, "step": 451 }, { "epoch": 0.4583016476552598, "grad_norm": 2.7797646522521973, "learning_rate": 1.2243883862019787e-05, "loss": 2.7244, "step": 452 }, { "epoch": 0.45931558935361216, "grad_norm": 2.9330852031707764, "learning_rate": 1.2211198083727262e-05, "loss": 2.9154, "step": 453 }, { "epoch": 0.4603295310519645, "grad_norm": 3.2787609100341797, "learning_rate": 1.2178487448486607e-05, "loss": 2.7193, "step": 454 }, { "epoch": 0.46134347275031684, "grad_norm": 3.0352675914764404, "learning_rate": 1.2145752324010948e-05, "loss": 2.4823, "step": 455 }, { "epoch": 0.4623574144486692, "grad_norm": 2.8447976112365723, "learning_rate": 1.2112993078288702e-05, "loss": 2.5812, "step": 456 }, { "epoch": 0.4633713561470216, "grad_norm": 2.8668317794799805, "learning_rate": 1.2080210079579452e-05, "loss": 2.5691, "step": 457 }, { "epoch": 0.4643852978453739, "grad_norm": 2.8658692836761475, "learning_rate": 1.2047403696409787e-05, "loss": 2.4761, "step": 458 }, { "epoch": 0.46539923954372625, "grad_norm": 2.8215885162353516, "learning_rate": 1.2014574297569182e-05, "loss": 2.7344, "step": 459 }, { "epoch": 0.4664131812420786, "grad_norm": 3.016486644744873, "learning_rate": 1.1981722252105827e-05, "loss": 2.7488, "step": 460 }, { "epoch": 0.46742712294043093, "grad_norm": 2.955415964126587, "learning_rate": 1.1948847929322498e-05, "loss": 2.9456, "step": 461 }, { "epoch": 0.46844106463878327, "grad_norm": 2.714385986328125, "learning_rate": 1.1915951698772403e-05, "loss": 2.6273, "step": 462 }, { "epoch": 0.4694550063371356, "grad_norm": 2.84726881980896, "learning_rate": 1.1883033930255018e-05, "loss": 2.6909, "step": 463 }, { "epoch": 0.47046894803548794, "grad_norm": 2.9898338317871094, "learning_rate": 1.1850094993811936e-05, "loss": 2.5776, "step": 464 }, { "epoch": 0.4714828897338403, "grad_norm": 2.896883964538574, "learning_rate": 1.1817135259722707e-05, "loss": 2.7808, "step": 465 }, { "epoch": 0.4724968314321927, "grad_norm": 3.1968889236450195, "learning_rate": 1.1784155098500682e-05, "loss": 2.3759, "step": 466 }, { "epoch": 0.473510773130545, "grad_norm": 2.7873728275299072, "learning_rate": 1.1751154880888835e-05, "loss": 2.4607, "step": 467 }, { "epoch": 0.47452471482889735, "grad_norm": 3.0125274658203125, "learning_rate": 1.17181349778556e-05, "loss": 2.6283, "step": 468 }, { "epoch": 0.4755386565272497, "grad_norm": 2.9340808391571045, "learning_rate": 1.1685095760590706e-05, "loss": 2.8088, "step": 469 }, { "epoch": 0.47655259822560203, "grad_norm": 2.9202420711517334, "learning_rate": 1.1652037600501007e-05, "loss": 2.7714, "step": 470 }, { "epoch": 0.47756653992395437, "grad_norm": 3.133967638015747, "learning_rate": 1.1618960869206287e-05, "loss": 2.247, "step": 471 }, { "epoch": 0.4785804816223067, "grad_norm": 2.8348443508148193, "learning_rate": 1.1585865938535106e-05, "loss": 2.7938, "step": 472 }, { "epoch": 0.47959442332065905, "grad_norm": 2.7735393047332764, "learning_rate": 1.1552753180520612e-05, "loss": 2.8799, "step": 473 }, { "epoch": 0.4806083650190114, "grad_norm": 2.82151198387146, "learning_rate": 1.1519622967396347e-05, "loss": 2.4982, "step": 474 }, { "epoch": 0.4816223067173637, "grad_norm": 2.670712471008301, "learning_rate": 1.1486475671592084e-05, "loss": 2.5624, "step": 475 }, { "epoch": 0.4826362484157161, "grad_norm": 2.903679370880127, "learning_rate": 1.1453311665729618e-05, "loss": 2.6059, "step": 476 }, { "epoch": 0.48365019011406846, "grad_norm": 2.8284971714019775, "learning_rate": 1.1420131322618601e-05, "loss": 2.5285, "step": 477 }, { "epoch": 0.4846641318124208, "grad_norm": 3.5497357845306396, "learning_rate": 1.138693501525233e-05, "loss": 2.5756, "step": 478 }, { "epoch": 0.48567807351077313, "grad_norm": 3.3905792236328125, "learning_rate": 1.135372311680356e-05, "loss": 2.584, "step": 479 }, { "epoch": 0.4866920152091255, "grad_norm": 3.1427557468414307, "learning_rate": 1.1320496000620325e-05, "loss": 2.677, "step": 480 }, { "epoch": 0.4877059569074778, "grad_norm": 2.9492239952087402, "learning_rate": 1.128725404022171e-05, "loss": 2.7053, "step": 481 }, { "epoch": 0.48871989860583015, "grad_norm": 2.99006986618042, "learning_rate": 1.1253997609293684e-05, "loss": 2.7686, "step": 482 }, { "epoch": 0.4897338403041825, "grad_norm": 2.840709924697876, "learning_rate": 1.122072708168487e-05, "loss": 2.8237, "step": 483 }, { "epoch": 0.4907477820025348, "grad_norm": 2.6475729942321777, "learning_rate": 1.1187442831402378e-05, "loss": 2.7403, "step": 484 }, { "epoch": 0.4917617237008872, "grad_norm": 2.9385244846343994, "learning_rate": 1.1154145232607558e-05, "loss": 2.487, "step": 485 }, { "epoch": 0.49277566539923956, "grad_norm": 3.061269760131836, "learning_rate": 1.1120834659611832e-05, "loss": 2.3668, "step": 486 }, { "epoch": 0.4937896070975919, "grad_norm": 2.8122615814208984, "learning_rate": 1.1087511486872461e-05, "loss": 2.4546, "step": 487 }, { "epoch": 0.49480354879594424, "grad_norm": 2.9320120811462402, "learning_rate": 1.1054176088988352e-05, "loss": 2.6993, "step": 488 }, { "epoch": 0.4958174904942966, "grad_norm": 3.0139100551605225, "learning_rate": 1.1020828840695836e-05, "loss": 2.7321, "step": 489 }, { "epoch": 0.4968314321926489, "grad_norm": 2.842785120010376, "learning_rate": 1.0987470116864454e-05, "loss": 2.7172, "step": 490 }, { "epoch": 0.49784537389100125, "grad_norm": 2.6393532752990723, "learning_rate": 1.0954100292492758e-05, "loss": 2.816, "step": 491 }, { "epoch": 0.4988593155893536, "grad_norm": 2.8561477661132812, "learning_rate": 1.0920719742704071e-05, "loss": 2.8228, "step": 492 }, { "epoch": 0.49987325728770593, "grad_norm": 2.7492289543151855, "learning_rate": 1.0887328842742307e-05, "loss": 2.6292, "step": 493 }, { "epoch": 0.5008871989860583, "grad_norm": 2.8030145168304443, "learning_rate": 1.0853927967967705e-05, "loss": 2.7269, "step": 494 }, { "epoch": 0.5019011406844106, "grad_norm": 2.7845194339752197, "learning_rate": 1.0820517493852655e-05, "loss": 2.5418, "step": 495 }, { "epoch": 0.502915082382763, "grad_norm": 2.990659475326538, "learning_rate": 1.0787097795977447e-05, "loss": 2.8466, "step": 496 }, { "epoch": 0.5039290240811153, "grad_norm": 2.703700304031372, "learning_rate": 1.0753669250026062e-05, "loss": 2.7314, "step": 497 }, { "epoch": 0.5049429657794677, "grad_norm": 2.9919204711914062, "learning_rate": 1.0720232231781944e-05, "loss": 2.6237, "step": 498 }, { "epoch": 0.5059569074778201, "grad_norm": 2.7852721214294434, "learning_rate": 1.0686787117123776e-05, "loss": 2.7113, "step": 499 }, { "epoch": 0.5069708491761724, "grad_norm": 3.1660399436950684, "learning_rate": 1.0653334282021261e-05, "loss": 2.5095, "step": 500 }, { "epoch": 0.5079847908745247, "grad_norm": 2.977863073348999, "learning_rate": 1.0619874102530886e-05, "loss": 2.6218, "step": 501 }, { "epoch": 0.5089987325728771, "grad_norm": 3.039355993270874, "learning_rate": 1.0586406954791702e-05, "loss": 2.5317, "step": 502 }, { "epoch": 0.5100126742712294, "grad_norm": 2.98754620552063, "learning_rate": 1.0552933215021088e-05, "loss": 2.6559, "step": 503 }, { "epoch": 0.5110266159695818, "grad_norm": 3.1123383045196533, "learning_rate": 1.0519453259510535e-05, "loss": 2.6153, "step": 504 }, { "epoch": 0.5120405576679341, "grad_norm": 2.846510887145996, "learning_rate": 1.0485967464621401e-05, "loss": 2.7191, "step": 505 }, { "epoch": 0.5130544993662864, "grad_norm": 2.6948962211608887, "learning_rate": 1.0452476206780686e-05, "loss": 2.6106, "step": 506 }, { "epoch": 0.5140684410646388, "grad_norm": 2.7842648029327393, "learning_rate": 1.041897986247681e-05, "loss": 2.871, "step": 507 }, { "epoch": 0.5150823827629911, "grad_norm": 2.8970916271209717, "learning_rate": 1.0385478808255358e-05, "loss": 2.5389, "step": 508 }, { "epoch": 0.5160963244613435, "grad_norm": 3.109102249145508, "learning_rate": 1.0351973420714878e-05, "loss": 2.4805, "step": 509 }, { "epoch": 0.5171102661596958, "grad_norm": 2.8477885723114014, "learning_rate": 1.031846407650261e-05, "loss": 2.7004, "step": 510 }, { "epoch": 0.5181242078580481, "grad_norm": 3.3832929134368896, "learning_rate": 1.0284951152310292e-05, "loss": 2.409, "step": 511 }, { "epoch": 0.5191381495564005, "grad_norm": 2.941394329071045, "learning_rate": 1.0251435024869894e-05, "loss": 2.5179, "step": 512 }, { "epoch": 0.5201520912547528, "grad_norm": 2.7577157020568848, "learning_rate": 1.0217916070949405e-05, "loss": 2.6069, "step": 513 }, { "epoch": 0.5211660329531052, "grad_norm": 3.035717487335205, "learning_rate": 1.0184394667348572e-05, "loss": 2.2385, "step": 514 }, { "epoch": 0.5221799746514575, "grad_norm": 2.8246779441833496, "learning_rate": 1.0150871190894693e-05, "loss": 2.8377, "step": 515 }, { "epoch": 0.5231939163498099, "grad_norm": 2.863114356994629, "learning_rate": 1.0117346018438367e-05, "loss": 2.8131, "step": 516 }, { "epoch": 0.5242078580481623, "grad_norm": 3.119429588317871, "learning_rate": 1.008381952684925e-05, "loss": 2.5764, "step": 517 }, { "epoch": 0.5252217997465146, "grad_norm": 2.976614236831665, "learning_rate": 