{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.7727975270479135, "eval_steps": 500, "global_step": 2500, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0030911901081916537, "grad_norm": 2.9735140800476074, "learning_rate": 9.183673469387756e-07, "loss": 1.8602472305297852, "step": 10 }, { "epoch": 0.0061823802163833074, "grad_norm": 2.6337854862213135, "learning_rate": 1.938775510204082e-06, "loss": 1.7525932312011718, "step": 20 }, { "epoch": 0.00927357032457496, "grad_norm": 1.5814393758773804, "learning_rate": 2.959183673469388e-06, "loss": 1.7173307418823243, "step": 30 }, { "epoch": 0.012364760432766615, "grad_norm": 1.5865761041641235, "learning_rate": 3.979591836734694e-06, "loss": 1.6625125885009766, "step": 40 }, { "epoch": 0.015455950540958269, "grad_norm": 1.6338456869125366, "learning_rate": 5e-06, "loss": 1.6665992736816406, "step": 50 }, { "epoch": 0.01854714064914992, "grad_norm": 1.336181879043579, "learning_rate": 6.020408163265307e-06, "loss": 1.6779584884643555, "step": 60 }, { "epoch": 0.021638330757341576, "grad_norm": 1.6245481967926025, "learning_rate": 7.0408163265306125e-06, "loss": 1.6278823852539062, "step": 70 }, { "epoch": 0.02472952086553323, "grad_norm": 1.3484340906143188, "learning_rate": 8.06122448979592e-06, "loss": 1.6239589691162108, "step": 80 }, { "epoch": 0.027820710973724884, "grad_norm": 1.4237396717071533, "learning_rate": 9.081632653061225e-06, "loss": 1.6229394912719726, "step": 90 }, { "epoch": 0.030911901081916538, "grad_norm": 1.9831488132476807, "learning_rate": 9.999997492674716e-06, "loss": 1.604932975769043, "step": 100 }, { "epoch": 0.03400309119010819, "grad_norm": 1.3235148191452026, "learning_rate": 9.99969661668322e-06, "loss": 1.7327735900878907, "step": 110 }, { "epoch": 0.03709428129829984, "grad_norm": 1.4738770723342896, "learning_rate": 9.998894310210835e-06, "loss": 1.5656912803649903, "step": 120 }, { "epoch": 0.0401854714064915, "grad_norm": 1.5969219207763672, "learning_rate": 9.997590653722625e-06, "loss": 1.6269208908081054, "step": 130 }, { "epoch": 0.04327666151468315, "grad_norm": 1.747842788696289, "learning_rate": 9.995785777965145e-06, "loss": 1.6059745788574218, "step": 140 }, { "epoch": 0.04636785162287481, "grad_norm": 1.5844131708145142, "learning_rate": 9.99347986395332e-06, "loss": 1.606407928466797, "step": 150 }, { "epoch": 0.04945904173106646, "grad_norm": 3.227466106414795, "learning_rate": 9.990673142952299e-06, "loss": 1.5951569557189942, "step": 160 }, { "epoch": 0.05255023183925812, "grad_norm": 1.5301669836044312, "learning_rate": 9.987365896454253e-06, "loss": 1.555880069732666, "step": 170 }, { "epoch": 0.05564142194744977, "grad_norm": 1.346501350402832, "learning_rate": 9.98355845615015e-06, "loss": 1.5443081855773926, "step": 180 }, { "epoch": 0.05873261205564142, "grad_norm": 1.7208951711654663, "learning_rate": 9.979251203896482e-06, "loss": 1.589011001586914, "step": 190 }, { "epoch": 0.061823802163833076, "grad_norm": 1.6657794713974, "learning_rate": 9.974444571676974e-06, "loss": 1.6033136367797851, "step": 200 }, { "epoch": 0.06491499227202473, "grad_norm": 1.3685671091079712, "learning_rate": 9.969139041559259e-06, "loss": 1.564203643798828, "step": 210 }, { "epoch": 0.06800618238021638, "grad_norm": 1.4963208436965942, "learning_rate": 9.963335145646528e-06, "loss": 1.5261777877807616, "step": 220 }, { "epoch": 0.07109737248840804, "grad_norm": 1.378618597984314, "learning_rate": 9.95703346602416e-06, "loss": 1.7190706253051757, "step": 230 }, { "epoch": 0.07418856259659969, "grad_norm": 1.3284642696380615, "learning_rate": 9.950234634701355e-06, "loss": 1.5670341491699218, "step": 240 }, { "epoch": 0.07727975270479134, "grad_norm": 1.2741881608963013, "learning_rate": 9.942939333547737e-06, "loss": 1.605707550048828, "step": 250 }, { "epoch": 0.080370942812983, "grad_norm": 1.4335650205612183, "learning_rate": 9.935148294224974e-06, "loss": 1.5591754913330078, "step": 260 }, { "epoch": 0.08346213292117466, "grad_norm": 1.4812300205230713, "learning_rate": 9.926862298113397e-06, "loss": 1.4808053016662597, "step": 270 }, { "epoch": 0.0865533230293663, "grad_norm": 1.5364317893981934, "learning_rate": 9.918082176233633e-06, "loss": 1.5635189056396483, "step": 280 }, { "epoch": 0.08964451313755796, "grad_norm": 1.4932867288589478, "learning_rate": 9.908808809163259e-06, "loss": 1.5150517463684081, "step": 290 }, { "epoch": 0.09273570324574962, "grad_norm": 1.27454674243927, "learning_rate": 9.899043126948488e-06, "loss": 1.5336437225341797, "step": 300 }, { "epoch": 0.09582689335394126, "grad_norm": 1.2767815589904785, "learning_rate": 9.888786109010895e-06, "loss": 