{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 2.0, "eval_steps": 500, "global_step": 2668, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0074990626171728535, "grad_norm": 155.28665254983696, "learning_rate": 1.111111111111111e-06, "loss": 1.9242, "step": 10 }, { "epoch": 0.014998125234345707, "grad_norm": 3.362258749516982, "learning_rate": 2.345679012345679e-06, "loss": 0.4378, "step": 20 }, { "epoch": 0.02249718785151856, "grad_norm": 2.831646536056193, "learning_rate": 3.580246913580247e-06, "loss": 0.0713, "step": 30 }, { "epoch": 0.029996250468691414, "grad_norm": 1.5621813736172037, "learning_rate": 4.814814814814815e-06, "loss": 0.0697, "step": 40 }, { "epoch": 0.03749531308586427, "grad_norm": 1.7344974736350776, "learning_rate": 6.049382716049383e-06, "loss": 0.0553, "step": 50 }, { "epoch": 0.04499437570303712, "grad_norm": 2.6386561576263934, "learning_rate": 7.283950617283952e-06, "loss": 0.0521, "step": 60 }, { "epoch": 0.05249343832020997, "grad_norm": 1.9147932291225627, "learning_rate": 8.518518518518519e-06, "loss": 0.053, "step": 70 }, { "epoch": 0.05999250093738283, "grad_norm": 3.3120020183007552, "learning_rate": 9.753086419753087e-06, "loss": 0.056, "step": 80 }, { "epoch": 0.06749156355455568, "grad_norm": 1.161380801138399, "learning_rate": 9.999764048113049e-06, "loss": 0.0457, "step": 90 }, { "epoch": 0.07499062617172854, "grad_norm": 1.024618818632747, "learning_rate": 9.998805531738831e-06, "loss": 0.0576, "step": 100 }, { "epoch": 0.0824896887889014, "grad_norm": 1.3408518766249093, "learning_rate": 9.99710984512739e-06, "loss": 0.0462, "step": 110 }, { "epoch": 0.08998875140607424, "grad_norm": 1.9136454297663925, "learning_rate": 9.994677238340407e-06, "loss": 0.0666, "step": 120 }, { "epoch": 0.09748781402324709, "grad_norm": 1.1077114177900125, "learning_rate": 9.991508070112645e-06, "loss": 0.0546, "step": 130 }, { "epoch": 0.10498687664041995, "grad_norm": 0.8659649657637791, "learning_rate": 9.987602807799048e-06, "loss": 0.0587, "step": 140 }, { "epoch": 0.1124859392575928, "grad_norm": 1.676921466244982, "learning_rate": 9.982962027305828e-06, "loss": 0.0477, "step": 150 }, { "epoch": 0.11998500187476566, "grad_norm": 1.4567007464131139, "learning_rate": 9.97758641300553e-06, "loss": 0.045, "step": 160 }, { "epoch": 0.1274840644919385, "grad_norm": 1.5446297494141707, "learning_rate": 9.971476757636106e-06, "loss": 0.0563, "step": 170 }, { "epoch": 0.13498312710911137, "grad_norm": 0.940205068836968, "learning_rate": 9.964633962184017e-06, "loss": 0.0445, "step": 180 }, { "epoch": 0.1424821897262842, "grad_norm": 0.6646370859905596, "learning_rate": 9.957059035751358e-06, "loss": 0.0486, "step": 190 }, { "epoch": 0.14998125234345708, "grad_norm": 1.6203365044428508, "learning_rate": 9.948753095407054e-06, "loss": 0.052, "step": 200 }, { "epoch": 0.15748031496062992, "grad_norm": 0.5890735741759071, "learning_rate": 9.93971736602212e-06, "loss": 0.0497, "step": 210 }, { "epoch": 0.1649793775778028, "grad_norm": 0.8121545619172544, "learning_rate": 9.92995318008904e-06, "loss": 0.0411, "step": 220 }, { "epoch": 0.17247844019497563, "grad_norm": 1.235756862042735, "learning_rate": 9.91946197752525e-06, "loss": 0.0463, "step": 230 }, { "epoch": 0.17997750281214847, "grad_norm": 1.117510228165351, "learning_rate": 9.908245305460802e-06, "loss": 0.0506, "step": 240 }, { "epoch": 0.18747656542932134, "grad_norm": 0.9227556935119661, "learning_rate": 9.896304818010222e-06, "loss": 0.0544, "step": 250 }, { "epoch": 0.19497562804649418, "grad_norm": 0.9516318298027734, "learning_rate": 9.883642276028555e-06, "loss": 0.0358, "step": 260 }, { "epoch": 0.20247469066366705, "grad_norm": 0.6291698708762183, "learning_rate": 9.870259546851715e-06, "loss": 0.0265, "step": 270 }, { "epoch": 0.2099737532808399, "grad_norm": 0.8307006617835949, "learning_rate": 9.856158604021094e-06, "loss": 0.0432, "step": 280 }, { "epoch": 0.21747281589801276, "grad_norm": 1.1289472435716672, "learning_rate": 9.841341526992536e-06, "loss": 0.0325, "step": 290 }, { "epoch": 0.2249718785151856, "grad_norm": 1.4392686825772976, "learning_rate": 9.825810500829678e-06, "loss": 0.0334, "step": 300 }, { "epoch": 0.23247094113235844, "grad_norm": 0.8025649829466946, "learning_rate": 9.809567815881715e-06, "loss": 0.0428, "step": 310 }, { "epoch": 0.2399700037495313, "grad_norm": 0.48061256880718023, "learning_rate": 9.792615867445655e-06, "loss": 0.0473, "step": 320 }, { "epoch": 0.24746906636670415, "grad_norm": 0.8197185615776427, "learning_rate": 9.774957155413071e-06, "loss": 