1.0050292093011835e-05, "loss": 2.4699, "step": 518 }, { "epoch": 0.526235741444867, "grad_norm": 2.798595666885376, "learning_rate": 1.0016764093821203e-05, "loss": 2.6019, "step": 519 }, { "epoch": 0.5272496831432193, "grad_norm": 2.6253113746643066, "learning_rate": 9.983235906178798e-06, "loss": 2.6515, "step": 520 }, { "epoch": 0.5282636248415716, "grad_norm": 2.9238436222076416, "learning_rate": 9.949707906988165e-06, "loss": 2.6297, "step": 521 }, { "epoch": 0.529277566539924, "grad_norm": 2.8237082958221436, "learning_rate": 9.916180473150753e-06, "loss": 2.7979, "step": 522 }, { "epoch": 0.5302915082382763, "grad_norm": 3.0830626487731934, "learning_rate": 9.882653981561638e-06, "loss": 2.5663, "step": 523 }, { "epoch": 0.5313054499366286, "grad_norm": 2.914485216140747, "learning_rate": 9.849128809105309e-06, "loss": 2.6301, "step": 524 }, { "epoch": 0.532319391634981, "grad_norm": 3.0977110862731934, "learning_rate": 9.815605332651433e-06, "loss": 2.5711, "step": 525 }, { "epoch": 0.5333333333333333, "grad_norm": 3.0849609375, "learning_rate": 9.782083929050601e-06, "loss": 2.6879, "step": 526 }, { "epoch": 0.5343472750316857, "grad_norm": 3.0231521129608154, "learning_rate": 9.748564975130106e-06, "loss": 2.7279, "step": 527 }, { "epoch": 0.535361216730038, "grad_norm": 2.895653247833252, "learning_rate": 9.71504884768971e-06, "loss": 2.436, "step": 528 }, { "epoch": 0.5363751584283903, "grad_norm": 3.167012929916382, "learning_rate": 9.681535923497394e-06, "loss": 2.4616, "step": 529 }, { "epoch": 0.5373891001267427, "grad_norm": 3.1906981468200684, "learning_rate": 9.648026579285125e-06, "loss": 2.7383, "step": 530 }, { "epoch": 0.538403041825095, "grad_norm": 3.151561975479126, "learning_rate": 9.614521191744644e-06, "loss": 2.7495, "step": 531 }, { "epoch": 0.5394169835234474, "grad_norm": 2.9482996463775635, "learning_rate": 9.581020137523192e-06, "loss": 2.6012, "step": 532 }, { "epoch": 0.5404309252217997, "grad_norm": 2.8822813034057617, "learning_rate": 9.547523793219315e-06, "loss": 2.5973, "step": 533 }, { "epoch": 0.5414448669201521, "grad_norm": 3.1009838581085205, "learning_rate": 9.514032535378604e-06, "loss": 2.6613, "step": 534 }, { "epoch": 0.5424588086185045, "grad_norm": 3.2803237438201904, "learning_rate": 9.480546740489468e-06, "loss": 2.5809, "step": 535 }, { "epoch": 0.5434727503168568, "grad_norm": 2.8916573524475098, "learning_rate": 9.447066784978914e-06, "loss": 2.7318, "step": 536 }, { "epoch": 0.5444866920152092, "grad_norm": 2.8549203872680664, "learning_rate": 9.413593045208303e-06, "loss": 2.6984, "step": 537 }, { "epoch": 0.5455006337135615, "grad_norm": 2.9765243530273438, "learning_rate": 9.380125897469116e-06, "loss": 2.6687, "step": 538 }, { "epoch": 0.5465145754119138, "grad_norm": 3.034773588180542, "learning_rate": 9.346665717978742e-06, "loss": 2.4404, "step": 539 }, { "epoch": 0.5475285171102662, "grad_norm": 3.125175714492798, "learning_rate": 9.313212882876228e-06, "loss": 2.3855, "step": 540 }, { "epoch": 0.5485424588086185, "grad_norm": 2.9196765422821045, "learning_rate": 9.279767768218058e-06, "loss": 2.7998, "step": 541 }, { "epoch": 0.5495564005069709, "grad_norm": 2.6196236610412598, "learning_rate": 9.246330749973943e-06, "loss": 2.7261, "step": 542 }, { "epoch": 0.5505703422053232, "grad_norm": 2.931138038635254, "learning_rate": 9.212902204022556e-06, "loss": 2.7242, "step": 543 }, { "epoch": 0.5515842839036755, "grad_norm": 3.1061699390411377, "learning_rate": 9.179482506147346e-06, "loss": 2.5819, "step": 544 }, { "epoch": 0.5525982256020279, "grad_norm": 2.7744109630584717, "learning_rate": 9.146072032032298e-06, "loss": 2.6329, "step": 545 }, { "epoch": 0.5536121673003802, "grad_norm": 3.1657395362854004, "learning_rate": 9.112671157257698e-06, "loss": 2.8361, "step": 546 }, { "epoch": 0.5546261089987325, "grad_norm": 2.9443604946136475, "learning_rate": 9.07928025729593e-06, "loss": 2.5906, "step": 547 }, { "epoch": 0.5556400506970849, "grad_norm": 2.9069535732269287, "learning_rate": 9.045899707507247e-06, "loss": 2.5274, "step": 548 }, { "epoch": 0.5566539923954372, "grad_norm": 3.0094900131225586, "learning_rate": 9.012529883135548e-06, "loss": 2.6779, "step": 549 }, { "epoch": 0.5576679340937896, "grad_norm": 2.8510031700134277, "learning_rate": 8.979171159304166e-06, "loss": 2.6337, "step": 550 }, { "epoch": 0.5586818757921419, "grad_norm": 2.801830768585205, "learning_rate": 8.94582391101165e-06, "loss": 2.6673, "step": 551 }, { "epoch": 0.5596958174904944, "grad_norm": 2.9249250888824463, "learning_rate": 8.912488513127539e-06, "loss": 2.5263, "step": 552 }, { "epoch": 0.5607097591888467, "grad_norm": 2.9476025104522705, "learning_rate": 8.879165340388171e-06, "loss": 2.517, "step": 553 }, { "epoch": 0.561723700887199, "grad_norm": 3.0242457389831543, "learning_rate": 8.845854767392448e-06, "loss": 2.657, "step": 554 }, { "epoch": 0.5627376425855514, "grad_norm": 2.858503580093384, "learning_rate": 8.812557168597626e-06, "loss": 2.684, "step": 555 }, { "epoch": 0.5637515842839037, "grad_norm": 2.6426961421966553, "learning_rate": 8.779272918315135e-06, "loss": 2.6881, "step": 556 }, { "epoch": 0.564765525982256, "grad_norm": 2.9629528522491455, "learning_rate": 8.746002390706318e-06, "loss": 2.5888, "step": 557 }, { "epoch": 0.5657794676806084, "grad_norm": 2.738772392272949, "learning_rate": 8.712745959778293e-06, "loss": 2.6913, "step": 558 }, { "epoch": 0.5667934093789607, "grad_norm": 2.958136796951294, "learning_rate": 8.679503999379679e-06, "loss": 2.6486, "step": 559 }, { "epoch": 0.5678073510773131, "grad_norm": 2.908803701400757, "learning_rate": 8.646276883196438e-06, "loss": 2.7243, "step": 560 }, { "epoch": 0.5688212927756654, "grad_norm": 2.9704983234405518, "learning_rate": 8.613064984747672e-06, "loss": 2.689, "step": 561 }, { "epoch": 0.5698352344740177, "grad_norm": 2.7091917991638184, "learning_rate": 8.5798686773814e-06, "loss": 2.6094, "step": 562 }, { "epoch": 0.5708491761723701, "grad_norm": 2.8450615406036377, "learning_rate": 8.546688334270381e-06, "loss": 2.5753, "step": 563 }, { "epoch": 0.5718631178707224, "grad_norm": 2.8870737552642822, "learning_rate": 8.51352432840792e-06, "loss": 2.76, "step": 564 }, { "epoch": 0.5728770595690748, "grad_norm": 2.8496322631835938, "learning_rate": 8.480377032603658e-06, "loss": 2.4644, "step": 565 }, { "epoch": 0.5738910012674271, "grad_norm": 2.944342851638794, "learning_rate": 8.44724681947939e-06, "loss": 2.5489, "step": 566 }, { "epoch": 0.5749049429657794, "grad_norm": 2.785560369491577, "learning_rate": 8.414134061464898e-06, "loss": 2.7094, "step": 567 }, { "epoch": 0.5759188846641318, "grad_norm": 2.931671619415283, "learning_rate": 8.381039130793718e-06, "loss": 2.527, "step": 568 }, { "epoch": 0.5769328263624841, "grad_norm": 2.7206380367279053, "learning_rate": 8.347962399498996e-06, "loss": 2.7661, "step": 569 }, { "epoch": 0.5779467680608364, "grad_norm": 3.110283613204956, "learning_rate": 8.314904239409295e-06, "loss": 2.6634, "step": 570 }, { "epoch": 0.5789607097591889, "grad_norm": 2.9628753662109375, "learning_rate": 8.281865022144403e-06, "loss": 2.5929, "step": 571 }, { "epoch": 0.5799746514575412, "grad_norm": 2.844921112060547, "learning_rate": 8.248845119111168e-06, "loss": 2.5214, "step": 572 }, { "epoch": 0.5809885931558936, "grad_norm": 2.7899045944213867, "learning_rate": 8.21584490149932e-06, "loss": 2.6966, "step": 573 }, { "epoch": 0.5820025348542459, "grad_norm": 2.985085964202881, "learning_rate": 8.182864740277293e-06, "loss": 2.5197, "step": 574 }, { "epoch": 0.5830164765525983, "grad_norm": 2.994450092315674, "learning_rate": 8.149905006188067e-06, "loss": 2.5945, "step": 575 }, { "epoch": 0.5840304182509506, "grad_norm": 3.165738582611084, "learning_rate": 8.116966069744987e-06, "loss": 2.4739, "step": 576 }, { "epoch": 0.5850443599493029, "grad_norm": 2.733795404434204, "learning_rate": 8.084048301227597e-06, "loss": 2.5658, "step": 577 }, { "epoch": 0.5860583016476553, "grad_norm": 3.101283311843872, "learning_rate": 8.051152070677504e-06, "loss": 2.5252, "step": 578 }, { "epoch": 0.5870722433460076, "grad_norm": 3.125256299972534, "learning_rate": 8.018277747894178e-06, "loss": 2.6929, "step": 579 }, { "epoch": 0.5880861850443599, "grad_norm": 2.952458620071411, "learning_rate": 7.985425702430821e-06, "loss": 2.7738, "step": 580 }, { "epoch": 0.5891001267427123, "grad_norm": 2.94323468208313, "learning_rate": 7.952596303590215e-06, "loss": 2.5122, "step": 581 }, { "epoch": 0.5901140684410646, "grad_norm": 3.326063394546509, "learning_rate": 7.91978992042055e-06, "loss": 2.492, "step": 582 }, { "epoch": 0.591128010139417, "grad_norm": 2.7418370246887207, "learning_rate": 7.887006921711301e-06, "loss": 2.5467, "step": 583 }, { "epoch": 0.5921419518377693, "grad_norm": 2.820239543914795, "learning_rate": 7.854247675989057e-06, "loss": 2.5913, "step": 584 }, { "epoch": 0.5931558935361216, "grad_norm": 3.0596511363983154, "learning_rate": 7.821512551513395e-06, "loss": 2.3895, "step": 585 }, { "epoch": 