1.5452400207519532, "step": 310 }, { "epoch": 0.09891808346213292, "grad_norm": 1.4611462354660034, "learning_rate": 9.878038784049187e-06, "loss": 1.4844867706298828, "step": 320 }, { "epoch": 0.10200927357032458, "grad_norm": 1.507378101348877, "learning_rate": 9.866802229936027e-06, "loss": 1.4919805526733398, "step": 330 }, { "epoch": 0.10510046367851623, "grad_norm": 1.380361795425415, "learning_rate": 9.855077573609943e-06, "loss": 1.5452465057373046, "step": 340 }, { "epoch": 0.10819165378670788, "grad_norm": 1.351883053779602, "learning_rate": 9.842865990962296e-06, "loss": 1.5766680717468262, "step": 350 }, { "epoch": 0.11128284389489954, "grad_norm": 1.4119234085083008, "learning_rate": 9.830168706719348e-06, "loss": 1.5874876022338866, "step": 360 }, { "epoch": 0.1143740340030912, "grad_norm": 1.3740119934082031, "learning_rate": 9.816986994319438e-06, "loss": 1.543256950378418, "step": 370 }, { "epoch": 0.11746522411128284, "grad_norm": 1.349916934967041, "learning_rate": 9.803322175785259e-06, "loss": 1.4975996971130372, "step": 380 }, { "epoch": 0.1205564142194745, "grad_norm": 1.8141902685165405, "learning_rate": 9.789175621591274e-06, "loss": 1.523211669921875, "step": 390 }, { "epoch": 0.12364760432766615, "grad_norm": 1.6711773872375488, "learning_rate": 9.774548750526261e-06, "loss": 1.5890820503234864, "step": 400 }, { "epoch": 0.1267387944358578, "grad_norm": 1.4761755466461182, "learning_rate": 9.75944302955103e-06, "loss": 1.5950213432312013, "step": 410 }, { "epoch": 0.12982998454404945, "grad_norm": 1.3480901718139648, "learning_rate": 9.743859973651296e-06, "loss": 1.5783711433410645, "step": 420 }, { "epoch": 0.13292117465224113, "grad_norm": 1.2381082773208618, "learning_rate": 9.727801145685725e-06, "loss": 1.5575005531311035, "step": 430 }, { "epoch": 0.13601236476043277, "grad_norm": 1.2985453605651855, "learning_rate": 9.71126815622921e-06, "loss": 1.5073147773742677, "step": 440 }, { "epoch": 0.1391035548686244, "grad_norm": 1.3880364894866943, "learning_rate": 9.694262663411333e-06, "loss": 1.56723051071167, "step": 450 }, { "epoch": 0.14219474497681608, "grad_norm": 1.4708359241485596, "learning_rate": 9.676786372750064e-06, "loss": 1.5140653610229493, "step": 460 }, { "epoch": 0.14528593508500773, "grad_norm": 1.6823925971984863, "learning_rate": 9.658841036980722e-06, "loss": 1.523008441925049, "step": 470 }, { "epoch": 0.14837712519319937, "grad_norm": 1.3621658086776733, "learning_rate": 9.640428455880178e-06, "loss": 1.5539534568786622, "step": 480 }, { "epoch": 0.15146831530139104, "grad_norm": 1.972955584526062, "learning_rate": 9.621550476086362e-06, "loss": 1.5369157791137695, "step": 490 }, { "epoch": 0.1545595054095827, "grad_norm": 1.6722270250320435, "learning_rate": 9.602208990913046e-06, "loss": 1.5470399856567383, "step": 500 }, { "epoch": 0.15765069551777433, "grad_norm": 1.5522538423538208, "learning_rate": 9.582405940159978e-06, "loss": 1.5396239280700683, "step": 510 }, { "epoch": 0.160741885625966, "grad_norm": 1.7494624853134155, "learning_rate": 9.562143309918319e-06, "loss": 1.572172260284424, "step": 520 }, { "epoch": 0.16383307573415765, "grad_norm": 1.5817722082138062, "learning_rate": 9.541423132371459e-06, "loss": 1.5051007270812988, "step": 530 }, { "epoch": 0.16692426584234932, "grad_norm": 1.7209810018539429, "learning_rate": 9.520247485591208e-06, "loss": 1.5711745262145995, "step": 540 }, { "epoch": 0.17001545595054096, "grad_norm": 3.1827101707458496, "learning_rate": 9.498618493329376e-06, "loss": 1.526050853729248, "step": 550 }, { "epoch": 0.1731066460587326, "grad_norm": 1.406969666481018, "learning_rate": 9.476538324804782e-06, "loss": 1.4522027015686034, "step": 560 }, { "epoch": 0.17619783616692428, "grad_norm": 1.7943847179412842, "learning_rate": 9.454009194485701e-06, "loss": 1.5250386238098144, "step": 570 }, { "epoch": 0.17928902627511592, "grad_norm": 1.3113778829574585, "learning_rate": 9.431033361867756e-06, "loss": 1.5368183135986329, "step": 580 }, { "epoch": 0.18238021638330756, "grad_norm": 1.3316926956176758, "learning_rate": 9.407613131247328e-06, "loss": 1.544140625, "step": 590 }, { "epoch": 0.18547140649149924, "grad_norm": 2.0932979583740234, "learning_rate": 9.383750851490438e-06, "loss": 1.521708106994629, "step": 600 }, { "epoch": 0.18856259659969088, "grad_norm": 1.614535927772522, "learning_rate": 9.359448915797178e-06, "loss": 1.5114651679992677, "step": 610 }, { "epoch": 0.19165378670788252, "grad_norm": 1.2698787450790405, "learning_rate": 9.334709761461696e-06, "loss": 1.513047218322754, "step": 620 }, { "epoch": 0.1947449768160742, "grad_norm": 