0.0384, "step": 330 }, { "epoch": 0.254968128983877, "grad_norm": 0.8815824566152508, "learning_rate": 9.756594283901465e-06, "loss": 0.0423, "step": 340 }, { "epoch": 0.26246719160104987, "grad_norm": 0.7240015505953853, "learning_rate": 9.737529960870215e-06, "loss": 0.0387, "step": 350 }, { "epoch": 0.26996625421822273, "grad_norm": 0.7689575409780028, "learning_rate": 9.717766997721256e-06, "loss": 0.0357, "step": 360 }, { "epoch": 0.27746531683539555, "grad_norm": 1.0612146943234804, "learning_rate": 9.697308308884472e-06, "loss": 0.0359, "step": 370 }, { "epoch": 0.2849643794525684, "grad_norm": 0.916372018396697, "learning_rate": 9.676156911387912e-06, "loss": 0.0327, "step": 380 }, { "epoch": 0.2924634420697413, "grad_norm": 0.5795785034711894, "learning_rate": 9.654315924412876e-06, "loss": 0.0242, "step": 390 }, { "epoch": 0.29996250468691416, "grad_norm": 0.9712956804729805, "learning_rate": 9.631788568833912e-06, "loss": 0.0541, "step": 400 }, { "epoch": 0.30746156730408697, "grad_norm": 0.668855291828949, "learning_rate": 9.608578166743865e-06, "loss": 0.034, "step": 410 }, { "epoch": 0.31496062992125984, "grad_norm": 0.6036360569268154, "learning_rate": 9.584688140963945e-06, "loss": 0.0399, "step": 420 }, { "epoch": 0.3224596925384327, "grad_norm": 0.7866302936543449, "learning_rate": 9.560122014538979e-06, "loss": 0.0238, "step": 430 }, { "epoch": 0.3299587551556056, "grad_norm": 0.5459008639707915, "learning_rate": 9.53488341021787e-06, "loss": 0.032, "step": 440 }, { "epoch": 0.3374578177727784, "grad_norm": 1.2136740166931843, "learning_rate": 9.508976049919346e-06, "loss": 0.0274, "step": 450 }, { "epoch": 0.34495688038995126, "grad_norm": 1.2673016962719876, "learning_rate": 9.482403754183095e-06, "loss": 0.0475, "step": 460 }, { "epoch": 0.35245594300712413, "grad_norm": 0.5890698587442688, "learning_rate": 9.455170441606358e-06, "loss": 0.0325, "step": 470 }, { "epoch": 0.35995500562429694, "grad_norm": 1.1247549851875165, "learning_rate": 9.427280128266049e-06, "loss": 0.0357, "step": 480 }, { "epoch": 0.3674540682414698, "grad_norm": 0.5250807668490772, "learning_rate": 9.398736927126511e-06, "loss": 0.0439, "step": 490 }, { "epoch": 0.3749531308586427, "grad_norm": 0.06936603228572029, "learning_rate": 9.369545047432971e-06, "loss": 0.0281, "step": 500 }, { "epoch": 0.38245219347581555, "grad_norm": 0.6447872570778751, "learning_rate": 9.339708794090825e-06, "loss": 0.04, "step": 510 }, { "epoch": 0.38995125609298836, "grad_norm": 0.4172181910763122, "learning_rate": 9.309232567030777e-06, "loss": 0.0418, "step": 520 }, { "epoch": 0.39745031871016123, "grad_norm": 0.1952842768797085, "learning_rate": 9.278120860559996e-06, "loss": 0.0358, "step": 530 }, { "epoch": 0.4049493813273341, "grad_norm": 0.8408813478372549, "learning_rate": 9.246378262699335e-06, "loss": 0.037, "step": 540 }, { "epoch": 0.4124484439445069, "grad_norm": 1.4249842371948296, "learning_rate": 9.214009454506754e-06, "loss": 0.0313, "step": 550 }, { "epoch": 0.4199475065616798, "grad_norm": 0.6966406944891084, "learning_rate": 9.181019209386988e-06, "loss": 0.0299, "step": 560 }, { "epoch": 0.42744656917885265, "grad_norm": 0.785346730227587, "learning_rate": 9.14741239238763e-06, "loss": 0.046, "step": 570 }, { "epoch": 0.4349456317960255, "grad_norm": 0.7996662193987384, "learning_rate": 9.113193959481684e-06, "loss": 0.0394, "step": 580 }, { "epoch": 0.44244469441319834, "grad_norm": 0.6309499999410825, "learning_rate": 9.078368956836708e-06, "loss": 0.0391, "step": 590 }, { "epoch": 0.4499437570303712, "grad_norm": 1.3467253518824047, "learning_rate": 9.04294252007066e-06, "loss": 0.0363, "step": 600 }, { "epoch": 0.4574428196475441, "grad_norm": 0.2919866713932631, "learning_rate": 9.006919873494553e-06, "loss": 0.0296, "step": 610 }, { "epoch": 0.4649418822647169, "grad_norm": 0.20177472779291208, "learning_rate": 8.970306329342033e-06, "loss": 0.0258, "step": 620 }, { "epoch": 0.47244094488188976, "grad_norm": 0.5973151461239269, "learning_rate": 8.933107286985977e-06, "loss": 0.0489, "step": 630 }, { "epoch": 0.4799400074990626, "grad_norm": 0.5871613572754036, "learning_rate": 8.895328232142269e-06, "loss": 0.0273, "step": 640 }, { "epoch": 0.4874390701162355, "grad_norm": 0.3808200172704599, "learning_rate": 8.856974736060805e-06, "loss": 0.0325, "step": 650 }, { "epoch": 0.4949381327334083, "grad_norm": 0.6862380697653905, "learning_rate": 8.81805245470392e-06, "loss": 0.0416, "step": 660 }, { "epoch": 0.5024371953505812, "grad_norm": 0.678148386185624, "learning_rate": 8.778567127912304e-06, "loss": 