0.594169835234474, "grad_norm": 3.111802577972412, "learning_rate": 7.788801916272739e-06, "loss": 2.3851, "step": 586 }, { "epoch": 0.5951837769328263, "grad_norm": 2.8186888694763184, "learning_rate": 7.75611613798022e-06, "loss": 2.4647, "step": 587 }, { "epoch": 0.5961977186311787, "grad_norm": 2.870859146118164, "learning_rate": 7.723455584069524e-06, "loss": 2.8919, "step": 588 }, { "epoch": 0.5972116603295311, "grad_norm": 2.9670660495758057, "learning_rate": 7.690820621690815e-06, "loss": 2.3913, "step": 589 }, { "epoch": 0.5982256020278834, "grad_norm": 2.862382650375366, "learning_rate": 7.65821161770654e-06, "loss": 2.5883, "step": 590 }, { "epoch": 0.5992395437262358, "grad_norm": 2.7800912857055664, "learning_rate": 7.625628938687349e-06, "loss": 2.4849, "step": 591 }, { "epoch": 0.6002534854245881, "grad_norm": 3.122760534286499, "learning_rate": 7.593072950907969e-06, "loss": 2.5025, "step": 592 }, { "epoch": 0.6012674271229405, "grad_norm": 2.840243339538574, "learning_rate": 7.560544020343071e-06, "loss": 2.7803, "step": 593 }, { "epoch": 0.6022813688212928, "grad_norm": 2.8622286319732666, "learning_rate": 7.528042512663174e-06, "loss": 2.7921, "step": 594 }, { "epoch": 0.6032953105196451, "grad_norm": 3.1672146320343018, "learning_rate": 7.495568793230516e-06, "loss": 2.3436, "step": 595 }, { "epoch": 0.6043092522179975, "grad_norm": 2.5706326961517334, "learning_rate": 7.463123227094962e-06, "loss": 2.6355, "step": 596 }, { "epoch": 0.6053231939163498, "grad_norm": 5.168808937072754, "learning_rate": 7.430706178989895e-06, "loss": 2.5555, "step": 597 }, { "epoch": 0.6063371356147021, "grad_norm": 2.9276273250579834, "learning_rate": 7.398318013328112e-06, "loss": 2.4021, "step": 598 }, { "epoch": 0.6073510773130545, "grad_norm": 2.889470338821411, "learning_rate": 7.365959094197734e-06, "loss": 2.5384, "step": 599 }, { "epoch": 0.6083650190114068, "grad_norm": 3.013488292694092, "learning_rate": 7.3336297853581115e-06, "loss": 2.4627, "step": 600 }, { "epoch": 0.6093789607097592, "grad_norm": 3.0487990379333496, "learning_rate": 7.301330450235733e-06, "loss": 2.5182, "step": 601 }, { "epoch": 0.6103929024081115, "grad_norm": 3.199193000793457, "learning_rate": 7.2690614519201315e-06, "loss": 2.7172, "step": 602 }, { "epoch": 0.6114068441064638, "grad_norm": 2.6934726238250732, "learning_rate": 7.236823153159832e-06, "loss": 2.446, "step": 603 }, { "epoch": 0.6124207858048162, "grad_norm": 3.0447793006896973, "learning_rate": 7.204615916358234e-06, "loss": 2.5658, "step": 604 }, { "epoch": 0.6134347275031685, "grad_norm": 2.838165521621704, "learning_rate": 7.172440103569566e-06, "loss": 2.9585, "step": 605 }, { "epoch": 0.6144486692015209, "grad_norm": 2.9292893409729004, "learning_rate": 7.140296076494809e-06, "loss": 2.884, "step": 606 }, { "epoch": 0.6154626108998733, "grad_norm": 2.599578857421875, "learning_rate": 7.108184196477622e-06, "loss": 2.5872, "step": 607 }, { "epoch": 0.6164765525982256, "grad_norm": 2.8179094791412354, "learning_rate": 7.076104824500294e-06, "loss": 2.6202, "step": 608 }, { "epoch": 0.617490494296578, "grad_norm": 3.000666379928589, "learning_rate": 7.044058321179671e-06, "loss": 2.7415, "step": 609 }, { "epoch": 0.6185044359949303, "grad_norm": 3.1160929203033447, "learning_rate": 7.012045046763111e-06, "loss": 2.3608, "step": 610 }, { "epoch": 0.6195183776932827, "grad_norm": 2.8095080852508545, "learning_rate": 6.980065361124437e-06, "loss": 2.4156, "step": 611 }, { "epoch": 0.620532319391635, "grad_norm": 3.549515962600708, "learning_rate": 6.948119623759888e-06, "loss": 2.7265, "step": 612 }, { "epoch": 0.6215462610899873, "grad_norm": 2.868363618850708, "learning_rate": 6.916208193784062e-06, "loss": 2.7277, "step": 613 }, { "epoch": 0.6225602027883397, "grad_norm": 2.762838125228882, "learning_rate": 6.884331429925919e-06, "loss": 2.8547, "step": 614 }, { "epoch": 0.623574144486692, "grad_norm": 2.8724491596221924, "learning_rate": 6.852489690524703e-06, "loss": 2.7768, "step": 615 }, { "epoch": 0.6245880861850444, "grad_norm": 2.692626476287842, "learning_rate": 6.820683333525942e-06, "loss": 2.7537, "step": 616 }, { "epoch": 0.6256020278833967, "grad_norm": 3.1846024990081787, "learning_rate": 6.788912716477417e-06, "loss": 2.432, "step": 617 }, { "epoch": 0.626615969581749, "grad_norm": 3.2031455039978027, "learning_rate": 6.7571781965251405e-06, "loss": 2.5432, "step": 618 }, { "epoch": 0.6276299112801014, "grad_norm": 2.8481509685516357, "learning_rate": 6.725480130409347e-06, "loss": 2.3483, "step": 619 }, { "epoch": 0.6286438529784537, "grad_norm": 2.80601167678833, "learning_rate": 6.693818874460475e-06, "loss": 2.6803, "step": 620 }, { "epoch": 0.629657794676806, "grad_norm": 2.8626856803894043, "learning_rate": 6.662194784595164e-06, "loss": 2.9226, "step": 621 }, { "epoch": 0.6306717363751584, "grad_norm": 2.815453290939331, "learning_rate": 6.63060821631226e-06, "loss": 2.4712, "step": 622 }, { "epoch": 0.6316856780735107, "grad_norm": 3.127218723297119, "learning_rate": 6.599059524688813e-06, "loss": 2.4857, "step": 623 }, { "epoch": 0.6326996197718631, "grad_norm": 2.635438919067383, "learning_rate": 6.567549064376078e-06, "loss": 2.5239, "step": 624 }, { "epoch": 0.6337135614702155, "grad_norm": 2.744525909423828, "learning_rate": 6.536077189595554e-06, "loss": 2.5372, "step": 625 }, { "epoch": 0.6347275031685679, "grad_norm": 2.62393856048584, "learning_rate": 6.504644254134969e-06, "loss": 2.5232, "step": 626 }, { "epoch": 0.6357414448669202, "grad_norm": 2.9516711235046387, "learning_rate": 6.4732506113443215e-06, "loss": 2.6682, "step": 627 }, { "epoch": 0.6367553865652725, "grad_norm": 2.90000319480896, "learning_rate": 6.441896614131918e-06, "loss": 2.6046, "step": 628 }, { "epoch": 0.6377693282636249, "grad_norm": 3.0262489318847656, "learning_rate": 6.410582614960375e-06, "loss": 2.861, "step": 629 }, { "epoch": 0.6387832699619772, "grad_norm": 2.911041498184204, "learning_rate": 6.379308965842689e-06, "loss": 2.6306, "step": 630 }, { "epoch": 0.6397972116603295, "grad_norm": 2.819647789001465, "learning_rate": 6.34807601833826e-06, "loss": 2.4897, "step": 631 }, { "epoch": 0.6408111533586819, "grad_norm": 2.881241798400879, "learning_rate": 6.316884123548947e-06, "loss": 2.6941, "step": 632 }, { "epoch": 0.6418250950570342, "grad_norm": 2.7107315063476562, "learning_rate": 6.285733632115118e-06, "loss": 2.8886, "step": 633 }, { "epoch": 0.6428390367553866, "grad_norm": 2.76619553565979, "learning_rate": 6.2546248942117134e-06, "loss": 2.6311, "step": 634 }, { "epoch": 0.6438529784537389, "grad_norm": 3.2412569522857666, "learning_rate": 6.2235582595442935e-06, "loss": 2.4515, "step": 635 }, { "epoch": 0.6448669201520912, "grad_norm": 2.7237205505371094, "learning_rate": 6.19253407734514e-06, "loss": 2.6107, "step": 636 }, { "epoch": 0.6458808618504436, "grad_norm": 2.886448383331299, "learning_rate": 6.161552696369291e-06, "loss": 2.56, "step": 637 }, { "epoch": 0.6468948035487959, "grad_norm": 2.9349300861358643, "learning_rate": 6.130614464890645e-06, "loss": 2.6451, "step": 638 }, { "epoch": 0.6479087452471483, "grad_norm": 2.790083646774292, "learning_rate": 6.099719730698046e-06, "loss": 2.6844, "step": 639 }, { "epoch": 0.6489226869455006, "grad_norm": 2.8875372409820557, "learning_rate": 6.068868841091361e-06, "loss": 2.5449, "step": 640 }, { "epoch": 0.6499366286438529, "grad_norm": 2.927098512649536, "learning_rate": 6.038062142877583e-06, "loss": 2.4283, "step": 641 }, { "epoch": 0.6509505703422053, "grad_norm": 2.8668813705444336, "learning_rate": 6.00729998236694e-06, "loss": 2.4133, "step": 642 }, { "epoch": 0.6519645120405577, "grad_norm": 2.6912641525268555, "learning_rate": 5.976582705368982e-06, "loss": 2.6628, "step": 643 }, { "epoch": 0.6529784537389101, "grad_norm": 2.862189292907715, "learning_rate": 5.945910657188717e-06, "loss": 2.6867, "step": 644 }, { "epoch": 0.6539923954372624, "grad_norm": 2.767120122909546, "learning_rate": 5.9152841826227136e-06, "loss": 2.6689, "step": 645 }, { "epoch": 0.6550063371356147, "grad_norm": 2.7868754863739014, "learning_rate": 5.884703625955219e-06, "loss": 2.6241, "step": 646 }, { "epoch": 0.6560202788339671, "grad_norm": 2.879535436630249, "learning_rate": 5.854169330954324e-06, "loss": 2.5689, "step": 647 }, { "epoch": 0.6570342205323194, "grad_norm": 2.824422836303711, "learning_rate": 5.823681640868049e-06, "loss": 2.4534, "step": 648 }, { "epoch": 0.6580481622306718, "grad_norm": 2.8804638385772705, "learning_rate": 5.793240898420521e-06, "loss": 2.4938, "step": 649 }, { "epoch": 0.6590621039290241, "grad_norm": 2.7216782569885254, "learning_rate": 5.762847445808111e-06, "loss": 2.5811, "step": 650 }, { "epoch": 0.6600760456273764, "grad_norm": 2.975800037384033, "learning_rate": 5.73250162469559e-06, "loss": 2.4781, "step": 651 }, { "epoch": 0.6610899873257288, "grad_norm": 2.927669048309326, "learning_rate": 5.702203776212269e-06, "loss": 2.6511, "step": 652 }, { "epoch": 0.6621039290240811, "grad_norm": 