1.365653395652771, "learning_rate": 9.309535869627753e-06, "loss": 1.473441219329834, "step": 630 }, { "epoch": 0.19783616692426584, "grad_norm": 1.4953657388687134, "learning_rate": 9.283929765039877e-06, "loss": 1.5206417083740233, "step": 640 }, { "epoch": 0.2009273570324575, "grad_norm": 1.307398796081543, "learning_rate": 9.257894015790158e-06, "loss": 1.5033920288085938, "step": 650 }, { "epoch": 0.20401854714064915, "grad_norm": 1.9029453992843628, "learning_rate": 9.231431233060691e-06, "loss": 1.5524487495422363, "step": 660 }, { "epoch": 0.2071097372488408, "grad_norm": 1.8270984888076782, "learning_rate": 9.204544070861682e-06, "loss": 1.474977684020996, "step": 670 }, { "epoch": 0.21020092735703247, "grad_norm": 1.9305938482284546, "learning_rate": 9.177235225765287e-06, "loss": 1.5872207641601563, "step": 680 }, { "epoch": 0.2132921174652241, "grad_norm": 1.651270866394043, "learning_rate": 9.149507436635156e-06, "loss": 1.5186875343322754, "step": 690 }, { "epoch": 0.21638330757341576, "grad_norm": 1.6599997282028198, "learning_rate": 9.121363484351753e-06, "loss": 1.5063211441040039, "step": 700 }, { "epoch": 0.21947449768160743, "grad_norm": 1.261690616607666, "learning_rate": 9.092806191533448e-06, "loss": 1.4991595268249511, "step": 710 }, { "epoch": 0.22256568778979907, "grad_norm": 1.2406865358352661, "learning_rate": 9.063838422253438e-06, "loss": 1.5417633056640625, "step": 720 }, { "epoch": 0.22565687789799072, "grad_norm": 1.2300302982330322, "learning_rate": 9.0344630817525e-06, "loss": 1.4868436813354493, "step": 730 }, { "epoch": 0.2287480680061824, "grad_norm": 1.4104863405227661, "learning_rate": 9.004683116147618e-06, "loss": 1.518869400024414, "step": 740 }, { "epoch": 0.23183925811437403, "grad_norm": 1.1874244213104248, "learning_rate": 8.974501512136508e-06, "loss": 1.5017603874206542, "step": 750 }, { "epoch": 0.23493044822256567, "grad_norm": 1.398455262184143, "learning_rate": 8.94392129669808e-06, "loss": 1.5286592483520507, "step": 760 }, { "epoch": 0.23802163833075735, "grad_norm": 1.5666356086730957, "learning_rate": 8.912945536788855e-06, "loss": 1.5568647384643555, "step": 770 }, { "epoch": 0.241112828438949, "grad_norm": 1.2765898704528809, "learning_rate": 8.881577339035368e-06, "loss": 1.4791644096374512, "step": 780 }, { "epoch": 0.24420401854714066, "grad_norm": 1.5090545415878296, "learning_rate": 8.849819849422605e-06, "loss": 1.4606804847717285, "step": 790 }, { "epoch": 0.2472952086553323, "grad_norm": 1.1877100467681885, "learning_rate": 8.817676252978482e-06, "loss": 1.5327486991882324, "step": 800 }, { "epoch": 0.250386398763524, "grad_norm": 1.518449306488037, "learning_rate": 8.785149773454406e-06, "loss": 1.5251803398132324, "step": 810 }, { "epoch": 0.2534775888717156, "grad_norm": 1.3751578330993652, "learning_rate": 8.75224367300197e-06, "loss": 1.5399330139160157, "step": 820 }, { "epoch": 0.25656877897990726, "grad_norm": 1.4341316223144531, "learning_rate": 8.718961251845776e-06, "loss": 1.4913371086120606, "step": 830 }, { "epoch": 0.2596599690880989, "grad_norm": 1.756329894065857, "learning_rate": 8.685305847952447e-06, "loss": 1.5053520202636719, "step": 840 }, { "epoch": 0.26275115919629055, "grad_norm": 1.2910538911819458, "learning_rate": 8.651280836695866e-06, "loss": 1.4810606956481933, "step": 850 }, { "epoch": 0.26584234930448225, "grad_norm": 1.1309559345245361, "learning_rate": 8.616889630518634e-06, "loss": 1.5381391525268555, "step": 860 }, { "epoch": 0.2689335394126739, "grad_norm": 1.6359164714813232, "learning_rate": 8.582135678589849e-06, "loss": 1.5432696342468262, "step": 870 }, { "epoch": 0.27202472952086554, "grad_norm": 1.5036001205444336, "learning_rate": 8.547022466459169e-06, "loss": 1.5345426559448243, "step": 880 }, { "epoch": 0.2751159196290572, "grad_norm": 1.5126945972442627, "learning_rate": 8.511553515707238e-06, "loss": 1.4968720436096192, "step": 890 }, { "epoch": 0.2782071097372488, "grad_norm": 1.4351264238357544, "learning_rate": 8.475732383592506e-06, "loss": 1.4474885940551758, "step": 900 }, { "epoch": 0.28129829984544047, "grad_norm": 1.3674299716949463, "learning_rate": 8.43956266269446e-06, "loss": 1.4778318405151367, "step": 910 }, { "epoch": 0.28438948995363217, "grad_norm": 2.175255298614502, "learning_rate": 8.403047980553316e-06, "loss": 1.5429688453674317, "step": 920 }, { "epoch": 0.2874806800618238, "grad_norm": 1.3890902996063232, "learning_rate": 8.366191999306203e-06, "loss": 1.4910104751586915, "step": 930 }, { "epoch": 0.29057187017001546, "grad_norm": 1.6042287349700928, "learning_rate": 8.328998415319887e-06, "loss": 1.5073558807373046, "step": 940 }, { "epoch": 