0.0427, "step": 670 }, { "epoch": 0.509936257967754, "grad_norm": 0.34892911586475395, "learning_rate": 8.738524578558547e-06, "loss": 0.0385, "step": 680 }, { "epoch": 0.5174353205849269, "grad_norm": 0.6807325750288069, "learning_rate": 8.697930711688447e-06, "loss": 0.0314, "step": 690 }, { "epoch": 0.5249343832020997, "grad_norm": 0.9156711144112105, "learning_rate": 8.656791513650198e-06, "loss": 0.0501, "step": 700 }, { "epoch": 0.5324334458192725, "grad_norm": 1.138715112396131, "learning_rate": 8.61511305121159e-06, "loss": 0.0278, "step": 710 }, { "epoch": 0.5399325084364455, "grad_norm": 0.9524196740213979, "learning_rate": 8.572901470665341e-06, "loss": 0.0362, "step": 720 }, { "epoch": 0.5474315710536183, "grad_norm": 1.1003737820266235, "learning_rate": 8.530162996922713e-06, "loss": 0.0327, "step": 730 }, { "epoch": 0.5549306336707911, "grad_norm": 0.4047087136451081, "learning_rate": 8.486903932595523e-06, "loss": 0.0329, "step": 740 }, { "epoch": 0.562429696287964, "grad_norm": 0.9415841939289905, "learning_rate": 8.443130657066707e-06, "loss": 0.0405, "step": 750 }, { "epoch": 0.5699287589051368, "grad_norm": 0.21632775513294392, "learning_rate": 8.398849625549558e-06, "loss": 0.0229, "step": 760 }, { "epoch": 0.5774278215223098, "grad_norm": 0.7441650531813314, "learning_rate": 8.354067368135777e-06, "loss": 0.0351, "step": 770 }, { "epoch": 0.5849268841394826, "grad_norm": 0.788679726979746, "learning_rate": 8.308790488832479e-06, "loss": 0.0356, "step": 780 }, { "epoch": 0.5924259467566554, "grad_norm": 0.6615010831412275, "learning_rate": 8.263025664588317e-06, "loss": 0.0357, "step": 790 }, { "epoch": 0.5999250093738283, "grad_norm": 0.9494758890507249, "learning_rate": 8.216779644308832e-06, "loss": 0.0311, "step": 800 }, { "epoch": 0.6074240719910011, "grad_norm": 0.7439179434432698, "learning_rate": 8.170059247861194e-06, "loss": 0.0319, "step": 810 }, { "epoch": 0.6149231346081739, "grad_norm": 0.4488228809119636, "learning_rate": 8.122871365068485e-06, "loss": 0.0395, "step": 820 }, { "epoch": 0.6224221972253469, "grad_norm": 1.2633381855505956, "learning_rate": 8.07522295469366e-06, "loss": 0.0342, "step": 830 }, { "epoch": 0.6299212598425197, "grad_norm": 0.5755472347583738, "learning_rate": 8.027121043413344e-06, "loss": 0.0289, "step": 840 }, { "epoch": 0.6374203224596925, "grad_norm": 0.5677066133831751, "learning_rate": 7.97857272478161e-06, "loss": 0.0231, "step": 850 }, { "epoch": 0.6449193850768654, "grad_norm": 0.45691776726403416, "learning_rate": 7.929585158183903e-06, "loss": 0.0321, "step": 860 }, { "epoch": 0.6524184476940382, "grad_norm": 0.913650230759926, "learning_rate": 7.880165567781245e-06, "loss": 0.0271, "step": 870 }, { "epoch": 0.6599175103112112, "grad_norm": 1.2159880827927547, "learning_rate": 7.830321241444905e-06, "loss": 0.0464, "step": 880 }, { "epoch": 0.667416572928384, "grad_norm": 0.5961909993096214, "learning_rate": 7.780059529681638e-06, "loss": 0.0359, "step": 890 }, { "epoch": 0.6749156355455568, "grad_norm": 0.9940584102100111, "learning_rate": 7.72938784454974e-06, "loss": 0.0311, "step": 900 }, { "epoch": 0.6824146981627297, "grad_norm": 1.0150428017252482, "learning_rate": 7.678313658565976e-06, "loss": 0.0445, "step": 910 }, { "epoch": 0.6899137607799025, "grad_norm": 0.8977759875123367, "learning_rate": 7.626844503603621e-06, "loss": 0.0323, "step": 920 }, { "epoch": 0.6974128233970753, "grad_norm": 0.5967876938950674, "learning_rate": 7.574987969781744e-06, "loss": 0.0221, "step": 930 }, { "epoch": 0.7049118860142483, "grad_norm": 1.0893638558798928, "learning_rate": 7.522751704345888e-06, "loss": 0.039, "step": 940 }, { "epoch": 0.7124109486314211, "grad_norm": 0.8481844582027183, "learning_rate": 7.470143410540347e-06, "loss": 0.0327, "step": 950 }, { "epoch": 0.7199100112485939, "grad_norm": 0.7557586268535357, "learning_rate": 7.4171708464721694e-06, "loss": 0.0355, "step": 960 }, { "epoch": 0.7274090738657668, "grad_norm": 0.7488921420210467, "learning_rate": 7.363841823967073e-06, "loss": 0.0425, "step": 970 }, { "epoch": 0.7349081364829396, "grad_norm": 0.718751333137861, "learning_rate": 7.310164207417448e-06, "loss": 0.0276, "step": 980 }, { "epoch": 0.7424071991001124, "grad_norm": 1.5008614111245941, "learning_rate": 7.25614591262259e-06, "loss": 0.0377, "step": 990 }, { "epoch": 0.7499062617172854, "grad_norm": 1.0099574286415736, "learning_rate": 7.201794905621374e-06, "loss": 0.0339, "step": 1000 }, { "epoch": 0.7574053243344582, "grad_norm": 0.8461039086905692, "learning_rate": 7.147119201517504e-06, "loss": 