2.6778831481933594, "learning_rate": 5.6719542409482e-06, "loss": 2.5375, "step": 653 }, { "epoch": 0.6631178707224334, "grad_norm": 2.6449270248413086, "learning_rate": 5.6417533589503036e-06, "loss": 2.7249, "step": 654 }, { "epoch": 0.6641318124207858, "grad_norm": 2.714900016784668, "learning_rate": 5.611601469718601e-06, "loss": 2.7848, "step": 655 }, { "epoch": 0.6651457541191381, "grad_norm": 3.157137393951416, "learning_rate": 5.5814989122023385e-06, "loss": 2.2345, "step": 656 }, { "epoch": 0.6661596958174905, "grad_norm": 2.847174882888794, "learning_rate": 5.551446024796214e-06, "loss": 2.6439, "step": 657 }, { "epoch": 0.6671736375158428, "grad_norm": 2.6003525257110596, "learning_rate": 5.521443145336568e-06, "loss": 2.6906, "step": 658 }, { "epoch": 0.6681875792141951, "grad_norm": 2.806028366088867, "learning_rate": 5.491490611097586e-06, "loss": 2.8077, "step": 659 }, { "epoch": 0.6692015209125475, "grad_norm": 2.8221116065979004, "learning_rate": 5.461588758787484e-06, "loss": 2.6715, "step": 660 }, { "epoch": 0.6702154626108999, "grad_norm": 2.9865975379943848, "learning_rate": 5.431737924544763e-06, "loss": 2.7053, "step": 661 }, { "epoch": 0.6712294043092523, "grad_norm": 2.7677266597747803, "learning_rate": 5.401938443934405e-06, "loss": 2.6684, "step": 662 }, { "epoch": 0.6722433460076046, "grad_norm": 3.146745443344116, "learning_rate": 5.3721906519440945e-06, "loss": 2.2221, "step": 663 }, { "epoch": 0.6732572877059569, "grad_norm": 2.9099998474121094, "learning_rate": 5.34249488298048e-06, "loss": 2.5466, "step": 664 }, { "epoch": 0.6742712294043093, "grad_norm": 3.0901663303375244, "learning_rate": 5.312851470865383e-06, "loss": 2.367, "step": 665 }, { "epoch": 0.6752851711026616, "grad_norm": 2.6712629795074463, "learning_rate": 5.283260748832072e-06, "loss": 2.6655, "step": 666 }, { "epoch": 0.676299112801014, "grad_norm": 2.7886345386505127, "learning_rate": 5.253723049521507e-06, "loss": 2.7724, "step": 667 }, { "epoch": 0.6773130544993663, "grad_norm": 2.9444360733032227, "learning_rate": 5.224238704978584e-06, "loss": 2.5407, "step": 668 }, { "epoch": 0.6783269961977186, "grad_norm": 2.850425958633423, "learning_rate": 5.194808046648434e-06, "loss": 2.8026, "step": 669 }, { "epoch": 0.679340937896071, "grad_norm": 3.44856333732605, "learning_rate": 5.165431405372674e-06, "loss": 2.7905, "step": 670 }, { "epoch": 0.6803548795944233, "grad_norm": 2.809282064437866, "learning_rate": 5.1361091113856875e-06, "loss": 2.6393, "step": 671 }, { "epoch": 0.6813688212927757, "grad_norm": 2.956043004989624, "learning_rate": 5.106841494310929e-06, "loss": 2.3758, "step": 672 }, { "epoch": 0.682382762991128, "grad_norm": 2.8450045585632324, "learning_rate": 5.077628883157205e-06, "loss": 2.666, "step": 673 }, { "epoch": 0.6833967046894803, "grad_norm": 2.9813477993011475, "learning_rate": 5.048471606314971e-06, "loss": 2.3843, "step": 674 }, { "epoch": 0.6844106463878327, "grad_norm": 2.9916036128997803, "learning_rate": 5.019369991552658e-06, "loss": 2.4761, "step": 675 }, { "epoch": 0.685424588086185, "grad_norm": 2.921954393386841, "learning_rate": 4.990324366012977e-06, "loss": 2.4414, "step": 676 }, { "epoch": 0.6864385297845373, "grad_norm": 3.0995535850524902, "learning_rate": 4.961335056209234e-06, "loss": 2.6297, "step": 677 }, { "epoch": 0.6874524714828897, "grad_norm": 2.7778313159942627, "learning_rate": 4.932402388021677e-06, "loss": 2.6954, "step": 678 }, { "epoch": 0.6884664131812421, "grad_norm": 3.039264678955078, "learning_rate": 4.9035266866938125e-06, "loss": 2.731, "step": 679 }, { "epoch": 0.6894803548795945, "grad_norm": 2.6352975368499756, "learning_rate": 4.87470827682877e-06, "loss": 2.7248, "step": 680 }, { "epoch": 0.6904942965779468, "grad_norm": 3.0940101146698, "learning_rate": 4.8459474823856445e-06, "loss": 2.4792, "step": 681 }, { "epoch": 0.6915082382762991, "grad_norm": 2.724853038787842, "learning_rate": 4.81724462667584e-06, "loss": 2.5454, "step": 682 }, { "epoch": 0.6925221799746515, "grad_norm": 2.9925169944763184, "learning_rate": 4.788600032359461e-06, "loss": 2.5472, "step": 683 }, { "epoch": 0.6935361216730038, "grad_norm": 2.9303464889526367, "learning_rate": 4.760014021441671e-06, "loss": 2.731, "step": 684 }, { "epoch": 0.6945500633713562, "grad_norm": 2.8822903633117676, "learning_rate": 4.731486915269066e-06, "loss": 2.7233, "step": 685 }, { "epoch": 0.6955640050697085, "grad_norm": 2.7755796909332275, "learning_rate": 4.703019034526082e-06, "loss": 2.7116, "step": 686 }, { "epoch": 0.6965779467680608, "grad_norm": 2.6300008296966553, "learning_rate": 4.674610699231373e-06, "loss": 2.5184, "step": 687 }, { "epoch": 0.6975918884664132, "grad_norm": 2.8265411853790283, "learning_rate": 4.6462622287342154e-06, "loss": 2.5711, "step": 688 }, { "epoch": 0.6986058301647655, "grad_norm": 2.8336949348449707, "learning_rate": 4.617973941710932e-06, "loss": 2.66, "step": 689 }, { "epoch": 0.6996197718631179, "grad_norm": 2.909071683883667, "learning_rate": 4.5897461561612814e-06, "loss": 2.8292, "step": 690 }, { "epoch": 0.7006337135614702, "grad_norm": 2.6716184616088867, "learning_rate": 4.561579189404929e-06, "loss": 2.7653, "step": 691 }, { "epoch": 0.7016476552598225, "grad_norm": 3.014017105102539, "learning_rate": 4.5334733580778305e-06, "loss": 2.6507, "step": 692 }, { "epoch": 0.7026615969581749, "grad_norm": 2.738978624343872, "learning_rate": 4.505428978128693e-06, "loss": 2.5285, "step": 693 }, { "epoch": 0.7036755386565272, "grad_norm": 2.7485463619232178, "learning_rate": 4.4774463648154375e-06, "loss": 2.854, "step": 694 }, { "epoch": 0.7046894803548795, "grad_norm": 2.6583411693573, "learning_rate": 4.4495258327016415e-06, "loss": 2.6731, "step": 695 }, { "epoch": 0.7057034220532319, "grad_norm": 2.986009359359741, "learning_rate": 4.421667695652987e-06, "loss": 2.6313, "step": 696 }, { "epoch": 0.7067173637515843, "grad_norm": 2.9571311473846436, "learning_rate": 4.393872266833764e-06, "loss": 2.4516, "step": 697 }, { "epoch": 0.7077313054499367, "grad_norm": 2.93039870262146, "learning_rate": 4.3661398587033355e-06, "loss": 2.5464, "step": 698 }, { "epoch": 0.708745247148289, "grad_norm": 3.0327370166778564, "learning_rate": 4.338470783012609e-06, "loss": 2.3182, "step": 699 }, { "epoch": 0.7097591888466414, "grad_norm": 2.8209986686706543, "learning_rate": 4.310865350800566e-06, "loss": 2.6407, "step": 700 }, { "epoch": 0.7107731305449937, "grad_norm": 2.630613327026367, "learning_rate": 4.283323872390728e-06, "loss": 2.3327, "step": 701 }, { "epoch": 0.711787072243346, "grad_norm": 3.7512900829315186, "learning_rate": 4.255846657387701e-06, "loss": 2.5038, "step": 702 }, { "epoch": 0.7128010139416984, "grad_norm": 2.8261454105377197, "learning_rate": 4.228434014673679e-06, "loss": 2.5155, "step": 703 }, { "epoch": 0.7138149556400507, "grad_norm": 2.7256920337677, "learning_rate": 4.201086252404962e-06, "loss": 2.7317, "step": 704 }, { "epoch": 0.714828897338403, "grad_norm": 2.859297513961792, "learning_rate": 4.1738036780085175e-06, "loss": 2.4831, "step": 705 }, { "epoch": 0.7158428390367554, "grad_norm": 3.3157968521118164, "learning_rate": 4.1465865981785055e-06, "loss": 2.8, "step": 706 }, { "epoch": 0.7168567807351077, "grad_norm": 3.097968816757202, "learning_rate": 4.11943531887283e-06, "loss": 2.7645, "step": 707 }, { "epoch": 0.7178707224334601, "grad_norm": 2.6948904991149902, "learning_rate": 4.0923501453097115e-06, "loss": 2.7608, "step": 708 }, { "epoch": 0.7188846641318124, "grad_norm": 2.7945899963378906, "learning_rate": 4.065331381964252e-06, "loss": 2.6215, "step": 709 }, { "epoch": 0.7198986058301647, "grad_norm": 3.100442409515381, "learning_rate": 4.0383793325650025e-06, "loss": 2.5183, "step": 710 }, { "epoch": 0.7209125475285171, "grad_norm": 2.81402850151062, "learning_rate": 4.0114943000905645e-06, "loss": 2.6106, "step": 711 }, { "epoch": 0.7219264892268694, "grad_norm": 2.5642473697662354, "learning_rate": 3.984676586766167e-06, "loss": 2.6009, "step": 712 }, { "epoch": 0.7229404309252218, "grad_norm": 3.010683536529541, "learning_rate": 3.957926494060285e-06, "loss": 2.5473, "step": 713 }, { "epoch": 0.7239543726235741, "grad_norm": 3.6138861179351807, "learning_rate": 3.931244322681243e-06, "loss": 2.5092, "step": 714 }, { "epoch": 0.7249683143219265, "grad_norm": 2.7241833209991455, "learning_rate": 3.90463037257383e-06, "loss": 2.5499, "step": 715 }, { "epoch": 0.7259822560202789, "grad_norm": 2.8698906898498535, "learning_rate": 3.8780849429159365e-06, "loss": 2.5449, "step": 716 }, { "epoch": 0.7269961977186312, "grad_norm": 2.8715462684631348, "learning_rate": 3.851608332115192e-06, "loss": 2.6355, "step": 717 }, { "epoch": 0.7280101394169836, "grad_norm": 3.0901811122894287, "learning_rate": 3.825200837805595e-06, "loss": 2.5549, "step": 718 }, { "epoch": 0.7290240811153359, "grad_norm": 2.8652830123901367, "learning_rate": 3.7988627568441884e-06, "loss": 2.7197, "step": 719 }, { "epoch": 0.7300380228136882, "grad_norm": 2.704918146133423, "learning_rate": 