0.2936630602782071, "grad_norm": 1.5018166303634644, "learning_rate": 8.291470958820046e-06, "loss": 1.5073823928833008, "step": 950 }, { "epoch": 0.29675425038639874, "grad_norm": 1.1693017482757568, "learning_rate": 8.253613393517161e-06, "loss": 1.4433947563171388, "step": 960 }, { "epoch": 0.29984544049459044, "grad_norm": 1.3259260654449463, "learning_rate": 8.215429516229043e-06, "loss": 1.485299777984619, "step": 970 }, { "epoch": 0.3029366306027821, "grad_norm": 1.3524744510650635, "learning_rate": 8.176923156500048e-06, "loss": 1.4936206817626954, "step": 980 }, { "epoch": 0.30602782071097373, "grad_norm": 1.2411019802093506, "learning_rate": 8.138098176216999e-06, "loss": 1.4466056823730469, "step": 990 }, { "epoch": 0.3091190108191654, "grad_norm": 1.7096987962722778, "learning_rate": 8.098958469221867e-06, "loss": 1.4811983108520508, "step": 1000 }, { "epoch": 0.312210200927357, "grad_norm": 1.2653203010559082, "learning_rate": 8.059507960921252e-06, "loss": 1.5032027244567872, "step": 1010 }, { "epoch": 0.31530139103554866, "grad_norm": 1.6908106803894043, "learning_rate": 8.019750607892696e-06, "loss": 1.5163268089294433, "step": 1020 }, { "epoch": 0.31839258114374036, "grad_norm": 1.4997762441635132, "learning_rate": 7.979690397487866e-06, "loss": 1.5213595390319825, "step": 1030 }, { "epoch": 0.321483771251932, "grad_norm": 1.3022050857543945, "learning_rate": 7.939331347432664e-06, "loss": 1.4342849731445313, "step": 1040 }, { "epoch": 0.32457496136012365, "grad_norm": 1.4664312601089478, "learning_rate": 7.89867750542426e-06, "loss": 1.4525555610656737, "step": 1050 }, { "epoch": 0.3276661514683153, "grad_norm": 1.2952008247375488, "learning_rate": 7.857732948725158e-06, "loss": 1.5019875526428224, "step": 1060 }, { "epoch": 0.33075734157650694, "grad_norm": 1.2665051221847534, "learning_rate": 7.816501783754278e-06, "loss": 1.474588966369629, "step": 1070 }, { "epoch": 0.33384853168469864, "grad_norm": 1.5099931955337524, "learning_rate": 7.774988145675101e-06, "loss": 1.4620919227600098, "step": 1080 }, { "epoch": 0.3369397217928903, "grad_norm": 1.9047678709030151, "learning_rate": 7.733196197980954e-06, "loss": 1.4711945533752442, "step": 1090 }, { "epoch": 0.3400309119010819, "grad_norm": 1.4548710584640503, "learning_rate": 7.691130132077446e-06, "loss": 1.5918668746948241, "step": 1100 }, { "epoch": 0.34312210200927357, "grad_norm": 1.414145588874817, "learning_rate": 7.648794166862093e-06, "loss": 1.5711587905883788, "step": 1110 }, { "epoch": 0.3462132921174652, "grad_norm": 1.1808687448501587, "learning_rate": 7.606192548301208e-06, "loss": 1.5401415824890137, "step": 1120 }, { "epoch": 0.34930448222565685, "grad_norm": 2.007089853286743, "learning_rate": 7.563329549004055e-06, "loss": 1.5030123710632324, "step": 1130 }, { "epoch": 0.35239567233384855, "grad_norm": 1.625108003616333, "learning_rate": 7.520209467794342e-06, "loss": 1.5099098205566406, "step": 1140 }, { "epoch": 0.3554868624420402, "grad_norm": 2.2485642433166504, "learning_rate": 7.47683662927908e-06, "loss": 1.5096467018127442, "step": 1150 }, { "epoch": 0.35857805255023184, "grad_norm": 1.484653353691101, "learning_rate": 7.4332153834148715e-06, "loss": 1.5069299697875977, "step": 1160 }, { "epoch": 0.3616692426584235, "grad_norm": 1.2877867221832275, "learning_rate": 7.389350105071621e-06, "loss": 1.5543519973754882, "step": 1170 }, { "epoch": 0.36476043276661513, "grad_norm": 1.3740814924240112, "learning_rate": 7.345245193593792e-06, "loss": 1.4476408004760741, "step": 1180 }, { "epoch": 0.3678516228748068, "grad_norm": 1.723948359489441, "learning_rate": 7.300905072359174e-06, "loss": 1.5037665367126465, "step": 1190 }, { "epoch": 0.37094281298299847, "grad_norm": 1.470979928970337, "learning_rate": 7.256334188335256e-06, "loss": 1.5103675842285156, "step": 1200 }, { "epoch": 0.3740340030911901, "grad_norm": 1.1751171350479126, "learning_rate": 7.211537011633232e-06, "loss": 1.3948946952819825, "step": 1210 }, { "epoch": 0.37712519319938176, "grad_norm": 2.2032206058502197, "learning_rate": 7.166518035059682e-06, "loss": 1.510918426513672, "step": 1220 }, { "epoch": 0.3802163833075734, "grad_norm": 2.0937609672546387, "learning_rate": 7.121281773665978e-06, "loss": 1.5443879127502442, "step": 1230 }, { "epoch": 0.38330757341576505, "grad_norm": 1.3330838680267334, "learning_rate": 7.075832764295463e-06, "loss": 1.5280852317810059, "step": 1240 }, { "epoch": 0.38639876352395675, "grad_norm": 1.2813427448272705, "learning_rate": 7.030175565128435e-06, "loss": 1.4667059898376464, "step": 1250 }, { "epoch": 0.3894899536321484, "grad_norm": 1.2253540754318237, "learning_rate": 