0.0328, "step": 1010 }, { "epoch": 0.7649043869516311, "grad_norm": 1.309690222450984, "learning_rate": 7.092126863297528e-06, "loss": 0.0412, "step": 1020 }, { "epoch": 0.7724034495688039, "grad_norm": 0.7995021674203338, "learning_rate": 7.036826000641801e-06, "loss": 0.0371, "step": 1030 }, { "epoch": 0.7799025121859767, "grad_norm": 0.8345118833173178, "learning_rate": 6.981224768728549e-06, "loss": 0.0252, "step": 1040 }, { "epoch": 0.7874015748031497, "grad_norm": 1.0150825448912708, "learning_rate": 6.925331367031241e-06, "loss": 0.0311, "step": 1050 }, { "epoch": 0.7949006374203225, "grad_norm": 0.7428758840727825, "learning_rate": 6.869154038109407e-06, "loss": 0.0384, "step": 1060 }, { "epoch": 0.8023997000374953, "grad_norm": 0.4459417200782627, "learning_rate": 6.8127010663931235e-06, "loss": 0.0288, "step": 1070 }, { "epoch": 0.8098987626546682, "grad_norm": 0.857285596187461, "learning_rate": 6.7559807769613095e-06, "loss": 0.027, "step": 1080 }, { "epoch": 0.817397825271841, "grad_norm": 0.5516682134477396, "learning_rate": 6.699001534314034e-06, "loss": 0.0333, "step": 1090 }, { "epoch": 0.8248968878890138, "grad_norm": 0.49819700310566756, "learning_rate": 6.641771741139011e-06, "loss": 0.0293, "step": 1100 }, { "epoch": 0.8323959505061868, "grad_norm": 0.8380004964515851, "learning_rate": 6.584299837072457e-06, "loss": 0.0341, "step": 1110 }, { "epoch": 0.8398950131233596, "grad_norm": 0.9193065052537274, "learning_rate": 6.526594297454505e-06, "loss": 0.0326, "step": 1120 }, { "epoch": 0.8473940757405324, "grad_norm": 0.9718704060771279, "learning_rate": 6.468663632079362e-06, "loss": 0.0359, "step": 1130 }, { "epoch": 0.8548931383577053, "grad_norm": 0.5481518437756783, "learning_rate": 6.410516383940357e-06, "loss": 0.0311, "step": 1140 }, { "epoch": 0.8623922009748781, "grad_norm": 0.5473864901903696, "learning_rate": 6.352161127970132e-06, "loss": 0.0333, "step": 1150 }, { "epoch": 0.869891263592051, "grad_norm": 0.4270954594394896, "learning_rate": 6.29360646977609e-06, "loss": 0.0227, "step": 1160 }, { "epoch": 0.8773903262092239, "grad_norm": 0.5634725176055181, "learning_rate": 6.234861044371331e-06, "loss": 0.0289, "step": 1170 }, { "epoch": 0.8848893888263967, "grad_norm": 0.86129333437104, "learning_rate": 6.175933514901263e-06, "loss": 0.0224, "step": 1180 }, { "epoch": 0.8923884514435696, "grad_norm": 1.0522496643038515, "learning_rate": 6.11683257136605e-06, "loss": 0.029, "step": 1190 }, { "epoch": 0.8998875140607424, "grad_norm": 0.8512061402211971, "learning_rate": 6.057566929339096e-06, "loss": 0.0326, "step": 1200 }, { "epoch": 0.9073865766779152, "grad_norm": 0.6674435023070615, "learning_rate": 5.9981453286817805e-06, "loss": 0.0405, "step": 1210 }, { "epoch": 0.9148856392950881, "grad_norm": 0.6092238375718538, "learning_rate": 5.938576532254585e-06, "loss": 0.0295, "step": 1220 }, { "epoch": 0.922384701912261, "grad_norm": 0.5529179473406505, "learning_rate": 5.878869324624845e-06, "loss": 0.0324, "step": 1230 }, { "epoch": 0.9298837645294338, "grad_norm": 0.5290133549210636, "learning_rate": 5.819032510771297e-06, "loss": 0.031, "step": 1240 }, { "epoch": 0.9373828271466067, "grad_norm": 0.6959203591181496, "learning_rate": 5.759074914785613e-06, "loss": 0.0305, "step": 1250 }, { "epoch": 0.9448818897637795, "grad_norm": 0.2866211665736003, "learning_rate": 5.699005378571118e-06, "loss": 0.0229, "step": 1260 }, { "epoch": 0.9523809523809523, "grad_norm": 1.1975314249356448, "learning_rate": 5.638832760538883e-06, "loss": 0.0366, "step": 1270 }, { "epoch": 0.9598800149981253, "grad_norm": 0.9933876835976754, "learning_rate": 5.57856593430138e-06, "loss": 0.0284, "step": 1280 }, { "epoch": 0.9673790776152981, "grad_norm": 0.7921164178929744, "learning_rate": 5.518213787363896e-06, "loss": 0.0245, "step": 1290 }, { "epoch": 0.974878140232471, "grad_norm": 1.2691607728017158, "learning_rate": 5.457785219813898e-06, "loss": 0.035, "step": 1300 }, { "epoch": 0.9823772028496438, "grad_norm": 0.8625218572408476, "learning_rate": 5.397289143008552e-06, "loss": 0.0277, "step": 1310 }, { "epoch": 0.9898762654668166, "grad_norm": 0.7780515583979966, "learning_rate": 5.3367344782605575e-06, "loss": 0.0264, "step": 1320 }, { "epoch": 0.9973753280839895, "grad_norm": 0.3785645610181852, "learning_rate": 5.276130155522541e-06, "loss": 0.0316, "step": 1330 }, { "epoch": 1.0044994375703038, "grad_norm": 0.7620934902827466, "learning_rate": 5.215485112070155e-06, "loss": 0.0379, "step": 1340 }, { "epoch": 1.0119985001874765, "grad_norm": 