3.7725943853077105e-06, "loss": 2.666, "step": 720 }, { "epoch": 0.7310519645120406, "grad_norm": 3.070158004760742, "learning_rate": 3.746396018489261e-06, "loss": 2.679, "step": 721 }, { "epoch": 0.7320659062103929, "grad_norm": 3.097076416015625, "learning_rate": 3.7202679508950015e-06, "loss": 2.4041, "step": 722 }, { "epoch": 0.7330798479087453, "grad_norm": 3.099027395248413, "learning_rate": 3.6942104762408183e-06, "loss": 2.3216, "step": 723 }, { "epoch": 0.7340937896070976, "grad_norm": 3.0055911540985107, "learning_rate": 3.6682238874490463e-06, "loss": 2.5474, "step": 724 }, { "epoch": 0.7351077313054499, "grad_norm": 2.9727060794830322, "learning_rate": 3.6423084766451622e-06, "loss": 2.3275, "step": 725 }, { "epoch": 0.7361216730038023, "grad_norm": 3.111468553543091, "learning_rate": 3.6164645351544956e-06, "loss": 2.6528, "step": 726 }, { "epoch": 0.7371356147021546, "grad_norm": 3.101276397705078, "learning_rate": 3.590692353498968e-06, "loss": 2.5109, "step": 727 }, { "epoch": 0.738149556400507, "grad_norm": 2.7668955326080322, "learning_rate": 3.564992221393825e-06, "loss": 2.6107, "step": 728 }, { "epoch": 0.7391634980988593, "grad_norm": 2.7561287879943848, "learning_rate": 3.5393644277443596e-06, "loss": 2.4118, "step": 729 }, { "epoch": 0.7401774397972116, "grad_norm": 3.077685594558716, "learning_rate": 3.513809260642694e-06, "loss": 2.5809, "step": 730 }, { "epoch": 0.741191381495564, "grad_norm": 3.1228139400482178, "learning_rate": 3.488327007364525e-06, "loss": 2.3581, "step": 731 }, { "epoch": 0.7422053231939163, "grad_norm": 3.054448127746582, "learning_rate": 3.4629179543658852e-06, "loss": 2.3218, "step": 732 }, { "epoch": 0.7432192648922687, "grad_norm": 3.002232313156128, "learning_rate": 3.437582387279946e-06, "loss": 2.3987, "step": 733 }, { "epoch": 0.7442332065906211, "grad_norm": 2.848593235015869, "learning_rate": 3.412320590913796e-06, "loss": 2.3704, "step": 734 }, { "epoch": 0.7452471482889734, "grad_norm": 2.9372968673706055, "learning_rate": 3.387132849245224e-06, "loss": 2.7844, "step": 735 }, { "epoch": 0.7462610899873258, "grad_norm": 3.0542829036712646, "learning_rate": 3.3620194454195565e-06, "loss": 2.3873, "step": 736 }, { "epoch": 0.7472750316856781, "grad_norm": 3.165482759475708, "learning_rate": 3.336980661746446e-06, "loss": 2.6344, "step": 737 }, { "epoch": 0.7482889733840304, "grad_norm": 2.833448648452759, "learning_rate": 3.3120167796967195e-06, "loss": 2.3989, "step": 738 }, { "epoch": 0.7493029150823828, "grad_norm": 2.797510862350464, "learning_rate": 3.2871280798992065e-06, "loss": 2.5353, "step": 739 }, { "epoch": 0.7503168567807351, "grad_norm": 2.9084537029266357, "learning_rate": 3.262314842137573e-06, "loss": 2.3216, "step": 740 }, { "epoch": 0.7513307984790875, "grad_norm": 3.0350236892700195, "learning_rate": 3.237577345347196e-06, "loss": 2.5678, "step": 741 }, { "epoch": 0.7523447401774398, "grad_norm": 2.864340305328369, "learning_rate": 3.2129158676120176e-06, "loss": 2.3784, "step": 742 }, { "epoch": 0.7533586818757921, "grad_norm": 3.111661672592163, "learning_rate": 3.1883306861614104e-06, "loss": 2.5248, "step": 743 }, { "epoch": 0.7543726235741445, "grad_norm": 3.0593674182891846, "learning_rate": 3.1638220773670825e-06, "loss": 2.5014, "step": 744 }, { "epoch": 0.7553865652724968, "grad_norm": 3.0310568809509277, "learning_rate": 3.1393903167399553e-06, "loss": 2.9185, "step": 745 }, { "epoch": 0.7564005069708492, "grad_norm": 2.886401891708374, "learning_rate": 3.115035678927063e-06, "loss": 2.5067, "step": 746 }, { "epoch": 0.7574144486692015, "grad_norm": 2.6182854175567627, "learning_rate": 3.090758437708482e-06, "loss": 2.7723, "step": 747 }, { "epoch": 0.7584283903675538, "grad_norm": 2.6697745323181152, "learning_rate": 3.0665588659942314e-06, "loss": 2.5685, "step": 748 }, { "epoch": 0.7594423320659062, "grad_norm": 2.8407485485076904, "learning_rate": 3.0424372358212285e-06, "loss": 2.5759, "step": 749 }, { "epoch": 0.7604562737642585, "grad_norm": 2.7550413608551025, "learning_rate": 3.0183938183502147e-06, "loss": 2.8251, "step": 750 }, { "epoch": 0.761470215462611, "grad_norm": 2.9071035385131836, "learning_rate": 2.9944288838627055e-06, "loss": 2.4514, "step": 751 }, { "epoch": 0.7624841571609633, "grad_norm": 2.9431047439575195, "learning_rate": 2.970542701757967e-06, "loss": 2.3782, "step": 752 }, { "epoch": 0.7634980988593156, "grad_norm": 2.7645556926727295, "learning_rate": 2.9467355405499788e-06, "loss": 2.6667, "step": 753 }, { "epoch": 0.764512040557668, "grad_norm": 2.9341866970062256, "learning_rate": 2.923007667864405e-06, "loss": 2.4445, "step": 754 }, { "epoch": 0.7655259822560203, "grad_norm": 3.016434907913208, "learning_rate": 2.8993593504356065e-06, "loss": 2.6087, "step": 755 }, { "epoch": 0.7665399239543726, "grad_norm": 2.9525911808013916, "learning_rate": 2.8757908541036338e-06, "loss": 2.4655, "step": 756 }, { "epoch": 0.767553865652725, "grad_norm": 2.9173786640167236, "learning_rate": 2.8523024438112236e-06, "loss": 2.4067, "step": 757 }, { "epoch": 0.7685678073510773, "grad_norm": 2.665409803390503, "learning_rate": 2.828894383600851e-06, "loss": 2.4272, "step": 758 }, { "epoch": 0.7695817490494297, "grad_norm": 2.8478453159332275, "learning_rate": 2.805566936611728e-06, "loss": 2.8092, "step": 759 }, { "epoch": 0.770595690747782, "grad_norm": 2.8794307708740234, "learning_rate": 2.782320365076874e-06, "loss": 2.5053, "step": 760 }, { "epoch": 0.7716096324461343, "grad_norm": 3.1319518089294434, "learning_rate": 2.7591549303201513e-06, "loss": 2.6314, "step": 761 }, { "epoch": 0.7726235741444867, "grad_norm": 3.0643534660339355, "learning_rate": 2.7360708927533285e-06, "loss": 2.588, "step": 762 }, { "epoch": 0.773637515842839, "grad_norm": 2.7867236137390137, "learning_rate": 2.7130685118731615e-06, "loss": 2.6412, "step": 763 }, { "epoch": 0.7746514575411914, "grad_norm": 2.8751060962677, "learning_rate": 2.6901480462584707e-06, "loss": 2.6974, "step": 764 }, { "epoch": 0.7756653992395437, "grad_norm": 2.7692108154296875, "learning_rate": 2.6673097535672287e-06, "loss": 2.5394, "step": 765 }, { "epoch": 0.776679340937896, "grad_norm": 2.860275983810425, "learning_rate": 2.6445538905336764e-06, "loss": 2.5796, "step": 766 }, { "epoch": 0.7776932826362484, "grad_norm": 3.0435452461242676, "learning_rate": 2.621880712965431e-06, "loss": 2.4691, "step": 767 }, { "epoch": 0.7787072243346007, "grad_norm": 2.8065273761749268, "learning_rate": 2.5992904757406025e-06, "loss": 2.4452, "step": 768 }, { "epoch": 0.779721166032953, "grad_norm": 2.893676996231079, "learning_rate": 2.5767834328049444e-06, "loss": 2.5815, "step": 769 }, { "epoch": 0.7807351077313055, "grad_norm": 2.7362284660339355, "learning_rate": 2.5543598371689826e-06, "loss": 2.4685, "step": 770 }, { "epoch": 0.7817490494296578, "grad_norm": 3.473865509033203, "learning_rate": 2.532019940905186e-06, "loss": 2.8166, "step": 771 }, { "epoch": 0.7827629911280102, "grad_norm": 2.8457305431365967, "learning_rate": 2.5097639951451247e-06, "loss": 2.6752, "step": 772 }, { "epoch": 0.7837769328263625, "grad_norm": 2.654867172241211, "learning_rate": 2.4875922500766414e-06, "loss": 2.3966, "step": 773 }, { "epoch": 0.7847908745247149, "grad_norm": 2.7692761421203613, "learning_rate": 2.4655049549410535e-06, "loss": 2.5635, "step": 774 }, { "epoch": 0.7858048162230672, "grad_norm": 3.1793344020843506, "learning_rate": 2.443502358030344e-06, "loss": 2.7287, "step": 775 }, { "epoch": 0.7868187579214195, "grad_norm": 2.9192662239074707, "learning_rate": 2.421584706684359e-06, "loss": 2.4833, "step": 776 }, { "epoch": 0.7878326996197719, "grad_norm": 3.0066676139831543, "learning_rate": 2.3997522472880496e-06, "loss": 2.5308, "step": 777 }, { "epoch": 0.7888466413181242, "grad_norm": 2.8126232624053955, "learning_rate": 2.378005225268689e-06, "loss": 2.4983, "step": 778 }, { "epoch": 0.7898605830164765, "grad_norm": 2.7183611392974854, "learning_rate": 2.3563438850931076e-06, "loss": 2.6066, "step": 779 }, { "epoch": 0.7908745247148289, "grad_norm": 2.824969530105591, "learning_rate": 2.334768470264963e-06, "loss": 2.4692, "step": 780 }, { "epoch": 0.7918884664131812, "grad_norm": 2.9735774993896484, "learning_rate": 2.3132792233219814e-06, "loss": 2.7286, "step": 781 }, { "epoch": 0.7929024081115336, "grad_norm": 2.792377471923828, "learning_rate": 2.2918763858332503e-06, "loss": 2.4081, "step": 782 }, { "epoch": 0.7939163498098859, "grad_norm": 2.925187826156616, "learning_rate": 2.2705601983964933e-06, "loss": 2.5134, "step": 783 }, { "epoch": 0.7949302915082382, "grad_norm": 2.921086549758911, "learning_rate": 2.249330900635359e-06, "loss": 2.4154, "step": 784 }, { "epoch": 0.7959442332065906, "grad_norm": 3.2176079750061035, "learning_rate": 2.2281887311967454e-06, "loss": 2.5693, "step": 785 }, { "epoch": 0.7969581749049429, "grad_norm": 2.746103048324585, "learning_rate": 2.207133927748104e-06, "loss": 2.5852, "step": 786 }, { "epoch": 0.7979721166032953, "grad_norm": 2.905566453933716, "learning_rate": 2.1861667269747623e-06, "loss": 2.6516, "step": 787 }, { "epoch": 0.7989860583016477, "grad_norm": 2.67879581451416, "learning_rate": 2.165287364577282e-06, "loss": 2.5244, "step": 788 }, { "epoch": 0.8, "grad_norm": 2.5994820594787598, "learning_rate": 2.1444960752687994e-06, "loss": 2.7985, "step": 789 }, { "epoch": 0.8010139416983524, "grad_norm": 2.890216112136841, "learning_rate": 2.1237930927723736e-06, "loss": 2.5104, "step": 790 }, { "epoch": 0.8020278833967047, "grad_norm": 2.9422292709350586, "learning_rate": 2.103178649818387e-06, "loss": 2.6468, "step": 791 }, { "epoch": 0.8030418250950571, "grad_norm": 2.9980218410491943, "learning_rate": 2.0826529781419092e-06, "loss": 2.6556, "step": 792 }, { "epoch": 0.8040557667934094, "grad_norm": 2.815119981765747, "learning_rate": 2.0622163084800904e-06, "loss": 2.5436, "step": 793 }, { "epoch": 0.8050697084917617, "grad_norm": 2.761706590652466, "learning_rate": 2.0418688705695846e-06, "loss": 2.6906, "step": 794 }, { "epoch": 0.8060836501901141, "grad_norm": 2.60274338722229, "learning_rate": 2.021610893143947e-06, "loss": 2.7891, "step": 795 }, { "epoch": 0.8070975918884664, "grad_norm": 2.892871618270874, "learning_rate": 2.0014426039310786e-06, "loss": 2.5267, "step": 796 }, { "epoch": 0.8081115335868188, "grad_norm": 2.916266679763794, "learning_rate": 1.9813642296506606e-06, "loss": 2.689, "step": 797 }, { "epoch": 0.8091254752851711, "grad_norm": 2.925898551940918, "learning_rate": 1.9613759960115986e-06, "loss": 2.6084, "step": 798 }, { "epoch": 0.8101394169835234, "grad_norm": 2.8048884868621826, "learning_rate": 1.9414781277094963e-06, "loss": 2.6537, "step": 799 }, { "epoch": 0.8111533586818758, "grad_norm": 3.465637445449829, "learning_rate": 1.9216708484241275e-06, "loss": 2.4329, "step": 800 }, { "epoch": 0.8121673003802281, "grad_norm": 3.048293113708496, "learning_rate": 1.9019543808169117e-06, "loss": 2.3845, "step": 801 }, { "epoch": 0.8131812420785804, "grad_norm": 2.635202169418335, "learning_rate": 1.8823289465284244e-06, "loss": 2.73, "step": 802 }, { "epoch": 0.8141951837769328, "grad_norm": 3.521111249923706, "learning_rate": 1.8627947661759027e-06, "loss": 2.5559, "step": 803 }, { "epoch": 0.8152091254752851, "grad_norm": 3.151444673538208, "learning_rate": 1.8433520593507515e-06, "loss": 2.6452, "step": 804 }, { "epoch": 0.8162230671736375, "grad_norm": 2.964160680770874, "learning_rate": 1.8240010446160973e-06, "loss": 2.731, "step": 805 }, { "epoch": 0.8172370088719899, "grad_norm": 3.4860939979553223, "learning_rate": 1.8047419395043086e-06, "loss": 2.437, "step": 806 }, { "epoch": 0.8182509505703423, "grad_norm": 2.681875705718994, "learning_rate": 1.7855749605145722e-06, "loss": 2.7035, "step": 807 }, { "epoch": 0.8192648922686946, "grad_norm": 2.733168601989746, "learning_rate": 1.766500323110445e-06, "loss": 2.7602, "step": 808 }, { "epoch": 0.8202788339670469, "grad_norm": 3.0019381046295166, "learning_rate": 1.7475182417174318e-06, "loss": 2.561, "step": 809 }, { "epoch": 0.8212927756653993, "grad_norm": 2.899308443069458, "learning_rate": 1.7286289297205826e-06, "loss": 2.5541, "step": 810 }, { "epoch": 0.8223067173637516, "grad_norm": 3.142498254776001, "learning_rate": 1.7098325994620934e-06, "loss": 2.4551, "step": 811 }, { "epoch": 0.8233206590621039, "grad_norm": 2.99397873878479, "learning_rate": 1.6911294622389075e-06, "loss": 2.8406, "step": 812 }, { "epoch": 0.8243346007604563, "grad_norm": 2.874096155166626, "learning_rate": 1.6725197283003548e-06, "loss": 2.3478, "step": 813 }, { "epoch": 0.8253485424588086, "grad_norm": 2.8119425773620605, "learning_rate": 1.6540036068457833e-06, "loss": 2.4847, "step": 814 }, { "epoch": 0.826362484157161, "grad_norm": 2.8022053241729736, "learning_rate": 1.6355813060221993e-06, "loss": 2.4975, "step": 815 }, { "epoch": 0.8273764258555133, "grad_norm": 2.844733715057373, "learning_rate": 1.6172530329219416e-06, "loss": 2.5104, "step": 816 }, { "epoch": 0.8283903675538656, "grad_norm": 2.806781530380249, "learning_rate": 1.5990189935803402e-06, "loss": 2.7239, "step": 817 }, { "epoch": 0.829404309252218, "grad_norm": 2.7376742362976074, "learning_rate": 1.58087939297341e-06, "loss": 2.6657, "step": 818 }, { "epoch": 0.8304182509505703, "grad_norm": 2.7552506923675537, "learning_rate": 1.5628344350155477e-06, "loss": 2.8755, "step": 819 }, { "epoch": 0.8314321926489227, "grad_norm": 2.751073122024536, "learning_rate": 1.5448843225572218e-06, "loss": 2.4813, "step": 820 }, { "epoch": 0.832446134347275, "grad_norm": 2.7169299125671387, "learning_rate": 1.5270292573827173e-06, "loss": 2.473, "step": 821 }, { "epoch": 0.8334600760456273, "grad_norm": 2.8066329956054688, "learning_rate": 1.509269440207851e-06, "loss": 2.6954, "step": 822 }, { "epoch": 0.8344740177439797, "grad_norm": 2.620018720626831, "learning_rate": 1.4916050706777185e-06, "loss": 2.577, "step": 823 }, { "epoch": 0.8354879594423321, "grad_norm": 2.9988808631896973, "learning_rate": 1.474036347364446e-06, "loss": 2.5485, "step": 824 }, { "epoch": 0.8365019011406845, "grad_norm": 2.9113547801971436, "learning_rate": 1.4565634677649786e-06, "loss": 2.4276, "step": 825 }, { "epoch": 0.8375158428390368, "grad_norm": 2.95076060295105, "learning_rate": 1.4391866282988266e-06, "loss": 2.5785, "step": 826 }, { "epoch": 0.8385297845373891, "grad_norm": 2.605067253112793, "learning_rate": 1.4219060243058879e-06, "loss": 2.8107, "step": 827 }, { "epoch": 0.8395437262357415, "grad_norm": 2.895616292953491, "learning_rate": 1.4047218500442305e-06, "loss": 2.9408, "step": 828 }, { "epoch": 0.8405576679340938, "grad_norm": 3.193804979324341, "learning_rate": 1.3876342986879243e-06, "loss": 2.3704, "step": 829 }, { "epoch": 0.8415716096324461, "grad_norm": 3.0509471893310547, "learning_rate": 1.3706435623248627e-06, "loss": 2.6771, "step": 830 }, { "epoch": 0.8425855513307985, "grad_norm": 2.8694870471954346, "learning_rate": 1.3537498319545984e-06, "loss": 2.8275, "step": 831 }, { "epoch": 0.8435994930291508, "grad_norm": 2.6654863357543945, "learning_rate": 1.3369532974862053e-06, "loss": 2.4856, "step": 832 }, { "epoch": 0.8446134347275032, "grad_norm": 2.8032288551330566, "learning_rate": 1.3202541477361441e-06, "loss": 2.7882, "step": 833 }, { "epoch": 0.8456273764258555, "grad_norm": 2.8845303058624268, "learning_rate": 1.303652570426125e-06, "loss": 2.6482, "step": 834 }, { "epoch": 0.8466413181242078, "grad_norm": 3.2056705951690674, "learning_rate": 1.2871487521810166e-06, "loss": 2.821, "step": 835 }, { "epoch": 0.8476552598225602, "grad_norm": 2.8983800411224365, "learning_rate": 1.2707428785267396e-06, "loss": 2.6287, "step": 836 }, { "epoch": 0.8486692015209125, "grad_norm": 2.935938596725464, "learning_rate": 1.2544351338881721e-06, "loss": 2.8519, "step": 837 }, { "epoch": 0.8496831432192649, "grad_norm": 2.7424423694610596, "learning_rate": 1.2382257015870957e-06, "loss": 2.8495, "step": 838 }, { "epoch": 0.8506970849176172, "grad_norm": 2.661113739013672, "learning_rate": 1.222114763840121e-06, "loss": 2.6281, "step": 839 }, { "epoch": 0.8517110266159695, "grad_norm": 2.766042947769165, "learning_rate": 1.2061025017566374e-06, "loss": 2.821, "step": 840 }, { "epoch": 0.8527249683143219, "grad_norm": 2.742476224899292, "learning_rate": 1.190189095336791e-06, "loss": 2.8773, "step": 841 }, { "epoch": 0.8537389100126743, "grad_norm": 2.753896474838257, "learning_rate": 1.1743747234694437e-06, "loss": 2.3899, "step": 842 }, { "epoch": 0.8547528517110267, "grad_norm": 2.794480562210083, "learning_rate": 1.1586595639301768e-06, "loss": 2.4172, "step": 843 }, { "epoch": 0.855766793409379, "grad_norm": 3.079993486404419, "learning_rate": 1.143043793379287e-06, "loss": 2.4708, "step": 844 }, { "epoch": 0.8567807351077313, "grad_norm": 2.8267061710357666, "learning_rate": 1.1275275873597957e-06, "loss": 2.8664, "step": 845 }, { "epoch": 0.8577946768060837, "grad_norm": 2.92879056930542, "learning_rate": 1.1121111202954836e-06, "loss": 2.5214, "step": 846 }, { "epoch": 0.858808618504436, "grad_norm": 3.016521692276001, "learning_rate": 1.096794565488929e-06, "loss": 2.4585, "step": 847 }, { "epoch": 0.8598225602027884, "grad_norm": 2.8173906803131104, "learning_rate": 1.0815780951195521e-06, "loss": 2.5214, "step": 848 }, { "epoch": 0.8608365019011407, "grad_norm": 2.774216651916504, "learning_rate": 1.0664618802416814e-06, "loss": 2.3993, "step": 849 }, { "epoch": 0.861850443599493, "grad_norm": 2.5246875286102295, "learning_rate": 1.0514460907826473e-06, "loss": 2.6165, "step": 850 }, { "epoch": 0.8628643852978454, "grad_norm": 2.8525874614715576, "learning_rate": 1.0365308955408459e-06, "loss": 2.5919, "step": 851 }, { "epoch": 0.8638783269961977, "grad_norm": 2.689223527908325, "learning_rate": 1.0217164621838605e-06, "loss": 2.7843, "step": 852 }, { "epoch": 0.86489226869455, "grad_norm": 2.990201473236084, "learning_rate": 1.0070029572465657e-06, "loss": 2.7435, "step": 853 }, { "epoch": 0.8659062103929024, "grad_norm": 2.704960346221924, "learning_rate": 9.923905461292638e-07, "loss": 2.7226, "step": 854 }, { "epoch": 0.8669201520912547, "grad_norm": 2.8485541343688965, "learning_rate": 9.77879393095823e-07, "loss": 2.4598, "step": 855 }, { "epoch": 0.8679340937896071, "grad_norm": 2.8298146724700928, "learning_rate": 9.634696612718242e-07, "loss": 2.6507, "step": 856 }, { "epoch": 0.8689480354879594, "grad_norm": 2.8180055618286133, "learning_rate": 9.491615126427356e-07, "loss": 2.3754, "step": 857 }, { "epoch": 0.8699619771863117, "grad_norm": 2.896484136581421, "learning_rate": 9.349551080520913e-07, "loss": 2.6731, "step": 858 }, { "epoch": 0.8709759188846641, "grad_norm": 2.691772699356079, "learning_rate": 9.208506071996759e-07, "loss": 2.7255, "step": 859 }, { "epoch": 0.8719898605830165, "grad_norm": 2.80303692817688, "learning_rate": 9.068481686397324e-07, "loss": 2.7703, "step": 860 }, { "epoch": 0.8730038022813689, "grad_norm": 2.9904346466064453, "learning_rate": 8.929479497791926e-07, "loss": 2.6612, "step": 861 }, { "epoch": 0.8740177439797212, "grad_norm": 2.7394704818725586, "learning_rate": 8.791501068758823e-07, "loss": 2.4495, "step": 862 }, { "epoch": 0.8750316856780735, "grad_norm": 2.5872786045074463, "learning_rate": 8.654547950367898e-07, "loss": 2.432, "step": 863 }, { "epoch": 0.8760456273764259, "grad_norm": 2.8211286067962646, "learning_rate": 8.51862168216303e-07, "loss": 2.6065, "step": 864 }, { "epoch": 0.8770595690747782, "grad_norm": 2.8662006855010986, "learning_rate": 8.383723792144916e-07, "loss": 2.5171, "step": 865 }, { "epoch": 0.8780735107731306, "grad_norm": 3.0293424129486084, "learning_rate": 8.249855796753881e-07, "loss": 2.4755, "step": 866 }, { "epoch": 0.8790874524714829, "grad_norm": 3.1426124572753906, "learning_rate": 8.117019200852716e-07, "loss": 2.635, "step": 867 }, { "epoch": 0.8801013941698352, "grad_norm": 2.7930748462677, "learning_rate": 7.985215497709909e-07, "loss": 2.4437, "step": 868 }, { "epoch": 0.8811153358681876, "grad_norm": 2.8567628860473633, "learning_rate": 7.854446168982777e-07, "loss": 2.602, "step": 869 }, { "epoch": 0.8821292775665399, "grad_norm": 2.7896361351013184, "learning_rate": 7.724712684700819e-07, "loss": 2.4404, "step": 870 }, { "epoch": 0.8831432192648923, "grad_norm": 2.7019593715667725, "learning_rate": 7.59601650324917e-07, "loss": 2.6032, "step": 871 }, { "epoch": 0.8841571609632446, "grad_norm": 3.116281747817993, "learning_rate": 7.468359071352338e-07, "loss": 2.4003, "step": 872 }, { "epoch": 0.8851711026615969, "grad_norm": 3.2974696159362793, "learning_rate": 7.341741824057713e-07, "loss": 2.3171, "step": 873 }, { "epoch": 0.8861850443599493, "grad_norm": 2.7963881492614746, "learning_rate": 7.216166184719653e-07, "loss": 2.4472, "step": 874 }, { "epoch": 0.8871989860583016, "grad_norm": 3.155557155609131, "learning_rate": 7.091633564983314e-07, "loss": 2.3749, "step": 875 }, { "epoch": 0.888212927756654, "grad_norm": 2.9222681522369385, "learning_rate": 6.96814536476893e-07, "loss": 2.8385, "step": 876 }, { "epoch": 0.8892268694550063, "grad_norm": 2.622359275817871, "learning_rate": 6.845702972255974e-07, "loss": 2.6269, "step": 877 }, { "epoch": 0.8902408111533587, "grad_norm": 2.6436614990234375, "learning_rate": 6.724307763867555e-07, "loss": 2.6646, "step": 878 }, { "epoch": 0.8912547528517111, "grad_norm": 2.8023335933685303, "learning_rate": 6.603961104255018e-07, "loss": 2.5532, "step": 879 }, { "epoch": 0.8922686945500634, "grad_norm": 3.015249729156494, "learning_rate": 6.484664346282555e-07, "loss": 2.6042, "step": 880 }, { "epoch": 0.8932826362484158, "grad_norm": 2.866190195083618, "learning_rate": 6.366418831011955e-07, "loss": 2.4562, "step": 881 }, { "epoch": 0.8942965779467681, "grad_norm": 2.755678653717041, "learning_rate": 6.249225887687615e-07, "loss": 2.4521, "step": 882 }, { "epoch": 0.8953105196451204, "grad_norm": 3.0547993183135986, "learning_rate": 6.133086833721569e-07, "loss": 2.5823, "step": 883 }, { "epoch": 0.8963244613434728, "grad_norm": 2.689230442047119, "learning_rate": 6.018002974678616e-07, "loss": 2.8689, "step": 884 }, { "epoch": 0.8973384030418251, "grad_norm": 2.649055004119873, "learning_rate": 5.903975604261725e-07, "loss": 2.3195, "step": 885 }, { "epoch": 0.8983523447401774, "grad_norm": 2.8953123092651367, "learning_rate": 5.791006004297451e-07, "loss": 2.5405, "step": 886 }, { "epoch": 0.8993662864385298, "grad_norm": 2.914782762527466, "learning_rate": 5.679095444721538e-07, "loss": 2.6512, "step": 887 }, { "epoch": 0.9003802281368821, "grad_norm": 2.9468483924865723, "learning_rate": 5.568245183564669e-07, "loss": 2.5355, "step": 888 }, { "epoch": 0.9013941698352345, "grad_norm": 3.1716208457946777, "learning_rate": 5.458456466938233e-07, "loss": 2.7402, "step": 889 }, { "epoch": 0.9024081115335868, "grad_norm": 3.0763444900512695, "learning_rate": 5.349730529020436e-07, "loss": 2.5703, "step": 890 }, { "epoch": 0.9034220532319391, "grad_norm": 2.981691360473633, "learning_rate": 5.242068592042349e-07, "loss": 2.4712, "step": 891 }, { "epoch": 0.9044359949302915, "grad_norm": 2.7758986949920654, "learning_rate": 5.135471866274167e-07, "loss": 2.8763, "step": 892 }, { "epoch": 0.9054499366286438, "grad_norm": 2.766244411468506, "learning_rate": 5.029941550011663e-07, "loss": 2.5244, "step": 893 }, { "epoch": 0.9064638783269962, "grad_norm": 2.747422218322754, "learning_rate": 4.925478829562668e-07, "loss": 2.7606, "step": 894 }, { "epoch": 0.9074778200253485, "grad_norm": 2.6289525032043457, "learning_rate": 4.822084879233746e-07, "loss": 2.7443, "step": 895 }, { "epoch": 0.9084917617237009, "grad_norm": 2.7913079261779785, "learning_rate": 4.7197608613169685e-07, "loss": 2.6684, "step": 896 }, { "epoch": 0.9095057034220533, "grad_norm": 2.585127353668213, "learning_rate": 4.618507926076954e-07, "loss": 2.6322, "step": 897 }, { "epoch": 0.9105196451204056, "grad_norm": 2.8578853607177734, "learning_rate": 4.518327211737761e-07, "loss": 2.7563, "step": 898 }, { "epoch": 0.911533586818758, "grad_norm": 2.9707372188568115, "learning_rate": 4.4192198444702685e-07, "loss": 2.4981, "step": 899 }, { "epoch": 0.9125475285171103, "grad_norm": 2.8918051719665527, "learning_rate": 4.3211869383793735e-07, "loss": 2.4355, "step": 900 }, { "epoch": 0.9135614702154626, "grad_norm": 2.5744242668151855, "learning_rate": 4.2242295954915913e-07, "loss": 2.8608, "step": 901 }, { "epoch": 0.914575411913815, "grad_norm": 3.1196258068084717, "learning_rate": 4.128348905742585e-07, "loss": 2.6406, "step": 902 }, { "epoch": 0.9155893536121673, "grad_norm": 2.755964994430542, "learning_rate": 4.0335459469649117e-07, "loss": 2.4686, "step": 903 }, { "epoch": 0.9166032953105197, "grad_norm": 2.6820852756500244, "learning_rate": 3.9398217848759637e-07, "loss": 2.6021, "step": 904 }, { "epoch": 0.917617237008872, "grad_norm": 2.6925339698791504, "learning_rate": 3.847177473065955e-07, "loss": 2.3577, "step": 905 }, { "epoch": 0.9186311787072243, "grad_norm": 3.050182819366455, "learning_rate": 3.755614052986056e-07, "loss": 2.7241, "step": 906 }, { "epoch": 0.9196451204055767, "grad_norm": 2.7628440856933594, "learning_rate": 3.66513255393669e-07, "loss": 2.2088, "step": 907 }, { "epoch": 0.920659062103929, "grad_norm": 2.9826819896698, "learning_rate": 3.575733993056063e-07, "loss": 2.2886, "step": 908 }, { "epoch": 0.9216730038022813, "grad_norm": 2.6961429119110107, "learning_rate": 3.4874193753085426e-07, "loss": 2.5012, "step": 909 }, { "epoch": 0.9226869455006337, "grad_norm": 2.7817845344543457, "learning_rate": 3.4001896934735436e-07, "loss": 2.6966, "step": 910 }, { "epoch": 0.923700887198986, "grad_norm": 2.5238335132598877, "learning_rate": 3.314045928134224e-07, "loss": 2.5631, "step": 911 }, { "epoch": 0.9247148288973384, "grad_norm": 2.87608003616333, "learning_rate": 3.2289890476665975e-07, "loss": 2.4905, "step": 912 }, { "epoch": 0.9257287705956907, "grad_norm": 2.7551474571228027, "learning_rate": 3.145020008228539e-07, "loss": 2.2909, "step": 913 }, { "epoch": 0.9267427122940431, "grad_norm": 2.788245677947998, "learning_rate": 3.0621397537490494e-07, "loss": 2.7361, "step": 914 }, { "epoch": 0.9277566539923955, "grad_norm": 2.9203968048095703, "learning_rate": 2.9803492159177103e-07, "loss": 2.3171, "step": 915 }, { "epoch": 0.9287705956907478, "grad_norm": 2.6838016510009766, "learning_rate": 2.8996493141741686e-07, "loss": 2.5996, "step": 916 }, { "epoch": 0.9297845373891002, "grad_norm": 2.8150994777679443, "learning_rate": 2.8200409556977894e-07, "loss": 2.5204, "step": 917 }, { "epoch": 0.9307984790874525, "grad_norm": 2.642317533493042, "learning_rate": 2.74152503539743e-07, "loss": 2.7703, "step": 918 }, { "epoch": 0.9318124207858048, "grad_norm": 2.8072235584259033, "learning_rate": 2.6641024359015056e-07, "loss": 2.6409, "step": 919 }, { "epoch": 0.9328263624841572, "grad_norm": 3.1344387531280518, "learning_rate": 2.587774027547918e-07, "loss": 2.3684, "step": 920 }, { "epoch": 0.9338403041825095, "grad_norm": 2.733198642730713, "learning_rate": 2.5125406683743417e-07, "loss": 2.5659, "step": 921 }, { "epoch": 