6.9843147552250054e-06, "loss": 1.4397510528564452, "step": 1260 }, { "epoch": 0.39258114374034003, "grad_norm": 1.5304349660873413, "learning_rate": 6.938254934065845e-06, "loss": 1.5280447006225586, "step": 1270 }, { "epoch": 0.3956723338485317, "grad_norm": 1.2107839584350586, "learning_rate": 6.892000721090904e-06, "loss": 1.4797983169555664, "step": 1280 }, { "epoch": 0.3987635239567233, "grad_norm": 1.7480978965759277, "learning_rate": 6.845556755236107e-06, "loss": 1.481153964996338, "step": 1290 }, { "epoch": 0.401854714064915, "grad_norm": 1.400068759918213, "learning_rate": 6.7989276944681095e-06, "loss": 1.4467869758605958, "step": 1300 }, { "epoch": 0.40494590417310666, "grad_norm": 1.3158193826675415, "learning_rate": 6.7521182153171425e-06, "loss": 1.4358047485351562, "step": 1310 }, { "epoch": 0.4080370942812983, "grad_norm": 1.780266523361206, "learning_rate": 6.705133012407986e-06, "loss": 1.4848631858825683, "step": 1320 }, { "epoch": 0.41112828438948995, "grad_norm": 1.4750027656555176, "learning_rate": 6.657976797989144e-06, "loss": 1.5357203483581543, "step": 1330 }, { "epoch": 0.4142194744976816, "grad_norm": 1.5012050867080688, "learning_rate": 6.610654301460234e-06, "loss": 1.4805206298828124, "step": 1340 }, { "epoch": 0.41731066460587324, "grad_norm": 1.5619773864746094, "learning_rate": 6.563170268897671e-06, "loss": 1.4869306564331055, "step": 1350 }, { "epoch": 0.42040185471406494, "grad_norm": 1.4492056369781494, "learning_rate": 6.515529462578669e-06, "loss": 1.528173065185547, "step": 1360 }, { "epoch": 0.4234930448222566, "grad_norm": 1.1812134981155396, "learning_rate": 6.4677366605036275e-06, "loss": 1.485201644897461, "step": 1370 }, { "epoch": 0.4265842349304482, "grad_norm": 1.2770708799362183, "learning_rate": 6.41979665591693e-06, "loss": 1.456434726715088, "step": 1380 }, { "epoch": 0.42967542503863987, "grad_norm": 1.4255800247192383, "learning_rate": 6.371714256826222e-06, "loss": 1.413369846343994, "step": 1390 }, { "epoch": 0.4327666151468315, "grad_norm": 1.6839423179626465, "learning_rate": 6.323494285520199e-06, "loss": 1.4879916191101075, "step": 1400 }, { "epoch": 0.43585780525502316, "grad_norm": 1.394959568977356, "learning_rate": 6.275141578084982e-06, "loss": 1.4854043960571288, "step": 1410 }, { "epoch": 0.43894899536321486, "grad_norm": 1.4087709188461304, "learning_rate": 6.226660983919086e-06, "loss": 1.4624568939208984, "step": 1420 }, { "epoch": 0.4420401854714065, "grad_norm": 1.4961775541305542, "learning_rate": 6.178057365247061e-06, "loss": 1.4420994758605956, "step": 1430 }, { "epoch": 0.44513137557959814, "grad_norm": 1.2653372287750244, "learning_rate": 6.129335596631858e-06, "loss": 1.4218201637268066, "step": 1440 }, { "epoch": 0.4482225656877898, "grad_norm": 1.2804330587387085, "learning_rate": 6.080500564485939e-06, "loss": 1.4568147659301758, "step": 1450 }, { "epoch": 0.45131375579598143, "grad_norm": 1.2200677394866943, "learning_rate": 6.031557166581219e-06, "loss": 1.4289538383483886, "step": 1460 }, { "epoch": 0.45440494590417313, "grad_norm": 1.2231463193893433, "learning_rate": 5.982510311557845e-06, "loss": 1.4658859252929688, "step": 1470 }, { "epoch": 0.4574961360123648, "grad_norm": 2.836029529571533, "learning_rate": 5.933364918431905e-06, "loss": 1.4995241165161133, "step": 1480 }, { "epoch": 0.4605873261205564, "grad_norm": 1.2030493021011353, "learning_rate": 5.884125916102093e-06, "loss": 1.4161153793334962, "step": 1490 }, { "epoch": 0.46367851622874806, "grad_norm": 1.3355892896652222, "learning_rate": 5.834798242855371e-06, "loss": 1.4728096961975097, "step": 1500 }, { "epoch": 0.4667697063369397, "grad_norm": 1.2987335920333862, "learning_rate": 5.785386845871699e-06, "loss": 1.4507723808288575, "step": 1510 }, { "epoch": 0.46986089644513135, "grad_norm": 1.297783374786377, "learning_rate": 5.735896680727875e-06, "loss": 1.443259048461914, "step": 1520 }, { "epoch": 0.47295208655332305, "grad_norm": 1.3137645721435547, "learning_rate": 5.6863327109005285e-06, "loss": 1.421434497833252, "step": 1530 }, { "epoch": 0.4760432766615147, "grad_norm": 1.2665537595748901, "learning_rate": 5.63669990726832e-06, "loss": 1.4575900077819823, "step": 1540 }, { "epoch": 0.47913446676970634, "grad_norm": 1.4960824251174927, "learning_rate": 5.5870032476134065e-06, "loss": 1.5381264686584473, "step": 1550 }, { "epoch": 0.482225656877898, "grad_norm": 1.3001457452774048, "learning_rate": 5.537247716122198e-06, "loss": 1.4955948829650878, "step": 1560 }, { "epoch": 0.4853168469860896, "grad_norm": 1.1044868230819702, "learning_rate": 5.487438302885495e-06, "loss": 1.4542874336242675, "step": 1570 }, { "epoch": 0.4884080370942813, "grad_norm": 1.253962516784668, "learning_rate": 5.437580003398012e-06, "loss": 1.4506648063659668, "step": 1580 }, { "epoch": 0.49149922720247297, "grad_norm": 1.7160922288894653, "learning_rate": 5.387677818057377e-06, "loss": 1.4201354026794433, "step": 1590 }, { "epoch": 0.4945904173106646, "grad_norm": 1.2351624965667725, "learning_rate": 5.337736751662622e-06, "loss": 1.445249080657959, "step": 1600 }, { "epoch": 0.49768160741885625, "grad_norm": 1.280388355255127, "learning_rate": 5.287761812912245e-06, "loss": 1.457985019683838, "step": 1610 }, { "epoch": 0.500772797527048, "grad_norm": 1.6783956289291382, "learning_rate": 5.237758013901876e-06, "loss": 1.4182465553283692, "step": 1620 }, { "epoch": 0.5038639876352395, "grad_norm": 1.1116238832473755, "learning_rate": 5.187730369621608e-06, "loss": 1.4542993545532226, "step": 1630 }, { "epoch": 0.5069551777434312, "grad_norm": 1.4436450004577637, "learning_rate": 5.1376838974530215e-06, "loss": 1.4795181274414062, "step": 1640 }, { "epoch": 0.5100463678516228, "grad_norm": 1.340255618095398, "learning_rate": 5.087623616665994e-06, "loss": 1.4716657638549804, "step": 1650 }, { "epoch": 0.5131375579598145, "grad_norm": 1.715916633605957, "learning_rate": 5.037554547915292e-06, "loss": 1.4676661491394043, "step": 1660 }, { "epoch": 0.5162287480680062, "grad_norm": 1.4235882759094238, "learning_rate": 4.987481712737053e-06, "loss": 1.43391695022583, "step": 1670 }, { "epoch": 0.5193199381761978, "grad_norm": 1.9213931560516357, "learning_rate": 4.937410133045152e-06, "loss": 1.5064863204956054, "step": 1680 }, { "epoch": 0.5224111282843895, "grad_norm": 1.2896068096160889, "learning_rate": 4.887344830627553e-06, "loss": 1.5532581329345703, "step": 1690 }, { "epoch": 0.5255023183925811, "grad_norm": 1.2903958559036255, "learning_rate": 4.8372908266426556e-06, "loss": 1.448100757598877, "step": 1700 }, { "epoch": 0.5285935085007728, "grad_norm": 1.4022008180618286, "learning_rate": 4.787253141115717e-06, "loss": 1.425368881225586, "step": 1710 }, { "epoch": 0.5316846986089645, "grad_norm": 1.234277367591858, "learning_rate": 4.737236792435378e-06, "loss": 1.4820143699645996, "step": 1720 }, { "epoch": 0.5347758887171561, "grad_norm": 1.5323388576507568, "learning_rate": 4.687246796850362e-06, "loss": 1.469198226928711, "step": 1730 }, { "epoch": 0.5378670788253478, "grad_norm": 1.232828974723816, "learning_rate": 4.637288167966384e-06, "loss": 1.4907366752624511, "step": 1740 }, { "epoch": 0.5409582689335394, "grad_norm": 1.4837671518325806, "learning_rate": 4.5873659162433245e-06, "loss": 1.4655179977416992, "step": 1750 }, { "epoch": 0.5440494590417311, "grad_norm": 1.357835054397583, "learning_rate": 4.537485048492714e-06, "loss": 1.334919261932373, "step": 1760 }, { "epoch": 0.5471406491499228, "grad_norm": 1.379494071006775, "learning_rate": 4.487650567375601e-06, "loss": 1.4235004425048827, "step": 1770 }, { "epoch": 0.5502318392581144, "grad_norm": 1.630753755569458, "learning_rate": 4.4378674709008156e-06, "loss": 1.4657986640930176, "step": 1780 }, { "epoch": 0.5533230293663061, "grad_norm": 1.2541428804397583, "learning_rate": 4.388140751923705e-06, "loss": 1.516214370727539, "step": 1790 }, { "epoch": 0.5564142194744977, "grad_norm": 1.3273460865020752, "learning_rate": 4.338475397645401e-06, "loss": 1.4450053215026855, "step": 1800 }, { "epoch": 0.5595054095826894, "grad_norm": 1.7613108158111572, "learning_rate": 4.28887638911263e-06, "loss": 1.4198290824890136, "step": 1810 }, { "epoch": 0.5625965996908809, "grad_norm": 1.384879231452942, "learning_rate": 4.239348700718162e-06, "loss": 1.5006150245666503, "step": 1820 }, { "epoch": 0.5656877897990726, "grad_norm": 1.1896439790725708, "learning_rate": 4.189897299701918e-06, "loss": 1.4708269119262696, "step": 1830 }, { "epoch": 0.5687789799072643, "grad_norm": 2.0120818614959717, "learning_rate": 4.140527145652783e-06, "loss": 1.4678752899169922, "step": 1840 }, { "epoch": 0.5718701700154559, "grad_norm": 1.3199154138565063, "learning_rate": 4.091243190011213e-06, "loss": 1.4660306930541993, "step": 1850 }, { "epoch": 0.5749613601236476, "grad_norm": 1.2792941331863403, "learning_rate": 4.042050375572639e-06, "loss": 1.4908181190490724, "step": 1860 }, { "epoch": 0.5780525502318392, "grad_norm": 1.3983755111694336, "learning_rate": 3.9929536359917335e-06, "loss": 1.4740056991577148, "step": 1870 }, { "epoch": 0.5811437403400309, "grad_norm": 1.2915738821029663, "learning_rate": 3.94395789528762e-06, "loss": 1.490330410003662, "step": 1880 }, { "epoch": 0.5842349304482226, "grad_norm": 1.2621806859970093, "learning_rate": 