0.29336780806674495, "learning_rate": 5.154808291184106e-06, "loss": 0.0254, "step": 1350 }, { "epoch": 1.0194975628046494, "grad_norm": 0.607356731223823, "learning_rate": 5.0941086408312934e-06, "loss": 0.0272, "step": 1360 }, { "epoch": 1.0269966254218224, "grad_norm": 0.7042597525474166, "learning_rate": 5.033395112345265e-06, "loss": 0.0284, "step": 1370 }, { "epoch": 1.034495688038995, "grad_norm": 0.3658551802356145, "learning_rate": 4.972676659106168e-06, "loss": 0.0199, "step": 1380 }, { "epoch": 1.041994750656168, "grad_norm": 1.160332898445305, "learning_rate": 4.911962235220395e-06, "loss": 0.0237, "step": 1390 }, { "epoch": 1.049493813273341, "grad_norm": 0.2955411320601641, "learning_rate": 4.8512607942001364e-06, "loss": 0.0262, "step": 1400 }, { "epoch": 1.0569928758905136, "grad_norm": 0.5620840027387812, "learning_rate": 4.7905812876430055e-06, "loss": 0.0249, "step": 1410 }, { "epoch": 1.0644919385076865, "grad_norm": 0.8224546267693695, "learning_rate": 4.7299326639119595e-06, "loss": 0.0237, "step": 1420 }, { "epoch": 1.0719910011248595, "grad_norm": 0.9932593274792849, "learning_rate": 4.669323866815685e-06, "loss": 0.0265, "step": 1430 }, { "epoch": 1.0794900637420322, "grad_norm": 0.887817835984614, "learning_rate": 4.608763834289667e-06, "loss": 0.0271, "step": 1440 }, { "epoch": 1.086989126359205, "grad_norm": 0.7886269299714586, "learning_rate": 4.548261497078109e-06, "loss": 0.0324, "step": 1450 }, { "epoch": 1.094488188976378, "grad_norm": 1.3444875248864863, "learning_rate": 4.4878257774169345e-06, "loss": 0.0313, "step": 1460 }, { "epoch": 1.1019872515935507, "grad_norm": 0.593542071000921, "learning_rate": 4.427465587718021e-06, "loss": 0.0246, "step": 1470 }, { "epoch": 1.1094863142107236, "grad_norm": 0.5885085022445967, "learning_rate": 4.3671898292548965e-06, "loss": 0.024, "step": 1480 }, { "epoch": 1.1169853768278966, "grad_norm": 0.42942288605303675, "learning_rate": 4.307007390850078e-06, "loss": 0.0287, "step": 1490 }, { "epoch": 1.1244844394450695, "grad_norm": 0.585086124425167, "learning_rate": 4.246927147564241e-06, "loss": 0.0274, "step": 1500 }, { "epoch": 1.1319835020622422, "grad_norm": 1.0512099727301292, "learning_rate": 4.186957959387421e-06, "loss": 0.0284, "step": 1510 }, { "epoch": 1.139482564679415, "grad_norm": 0.4678702656704095, "learning_rate": 4.127108669932435e-06, "loss": 0.0264, "step": 1520 }, { "epoch": 1.1469816272965878, "grad_norm": 0.02504754453116866, "learning_rate": 4.067388105130721e-06, "loss": 0.0197, "step": 1530 }, { "epoch": 1.1544806899137607, "grad_norm": 0.6534257230713213, "learning_rate": 4.0078050719307895e-06, "loss": 0.0253, "step": 1540 }, { "epoch": 1.1619797525309337, "grad_norm": 0.5858770109490005, "learning_rate": 3.948368356999462e-06, "loss": 0.0186, "step": 1550 }, { "epoch": 1.1694788151481066, "grad_norm": 0.8051772700283486, "learning_rate": 3.889086725426112e-06, "loss": 0.0265, "step": 1560 }, { "epoch": 1.1769778777652793, "grad_norm": 0.729821216683295, "learning_rate": 3.829968919430085e-06, "loss": 0.0195, "step": 1570 }, { "epoch": 1.1844769403824522, "grad_norm": 0.7350444945493317, "learning_rate": 3.771023657071481e-06, "loss": 0.0271, "step": 1580 }, { "epoch": 1.1919760029996251, "grad_norm": 1.0257836164894436, "learning_rate": 3.712259630965518e-06, "loss": 0.0355, "step": 1590 }, { "epoch": 1.1994750656167978, "grad_norm": 1.092442924497701, "learning_rate": 3.6536855070006356e-06, "loss": 0.0227, "step": 1600 }, { "epoch": 1.2069741282339708, "grad_norm": 0.6582585131288117, "learning_rate": 3.59530992306054e-06, "loss": 0.0269, "step": 1610 }, { "epoch": 1.2144731908511437, "grad_norm": 0.9368405995653466, "learning_rate": 3.5371414877503863e-06, "loss": 0.0288, "step": 1620 }, { "epoch": 1.2219722534683164, "grad_norm": 0.7428211370087358, "learning_rate": 3.4791887791272694e-06, "loss": 0.021, "step": 1630 }, { "epoch": 1.2294713160854893, "grad_norm": 1.0168773047570854, "learning_rate": 3.421460343435223e-06, "loss": 0.0342, "step": 1640 }, { "epoch": 1.2369703787026622, "grad_norm": 1.1714716424240927, "learning_rate": 3.3639646938449167e-06, "loss": 0.0303, "step": 1650 }, { "epoch": 1.244469441319835, "grad_norm": 0.9469491677719571, "learning_rate": 3.306710309198223e-06, "loss": 0.0226, "step": 1660 }, { "epoch": 1.2519685039370079, "grad_norm": 0.7154981642683208, "learning_rate": 3.249705632757846e-06, "loss": 0.0295, "step": 1670 }, { "epoch": 1.2594675665541808, "grad_norm": 0.6721033014226055, "learning_rate": 3.1929590709622e-06, "loss": 0.0237, "step": 1680 }, { "epoch": 1.2669666291713535, "grad_norm": 0.6096739033180646, "learning_rate": 3.136478992185723e-06, "loss": 0.0275, "step": 1690 }, { "epoch": 1.2744656917885264, "grad_norm": 0.5868533026592397, "learning_rate": 3.08027372550479e-06, "loss": 0.0213, "step": 1700 }, { "epoch": 1.2819647544056993, "grad_norm": 0.6104038648526199, "learning_rate": 3.0243515594694375e-06, "loss": 0.0246, "step": 1710 }, { "epoch": 1.289463817022872, "grad_norm": 0.6820744511372772, "learning_rate": 2.968720740881056e-06, "loss": 0.0349, "step": 1720 }, { "epoch": 1.296962879640045, "grad_norm": 0.7739599424922933, "learning_rate": 2.9133894735762375e-06, "loss": 0.0241, "step": 1730 }, { "epoch": 1.304461942257218, "grad_norm": 0.5574710632213771, "learning_rate": 2.85836591721696e-06, "loss": 0.0264, "step": 1740 }, { "epoch": 1.3119610048743908, "grad_norm": 0.8045526136243909, "learning_rate": 2.8036581860872953e-06, "loss": 0.0266, "step": 1750 }, { "epoch": 1.3194600674915635, "grad_norm": 1.2531122590655264, "learning_rate": 2.749274347896794e-06, "loss": 0.025, "step": 1760 }, { "epoch": 1.3269591301087365, "grad_norm": 0.7493353641725026, "learning_rate": 2.6952224225907503e-06, "loss": 0.0229, "step": 1770 }, { "epoch": 1.3344581927259092, "grad_norm": 0.6371123884589687, "learning_rate": 2.6415103811675053e-06, "loss": 0.0229, "step": 1780 }, { "epoch": 1.341957255343082, "grad_norm": 0.6859171205888811, "learning_rate": 2.58814614450297e-06, "loss": 0.0191, "step": 1790 }, { "epoch": 1.349456317960255, "grad_norm": 0.704905847653705, "learning_rate": 2.5351375821825376e-06, "loss": 0.0332, "step": 1800 }, { "epoch": 1.356955380577428, "grad_norm": 0.7714378701271534, "learning_rate": 2.482492511340564e-06, "loss": 0.0274, "step": 1810 }, { "epoch": 1.3644544431946006, "grad_norm": 0.769576770946243, "learning_rate": 2.430218695507581e-06, "loss": 0.0281, "step": 1820 }, { "epoch": 1.3719535058117736, "grad_norm": 0.816547670817867, "learning_rate": 2.37832384346541e-06, "loss": 0.0217, "step": 1830 }, { "epoch": 1.3794525684289463, "grad_norm": 0.7080288850255104, "learning_rate": 2.3268156081103597e-06, "loss": 0.0201, "step": 1840 }, { "epoch": 1.3869516310461192, "grad_norm": 0.7433400666651706, "learning_rate": 2.2757015853246493e-06, "loss": 0.0263, "step": 1850 }, { "epoch": 1.394450693663292, "grad_norm": 0.89359502651739, "learning_rate": 2.2249893128562614e-06, "loss": 0.0362, "step": 1860 }, { "epoch": 1.401949756280465, "grad_norm": 1.0058093010060205, "learning_rate": 2.1746862692073488e-06, "loss": 0.0228, "step": 1870 }, { "epoch": 1.4094488188976377, "grad_norm": 0.9198703570261983, "learning_rate": 2.1247998725313835e-06, "loss": 0.0276, "step": 1880 }, { "epoch": 1.4169478815148107, "grad_norm": 0.7133547263420038, "learning_rate": 2.0753374795392122e-06, "loss": 0.0229, "step": 1890 }, { "epoch": 1.4244469441319836, "grad_norm": 1.1063175065381492, "learning_rate": 2.0263063844141647e-06, "loss": 0.0275, "step": 1900 }, { "epoch": 1.4319460067491563, "grad_norm": 0.33588809125453883, "learning_rate": 1.9777138177363844e-06, "loss": 0.0215, "step": 1910 }, { "epoch": 1.4394450693663292, "grad_norm": 0.45638106784958116, "learning_rate": 1.9295669454165432e-06, "loss": 0.0159, "step": 1920 }, { "epoch": 1.4469441319835021, "grad_norm": 0.5351801295171318, "learning_rate": 1.881872867639089e-06, "loss": 0.0257, "step": 1930 }, { "epoch": 1.4544431946006748, "grad_norm": 0.7558859788462811, "learning_rate": 1.8346386178151843e-06, "loss": 0.0248, "step": 1940 }, { "epoch": 1.4619422572178478, "grad_norm": 0.23778680392401053, "learning_rate": 1.7878711615454957e-06, "loss": 0.0246, "step": 1950 }, { "epoch": 1.4694413198350207, "grad_norm": 0.42174383426805, "learning_rate": 1.7415773955929854e-06, "loss": 0.0228, "step": 1960 }, { "epoch": 1.4769403824521934, "grad_norm": 0.7513464393079531, "learning_rate": 1.6957641468658404e-06, "loss": 0.031, "step": 1970 }, { "epoch": 1.4844394450693663, "grad_norm": 0.7347883084390118, "learning_rate": 1.6504381714107254e-06, "loss": 0.0255, "step": 1980 }, { "epoch": 1.4919385076865392, "grad_norm": 0.44775654642785795, "learning_rate": 1.605606153416467e-06, "loss": 0.0235, "step": 1990 }, { "epoch": 1.4994375703037122, "grad_norm": 1.291594215640522, "learning_rate": 1.5612747042283405e-06, "loss": 0.0269, "step": 2000 }, { "epoch": 1.5069366329208849, "grad_norm": 0.7582358109122407, "learning_rate": 1.5174503613731029e-06, "loss": 0.0237, "step": 2010 }, { "epoch": 1.5144356955380578, "grad_norm": 0.5576449502318991, "learning_rate": 1.4741395875949072e-06, "loss": 0.0242, "step": 2020 }, { "epoch": 1.5219347581552305, "grad_norm": 0.695920779808547, "learning_rate": 1.4313487699022444e-06, "loss": 0.0324, "step": 2030 }, { "epoch": 1.5294338207724034, "grad_norm": 0.8584859257106142, "learning_rate": 1.3890842186260589e-06, "loss": 0.0245, "step": 2040 }, { "epoch": 1.5369328833895763, "grad_norm": 0.6261347659173438, "learning_rate": 1.347352166489166e-06, "loss": 0.0228, "step": 2050 }, { "epoch": 1.5444319460067493, "grad_norm": 0.5742387509786766, "learning_rate": 1.3061587676871196e-06, "loss": 0.0262, "step": 2060 }, { "epoch": 1.551931008623922, "grad_norm": 0.4842318955788589, "learning_rate": 1.2655100969806539e-06, "loss": 0.0183, "step": 2070 }, { "epoch": 1.559430071241095, "grad_norm": 0.5454474791140284, "learning_rate": 1.2254121487998483e-06, "loss": 0.0278, "step": 2080 }, { "epoch": 1.5669291338582676, "grad_norm": 0.6902289389404713, "learning_rate": 1.1858708363601229e-06, "loss": 0.0208, "step": 2090 }, { "epoch": 1.5744281964754405, "grad_norm": 0.40763256559629907, "learning_rate": 1.1468919907902332e-06, "loss": 0.0265, "step": 2100 }, { "epoch": 1.5819272590926134, "grad_norm": 0.7420544282115911, "learning_rate": 1.1084813602723516e-06, "loss": 0.0266, "step": 2110 }, { "epoch": 1.5894263217097864, "grad_norm": 0.6757940051603476, "learning_rate": 1.070644609194385e-06, "loss": 0.0187, "step": 2120 }, { "epoch": 1.5969253843269593, "grad_norm": 0.496577248637528, "learning_rate": 1.0333873173146568e-06, "loss": 0.0206, "step": 2130 }, { "epoch": 1.604424446944132, "grad_norm": 0.4765315255970703, "learning_rate": 9.967149789390606e-07, "loss": 0.0227, "step": 2140 }, { "epoch": 1.6119235095613047, "grad_norm": 0.8010099915946336, "learning_rate": 9.60633002110819e-07, "loss": 0.0203, "step": 2150 }, { "epoch": 1.6194225721784776, "grad_norm": 0.7632623474920002, "learning_rate": 9.251467078129645e-07, "loss": 0.0242, "step": 2160 }, { "epoch": 1.6269216347956506, "grad_norm": 0.5120513583961543, "learning_rate": 8.902613291836587e-07, "loss": 0.022, "step": 2170 }, { "epoch": 1.6344206974128235, "grad_norm": 0.9050519954541316, "learning_rate": 8.559820107444622e-07, "loss": 0.03, "step": 2180 }, { "epoch": 1.6419197600299964, "grad_norm": 0.4102594991340787, "learning_rate": 8.223138076416798e-07, "loss": 0.0282, "step": 2190 }, { "epoch": 1.649418822647169, "grad_norm": 0.5468068221758551, "learning_rate": 7.892616849008761e-07, "loss": 0.0259, "step": 2200 }, { "epoch": 1.6569178852643418, "grad_norm": 0.3334842129500887, "learning_rate": 7.568305166946932e-07, "loss": 0.0222, "step": 2210 }, { "epoch": 1.6644169478815147, "grad_norm": 0.5435063563125567, "learning_rate": 7.250250856240565e-07, "loss": 0.02, "step": 2220 }, { "epoch": 1.6719160104986877, "grad_norm": 0.9639924640434693, "learning_rate": 6.938500820128879e-07, "loss": 0.0238, "step": 2230 }, { "epoch": 1.6794150731158606, "grad_norm": 0.9157205849475846, "learning_rate": 6.633101032164274e-07, "loss": 0.0195, "step": 2240 }, { "epoch": 1.6869141357330335, "grad_norm": 0.5589681211648014, "learning_rate": 6.33409652943266e-07, "loss": 0.0262, "step": 2250 }, { "epoch": 1.6944131983502062, "grad_norm": 1.166355501161183, "learning_rate": 6.041531405911849e-07, "loss": 0.0262, "step": 2260 }, { "epoch": 1.7019122609673791, "grad_norm": 0.9160009257258491, "learning_rate": 5.755448805969055e-07, "loss": 0.0282, "step": 2270 }, { "epoch": 1.7094113235845518, "grad_norm": 0.8133397515189339, "learning_rate": 5.475890917998428e-07, "loss": 0.0152, "step": 2280 }, { "epoch": 1.7169103862017248, "grad_norm": 0.5062514510614812, "learning_rate": 5.202898968199566e-07, "loss": 0.0223, "step": 2290 }, { "epoch": 1.7244094488188977, "grad_norm": 0.08473215633159845, "learning_rate": 4.936513214497918e-07, "loss": 0.0197, "step": 2300 }, { "epoch": 1.7319085114360706, "grad_norm": 0.5383219207425006, "learning_rate": 4.67677294060796e-07, "loss": 0.0194, "step": 2310 }, { "epoch": 1.7394075740532433, "grad_norm": 0.9598442304932463, "learning_rate": 4.423716450240062e-07, "loss": 0.0214, "step": 2320 }, { "epoch": 1.7469066366704162, "grad_norm": 0.31299575069443586, "learning_rate": 4.1773810614518795e-07, "loss": 0.024, "step": 2330 }, { "epoch": 1.754405699287589, "grad_norm": 0.630022009368115, "learning_rate": 3.9378031011450825e-07, "loss": 0.021, "step": 2340 }, { "epoch": 1.7619047619047619, "grad_norm": 0.13672535272747552, "learning_rate": 3.7050178997082297e-07, "loss": 0.0214, "step": 2350 }, { "epoch": 1.7694038245219348, "grad_norm": 0.566304342553695, "learning_rate": 3.479059785806677e-07, "loss": 0.022, "step": 2360 }, { "epoch": 1.7769028871391077, "grad_norm": 0.5480006505856806, "learning_rate": 3.259962081320084e-07, "loss": 0.0215, "step": 2370 }, { "epoch": 1.7844019497562804, "grad_norm": 0.9138677161065817, "learning_rate": 3.0477570964285e-07, "loss": 0.0247, "step": 2380 }, { "epoch": 1.7919010123734533, "grad_norm": 0.7532281955497285, "learning_rate": 2.842476124847615e-07, "loss": 0.02, "step": 2390 }, { "epoch": 1.799400074990626, "grad_norm": 0.7784718156745437, "learning_rate": 2.644149439213872e-07, "loss": 0.0187, "step": 2400 }, { "epoch": 1.806899137607799, "grad_norm": 0.6121232898382328, "learning_rate": 2.4528062866201907e-07, "loss": 0.0184, "step": 2410 }, { "epoch": 1.814398200224972, "grad_norm": 0.3237254818683585, "learning_rate": 2.2684748843029236e-07, "loss": 0.0198, "step": 2420 }, { "epoch": 1.8218972628421448, "grad_norm": 0.98847013191546, "learning_rate": 2.0911824154806916e-07, "loss": 0.0277, "step": 2430 }, { "epoch": 1.8293963254593177, "grad_norm": 0.4462032788583046, "learning_rate": 1.9209550253456723e-07, "loss": 0.0294, "step": 2440 }, { "epoch": 1.8368953880764904, "grad_norm": 0.8638215384228228, "learning_rate": 1.7578178172079963e-07, "loss": 0.0232, "step": 2450 }, { "epoch": 1.8443944506936631, "grad_norm": 0.6812447482944519, "learning_rate": 1.6017948487937974e-07, "loss": 0.0197, "step": 2460 }, { "epoch": 1.851893513310836, "grad_norm": 0.6887677360414736, "learning_rate": 1.4529091286973994e-07, "loss": 0.0133, "step": 2470 }, { "epoch": 1.859392575928009, "grad_norm": 0.09197389963501222, "learning_rate": 1.3111826129882932e-07, "loss": 0.019, "step": 2480 }, { "epoch": 1.866891638545182, "grad_norm": 0.4650442637426985, "learning_rate": 1.1766362019732691e-07, "loss": 0.0213, "step": 2490 }, { "epoch": 1.8743907011623548, "grad_norm": 0.8489264361424917, "learning_rate": 1.049289737114273e-07, "loss": 0.0231, "step": 2500 }, { "epoch": 1.8818897637795275, "grad_norm": 0.5043174431292045, "learning_rate": 9.291619981023959e-08, "loss": 0.0223, "step": 2510 }, { "epoch": 1.8893888263967002, "grad_norm": 0.5269949672026591, "learning_rate": 8.162707000884507e-08, "loss": 0.0151, "step": 2520 }, { "epoch": 1.8968878890138732, "grad_norm": 0.7079843382258325, "learning_rate": 7.106324910705175e-08, "loss": 0.0254, "step": 2530 }, { "epoch": 1.904386951631046, "grad_norm": 0.9008327398168677, "learning_rate": 6.122629494388966e-08, "loss": 0.0251, "step": 2540 }, { "epoch": 1.911886014248219, "grad_norm": 0.6329175493654771, "learning_rate": 5.2117658167877285e-08, "loss": 0.0139, "step": 2550 }, { "epoch": 1.919385076865392, "grad_norm": 0.6314369346331038, "learning_rate": 4.3738682023092285e-08, "loss": 0.0212, "step": 2560 }, { "epoch": 1.9268841394825647, "grad_norm": 0.49954023384961405, "learning_rate": 3.6090602151089284e-08, "loss": 0.0212, "step": 2570 }, { "epoch": 1.9343832020997376, "grad_norm": 0.9631727443171046, "learning_rate": 2.917454640867623e-08, "loss": 0.0188, "step": 2580 }, { "epoch": 1.9418822647169103, "grad_norm": 0.40692123840471256, "learning_rate": 2.2991534701592988e-08, "loss": 0.0206, "step": 2590 }, { "epoch": 1.9493813273340832, "grad_norm": 0.44428845370704506, "learning_rate": 1.754247883410498e-08, "loss": 0.0212, "step": 2600 }, { "epoch": 1.9568803899512561, "grad_norm": 0.741830022789216, "learning_rate": 1.2828182374540199e-08, "loss": 0.0201, "step": 2610 }, { "epoch": 1.964379452568429, "grad_norm": 0.5155517877684481, "learning_rate": 8.84934053678954e-09, "loss": 0.0161, "step": 2620 }, { "epoch": 1.9718785151856018, "grad_norm": 0.8696441458504119, "learning_rate": 5.606540077782164e-09, "loss": 0.0206, "step": 2630 }, { "epoch": 1.9793775778027747, "grad_norm": 0.06985446028079093, "learning_rate": 3.100259210955803e-09, "loss": 0.0231, "step": 2640 }, { "epoch": 1.9868766404199474, "grad_norm": 0.7165094119300843, "learning_rate": 1.3308675357381895e-09, "loss": 0.0219, "step": 2650 }, { "epoch": 1.9943757030371203, "grad_norm": 0.7835649188227006, "learning_rate": 2.986259830400906e-10, "loss": 0.022, "step": 2660 }, { "epoch": 2.0, "step": 2668, "total_flos": 52949293006848.0, "train_loss": 0.03929861019766223, "train_runtime": 3158.0303, "train_samples_per_second": 13.512, "train_steps_per_second": 0.845 } ], "logging_steps": 10, "max_steps": 2668, "num_input_tokens_seen": 0, "num_train_epochs": 2, "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": 52949293006848.0, "train_batch_size": 2, "trial_name": null, "trial_params": null }