0.9348542458808619, "grad_norm": 2.8597402572631836, "learning_rate": 2.438403204108597e-07, "loss": 2.6037, "step": 922 }, { "epoch": 0.9358681875792142, "grad_norm": 2.898003578186035, "learning_rate": 2.3653624681591048e-07, "loss": 2.5481, "step": 923 }, { "epoch": 0.9368821292775665, "grad_norm": 2.923548698425293, "learning_rate": 2.2934192816055355e-07, "loss": 2.6664, "step": 924 }, { "epoch": 0.9378960709759189, "grad_norm": 2.659433364868164, "learning_rate": 2.2225744531895632e-07, "loss": 2.6727, "step": 925 }, { "epoch": 0.9389100126742712, "grad_norm": 3.0512163639068604, "learning_rate": 2.1528287793057934e-07, "loss": 2.3878, "step": 926 }, { "epoch": 0.9399239543726235, "grad_norm": 2.760099411010742, "learning_rate": 2.0841830439928045e-07, "loss": 2.5098, "step": 927 }, { "epoch": 0.9409378960709759, "grad_norm": 3.138976812362671, "learning_rate": 2.016638018924344e-07, "loss": 2.5367, "step": 928 }, { "epoch": 0.9419518377693282, "grad_norm": 2.7796897888183594, "learning_rate": 1.95019446340059e-07, "loss": 2.4234, "step": 929 }, { "epoch": 0.9429657794676806, "grad_norm": 2.895256519317627, "learning_rate": 1.8848531243397471e-07, "loss": 2.3556, "step": 930 }, { "epoch": 0.9439797211660329, "grad_norm": 2.9773645401000977, "learning_rate": 1.8206147362695214e-07, "loss": 2.341, "step": 931 }, { "epoch": 0.9449936628643854, "grad_norm": 2.657684564590454, "learning_rate": 1.7574800213189137e-07, "loss": 2.5773, "step": 932 }, { "epoch": 0.9460076045627377, "grad_norm": 2.844395160675049, "learning_rate": 1.6954496892101047e-07, "loss": 2.6748, "step": 933 }, { "epoch": 0.94702154626109, "grad_norm": 3.145855188369751, "learning_rate": 1.6345244372504842e-07, "loss": 2.597, "step": 934 }, { "epoch": 0.9480354879594424, "grad_norm": 3.008000373840332, "learning_rate": 1.5747049503248013e-07, "loss": 2.4269, "step": 935 }, { "epoch": 0.9490494296577947, "grad_norm": 2.8397281169891357, "learning_rate": 1.5159919008874368e-07, "loss": 2.5656, "step": 936 }, { "epoch": 0.950063371356147, "grad_norm": 2.601118803024292, "learning_rate": 1.458385948954899e-07, "loss": 2.7157, "step": 937 }, { "epoch": 0.9510773130544994, "grad_norm": 2.9411909580230713, "learning_rate": 1.4018877420983956e-07, "loss": 2.3314, "step": 938 }, { "epoch": 0.9520912547528517, "grad_norm": 2.7778210639953613, "learning_rate": 1.3464979154364844e-07, "loss": 2.558, "step": 939 }, { "epoch": 0.9531051964512041, "grad_norm": 2.8902809619903564, "learning_rate": 1.2922170916280118e-07, "loss": 2.7303, "step": 940 }, { "epoch": 0.9541191381495564, "grad_norm": 2.9819915294647217, "learning_rate": 1.2390458808651085e-07, "loss": 2.2839, "step": 941 }, { "epoch": 0.9551330798479087, "grad_norm": 2.7157628536224365, "learning_rate": 1.186984880866271e-07, "loss": 2.5223, "step": 942 }, { "epoch": 0.9561470215462611, "grad_norm": 2.838313579559326, "learning_rate": 1.1360346768696907e-07, "loss": 2.4969, "step": 943 }, { "epoch": 0.9571609632446134, "grad_norm": 2.63149094581604, "learning_rate": 1.0861958416266805e-07, "loss": 2.8127, "step": 944 }, { "epoch": 0.9581749049429658, "grad_norm": 2.867000102996826, "learning_rate": 1.0374689353952027e-07, "loss": 2.5835, "step": 945 }, { "epoch": 0.9591888466413181, "grad_norm": 3.0157129764556885, "learning_rate": 9.898545059335852e-08, "loss": 2.4226, "step": 946 }, { "epoch": 0.9602027883396704, "grad_norm": 3.223989486694336, "learning_rate": 9.433530884943698e-08, "loss": 2.5887, "step": 947 }, { "epoch": 0.9612167300380228, "grad_norm": 2.9932541847229004, "learning_rate": 8.979652058183185e-08, "loss": 2.7176, "step": 948 }, { "epoch": 0.9622306717363751, "grad_norm": 3.0052859783172607, "learning_rate": 8.536913681284731e-08, "loss": 2.3166, "step": 949 }, { "epoch": 0.9632446134347274, "grad_norm": 2.8431527614593506, "learning_rate": 8.105320731244703e-08, "loss": 2.2966, "step": 950 }, { "epoch": 0.9642585551330799, "grad_norm": 2.9385998249053955, "learning_rate": 7.684878059769363e-08, "loss": 2.7675, "step": 951 }, { "epoch": 0.9652724968314322, "grad_norm": 2.7830967903137207, "learning_rate": 7.275590393220456e-08, "loss": 2.5262, "step": 952 }, { "epoch": 0.9662864385297846, "grad_norm": 2.4871981143951416, "learning_rate": 6.877462332561479e-08, "loss": 2.4801, "step": 953 }, { "epoch": 0.9673003802281369, "grad_norm": 3.1035871505737305, "learning_rate": 6.49049835330684e-08, "loss": 2.6659, "step": 954 }, { "epoch": 0.9683143219264893, "grad_norm": 2.684152603149414, "learning_rate": 6.114702805471107e-08, "loss": 2.6706, "step": 955 }, { "epoch": 0.9693282636248416, "grad_norm": 2.5241572856903076, "learning_rate": 5.750079913519835e-08, "loss": 2.6851, "step": 956 }, { "epoch": 0.9703422053231939, "grad_norm": 2.860586166381836, "learning_rate": 5.3966337763223795e-08, "loss": 2.8105, "step": 957 }, { "epoch": 0.9713561470215463, "grad_norm": 2.7309417724609375, "learning_rate": 5.054368367106044e-08, "loss": 2.4778, "step": 958 }, { "epoch": 0.9723700887198986, "grad_norm": 2.763823986053467, "learning_rate": 4.723287533411003e-08, "loss": 2.6899, "step": 959 }, { "epoch": 0.973384030418251, "grad_norm": 3.758967399597168, "learning_rate": 4.403394997047339e-08, "loss": 2.6874, "step": 960 }, { "epoch": 0.9743979721166033, "grad_norm": 2.725534200668335, "learning_rate": 4.094694354052742e-08, "loss": 2.4807, "step": 961 }, { "epoch": 0.9754119138149556, "grad_norm": 2.951953172683716, "learning_rate": 3.797189074652874e-08, "loss": 2.7076, "step": 962 }, { "epoch": 0.976425855513308, "grad_norm": 2.8677074909210205, "learning_rate": 3.5108825032217355e-08, "loss": 2.6133, "step": 963 }, { "epoch": 0.9774397972116603, "grad_norm": 2.856584310531616, "learning_rate": 3.235777858244027e-08, "loss": 2.733, "step": 964 }, { "epoch": 0.9784537389100126, "grad_norm": 2.748422622680664, "learning_rate": 2.9718782322794015e-08, "loss": 2.5125, "step": 965 }, { "epoch": 0.979467680608365, "grad_norm": 2.9938743114471436, "learning_rate": 2.719186591927603e-08, "loss": 2.5371, "step": 966 }, { "epoch": 0.9804816223067173, "grad_norm": 3.208367109298706, "learning_rate": 2.4777057777946034e-08, "loss": 2.5367, "step": 967 }, { "epoch": 0.9814955640050697, "grad_norm": 2.9483325481414795, "learning_rate": 2.2474385044615188e-08, "loss": 2.4301, "step": 968 }, { "epoch": 0.9825095057034221, "grad_norm": 2.8662376403808594, "learning_rate": 2.028387360453188e-08, "loss": 2.4986, "step": 969 }, { "epoch": 0.9835234474017744, "grad_norm": 2.7627525329589844, "learning_rate": 1.8205548082099733e-08, "loss": 2.353, "step": 970 }, { "epoch": 0.9845373891001268, "grad_norm": 2.735853910446167, "learning_rate": 1.623943184059229e-08, "loss": 2.9126, "step": 971 }, { "epoch": 0.9855513307984791, "grad_norm": 2.9360198974609375, "learning_rate": 1.4385546981897647e-08, "loss": 2.3977, "step": 972 }, { "epoch": 0.9865652724968315, "grad_norm": 3.8521199226379395, "learning_rate": 1.264391434626533e-08, "loss": 2.6582, "step": 973 }, { "epoch": 0.9875792141951838, "grad_norm": 2.916172981262207, "learning_rate": 1.1014553512072036e-08, "loss": 2.4163, "step": 974 }, { "epoch": 0.9885931558935361, "grad_norm": 2.8792824745178223, "learning_rate": 9.49748279560514e-09, "loss": 2.369, "step": 975 }, { "epoch": 0.9896070975918885, "grad_norm": 2.9305737018585205, "learning_rate": 8.092719250853975e-09, "loss": 2.5004, "step": 976 }, { "epoch": 0.9906210392902408, "grad_norm": 2.9403040409088135, "learning_rate": 6.800278669317762e-09, "loss": 2.4728, "step": 977 }, { "epoch": 0.9916349809885932, "grad_norm": 2.7486960887908936, "learning_rate": 5.6201755798313e-09, "loss": 2.6734, "step": 978 }, { "epoch": 0.9926489226869455, "grad_norm": 2.7036991119384766, "learning_rate": 4.55242324839622e-09, "loss": 2.7176, "step": 979 }, { "epoch": 0.9936628643852978, "grad_norm": 2.9134089946746826, "learning_rate": 3.597033678038875e-09, "loss": 2.6166, "step": 980 }, { "epoch": 0.9946768060836502, "grad_norm": 3.0970189571380615, "learning_rate": 2.7540176086671145e-09, "loss": 2.4814, "step": 981 }, { "epoch": 0.9956907477820025, "grad_norm": 2.951559066772461, "learning_rate": 2.02338451695816e-09, "loss": 2.4173, "step": 982 }, { "epoch": 0.9967046894803548, "grad_norm": 2.8410286903381348, "learning_rate": 1.4051426162464687e-09, "loss": 2.7181, "step": 983 }, { "epoch": 0.9977186311787072, "grad_norm": 2.9073750972747803, "learning_rate": 8.992988564315852e-10, "loss": 2.7888, "step": 984 }, { "epoch": 0.9987325728770595, "grad_norm": 2.890777826309204, "learning_rate": 5.058589239026468e-10, "loss": 2.5691, "step": 985 }, { "epoch": 0.9997465145754119, "grad_norm": 2.7914986610412598, "learning_rate": 2.2482724147177005e-10, "loss": 2.6085, "step": 986 }, { "epoch": 1.0, "grad_norm": 7.341601371765137, "learning_rate": 5.620696832964179e-11, "loss": 1.953, "step": 987 } ], "logging_steps": 1, "max_steps": 987, "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": 6.404770150455706e+16, "train_batch_size": 6, "trial_name": null, "trial_params": null }