3.895068067350021e-06, "loss": 1.370198917388916, "step": 1890 }, { "epoch": 0.5873261205564142, "grad_norm": 1.462422490119934, "learning_rate": 3.846289055446438e-06, "loss": 1.4030427932739258, "step": 1900 }, { "epoch": 0.5904173106646059, "grad_norm": 1.3890163898468018, "learning_rate": 3.7976257517303895e-06, "loss": 1.4210404396057128, "step": 1910 }, { "epoch": 0.5935085007727975, "grad_norm": 1.6229174137115479, "learning_rate": 3.749083036750765e-06, "loss": 1.4700294494628907, "step": 1920 }, { "epoch": 0.5965996908809892, "grad_norm": 1.415581464767456, "learning_rate": 3.7006657789623537e-06, "loss": 1.452810573577881, "step": 1930 }, { "epoch": 0.5996908809891809, "grad_norm": 1.2987124919891357, "learning_rate": 3.652378834237561e-06, "loss": 1.4616636276245116, "step": 1940 }, { "epoch": 0.6027820710973725, "grad_norm": 1.3295176029205322, "learning_rate": 3.604227045379416e-06, "loss": 1.5117558479309081, "step": 1950 }, { "epoch": 0.6058732612055642, "grad_norm": 1.8061981201171875, "learning_rate": 3.556215241635873e-06, "loss": 1.4809531211853026, "step": 1960 }, { "epoch": 0.6089644513137558, "grad_norm": 1.291310429573059, "learning_rate": 3.508348238215466e-06, "loss": 1.4826027870178222, "step": 1970 }, { "epoch": 0.6120556414219475, "grad_norm": 1.3516390323638916, "learning_rate": 3.4606308358043955e-06, "loss": 1.4254460334777832, "step": 1980 }, { "epoch": 0.615146831530139, "grad_norm": 1.4707870483398438, "learning_rate": 3.4130678200850507e-06, "loss": 1.481752586364746, "step": 1990 }, { "epoch": 0.6182380216383307, "grad_norm": 1.325650930404663, "learning_rate": 3.365663961256037e-06, "loss": 1.546794605255127, "step": 2000 }, { "epoch": 0.6213292117465224, "grad_norm": 1.1322145462036133, "learning_rate": 3.318424013553773e-06, "loss": 1.4172988891601563, "step": 2010 }, { "epoch": 0.624420401854714, "grad_norm": 1.711897611618042, "learning_rate": 3.2713527147756695e-06, "loss": 1.4668429374694825, "step": 2020 }, { "epoch": 0.6275115919629057, "grad_norm": 1.1886658668518066, "learning_rate": 3.2244547858049706e-06, "loss": 1.4519427299499512, "step": 2030 }, { "epoch": 0.6306027820710973, "grad_norm": 1.2208441495895386, "learning_rate": 3.1777349301372875e-06, "loss": 1.4594807624816895, "step": 2040 }, { "epoch": 0.633693972179289, "grad_norm": 1.2890353202819824, "learning_rate": 3.1311978334088622e-06, "loss": 1.4782755851745606, "step": 2050 }, { "epoch": 0.6367851622874807, "grad_norm": 1.658651351928711, "learning_rate": 3.084848162926656e-06, "loss": 1.4407502174377442, "step": 2060 }, { "epoch": 0.6398763523956723, "grad_norm": 1.2660738229751587, "learning_rate": 3.038690567200231e-06, "loss": 1.477914810180664, "step": 2070 }, { "epoch": 0.642967542503864, "grad_norm": 1.553490161895752, "learning_rate": 2.9927296754755606e-06, "loss": 1.4243447303771972, "step": 2080 }, { "epoch": 0.6460587326120556, "grad_norm": 1.3240909576416016, "learning_rate": 2.946970097270746e-06, "loss": 1.4535947799682618, "step": 2090 }, { "epoch": 0.6491499227202473, "grad_norm": 1.3599040508270264, "learning_rate": 2.9014164219137097e-06, "loss": 1.4827692031860351, "step": 2100 }, { "epoch": 0.652241112828439, "grad_norm": 1.1968400478363037, "learning_rate": 2.856073218081932e-06, "loss": 1.4551926612854005, "step": 2110 }, { "epoch": 0.6553323029366306, "grad_norm": 1.4659433364868164, "learning_rate": 2.810945033344249e-06, "loss": 1.3994011878967285, "step": 2120 }, { "epoch": 0.6584234930448223, "grad_norm": 1.163133144378662, "learning_rate": 2.766036393704751e-06, "loss": 1.4950058937072754, "step": 2130 }, { "epoch": 0.6615146831530139, "grad_norm": 1.5813230276107788, "learning_rate": 2.7213518031488873e-06, "loss": 1.4376729011535645, "step": 2140 }, { "epoch": 0.6646058732612056, "grad_norm": 1.7495330572128296, "learning_rate": 2.6768957431917188e-06, "loss": 1.4890124320983886, "step": 2150 }, { "epoch": 0.6676970633693973, "grad_norm": 1.6101948022842407, "learning_rate": 2.6326726724284896e-06, "loss": 1.4041688919067383, "step": 2160 }, { "epoch": 0.6707882534775889, "grad_norm": 1.634790301322937, "learning_rate": 2.5886870260874397e-06, "loss": 1.4599223136901855, "step": 2170 }, { "epoch": 0.6738794435857806, "grad_norm": 1.5386630296707153, "learning_rate": 2.5449432155849996e-06, "loss": 1.4984040260314941, "step": 2180 }, { "epoch": 0.6769706336939721, "grad_norm": 1.3177083730697632, "learning_rate": 2.5014456280833555e-06, "loss": 1.4889844894409179, "step": 2190 }, { "epoch": 0.6800618238021638, "grad_norm": 1.5407538414001465, "learning_rate": 2.458198626050446e-06, "loss": 1.4642755508422851, "step": 2200 }, { "epoch": 0.6831530139103554, "grad_norm": 1.5543229579925537, "learning_rate": 2.4152065468224567e-06, "loss": 1.4338790893554687, "step": 2210 }, { "epoch": 0.6862442040185471, "grad_norm": 1.2793071269989014, "learning_rate": 2.3724737021688025e-06, "loss": 1.4760396003723144, "step": 2220 }, { "epoch": 0.6893353941267388, "grad_norm": 1.5485234260559082, "learning_rate": 2.330004377859699e-06, "loss": 1.420406436920166, "step": 2230 }, { "epoch": 0.6924265842349304, "grad_norm": 1.4266314506530762, "learning_rate": 2.2878028332363276e-06, "loss": 1.4978084564208984, "step": 2240 }, { "epoch": 0.6955177743431221, "grad_norm": 1.5382843017578125, "learning_rate": 2.2458733007836716e-06, "loss": 1.479283332824707, "step": 2250 }, { "epoch": 0.6986089644513137, "grad_norm": 1.217307686805725, "learning_rate": 2.2042199857060066e-06, "loss": 1.4262738227844238, "step": 2260 }, { "epoch": 0.7017001545595054, "grad_norm": 1.447533130645752, "learning_rate": 2.1628470655051732e-06, "loss": 1.4787374496459962, "step": 2270 }, { "epoch": 0.7047913446676971, "grad_norm": 1.182555913925171, "learning_rate": 2.1217586895615965e-06, "loss": 1.4669020652770997, "step": 2280 }, { "epoch": 0.7078825347758887, "grad_norm": 1.1514277458190918, "learning_rate": 2.0809589787181354e-06, "loss": 1.406630516052246, "step": 2290 }, { "epoch": 0.7109737248840804, "grad_norm": 1.264469861984253, "learning_rate": 2.0404520248668038e-06, "loss": 1.3660908699035645, "step": 2300 }, { "epoch": 0.714064914992272, "grad_norm": 1.5543115139007568, "learning_rate": 2.000241890538365e-06, "loss": 1.4065464973449706, "step": 2310 }, { "epoch": 0.7171561051004637, "grad_norm": 1.4976688623428345, "learning_rate": 1.960332608494918e-06, "loss": 1.399527645111084, "step": 2320 }, { "epoch": 0.7202472952086554, "grad_norm": 1.4011090993881226, "learning_rate": 1.9207281813254188e-06, "loss": 1.3892153739929198, "step": 2330 }, { "epoch": 0.723338485316847, "grad_norm": 1.495736002922058, "learning_rate": 1.8814325810442723e-06, "loss": 1.4148066520690918, "step": 2340 }, { "epoch": 0.7264296754250387, "grad_norm": 1.445772647857666, "learning_rate": 1.8424497486929555e-06, "loss": 1.4055349349975585, "step": 2350 }, { "epoch": 0.7295208655332303, "grad_norm": 1.5451759099960327, "learning_rate": 1.803783593944769e-06, "loss": 1.4828357696533203, "step": 2360 }, { "epoch": 0.732612055641422, "grad_norm": 1.4374388456344604, "learning_rate": 1.765437994712725e-06, "loss": 1.4416637420654297, "step": 2370 }, { "epoch": 0.7357032457496137, "grad_norm": 1.218193769454956, "learning_rate": 1.7274167967606247e-06, "loss": 1.420787239074707, "step": 2380 }, { "epoch": 0.7387944358578052, "grad_norm": 1.3660622835159302, "learning_rate": 1.6897238133173561e-06, "loss": 1.4786205291748047, "step": 2390 }, { "epoch": 0.7418856259659969, "grad_norm": 1.4243738651275635, "learning_rate": 1.6523628246944595e-06, "loss": 1.4805352210998535, "step": 2400 }, { "epoch": 0.7449768160741885, "grad_norm": 1.4238884449005127, "learning_rate": 1.6153375779069896e-06, "loss": 1.417660903930664, "step": 2410 }, { "epoch": 0.7480680061823802, "grad_norm": 1.4607441425323486, "learning_rate": 1.5786517862977175e-06, "loss": 1.4552452087402343, "step": 2420 }, { "epoch": 0.7511591962905718, "grad_norm": 1.6682343482971191, "learning_rate": 1.5423091291647219e-06, "loss": 1.4331506729125976, "step": 2430 }, { "epoch": 0.7542503863987635, "grad_norm": 1.4679391384124756, "learning_rate": 1.5063132513923645e-06, "loss": 1.422628688812256, "step": 2440 }, { "epoch": 0.7573415765069552, "grad_norm": 1.6069694757461548, "learning_rate": 1.4706677630857596e-06, "loss": 1.461559772491455, "step": 2450 }, { "epoch": 0.7604327666151468, "grad_norm": 1.4631198644638062, "learning_rate": 1.43537623920869e-06, "loss": 1.4700774192810058, "step": 2460 }, { "epoch": 0.7635239567233385, "grad_norm": 1.7610853910446167, "learning_rate": 1.4004422192250784e-06, "loss": 1.4959105491638183, "step": 2470 }, { "epoch": 0.7666151468315301, "grad_norm": 1.5206730365753174, "learning_rate": 1.3658692067439982e-06, "loss": 1.3961060523986817, "step": 2480 }, { "epoch": 0.7697063369397218, "grad_norm": 1.3395452499389648, "learning_rate": 1.3316606691682953e-06, "loss": 1.4280083656311036, "step": 2490 }, { "epoch": 0.7727975270479135, "grad_norm": 1.3363163471221924, "learning_rate": 1.2978200373468319e-06, "loss": 1.4793813705444336, "step": 2500 } ], "logging_steps": 10, "max_steps": 3235, "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": false }, "attributes": {} } }, "total_flos": 7.12798243617792e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }