{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 2414, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00041425020712510354, "grad_norm": 25.62216256914292, "learning_rate": 4.132231404958678e-08, "loss": 1.408, "step": 1 }, { "epoch": 0.002071251035625518, "grad_norm": 24.73039890627057, "learning_rate": 2.066115702479339e-07, "loss": 1.4218, "step": 5 }, { "epoch": 0.004142502071251036, "grad_norm": 15.880166030762085, "learning_rate": 4.132231404958678e-07, "loss": 1.3728, "step": 10 }, { "epoch": 0.006213753106876553, "grad_norm": 9.429907209890372, "learning_rate": 6.198347107438018e-07, "loss": 1.2705, "step": 15 }, { "epoch": 0.008285004142502071, "grad_norm": 10.159424910052133, "learning_rate": 8.264462809917356e-07, "loss": 1.1466, "step": 20 }, { "epoch": 0.010356255178127589, "grad_norm": 4.617335827062072, "learning_rate": 1.0330578512396695e-06, "loss": 1.0327, "step": 25 }, { "epoch": 0.012427506213753107, "grad_norm": 4.402523716127155, "learning_rate": 1.2396694214876035e-06, "loss": 0.9745, "step": 30 }, { "epoch": 0.014498757249378625, "grad_norm": 3.4984689094640147, "learning_rate": 1.4462809917355372e-06, "loss": 0.9391, "step": 35 }, { "epoch": 0.016570008285004142, "grad_norm": 3.0928408385431596, "learning_rate": 1.6528925619834712e-06, "loss": 0.9235, "step": 40 }, { "epoch": 0.018641259320629662, "grad_norm": 3.2767710714157317, "learning_rate": 1.859504132231405e-06, "loss": 0.9056, "step": 45 }, { "epoch": 0.020712510356255178, "grad_norm": 3.1369544849631215, "learning_rate": 2.066115702479339e-06, "loss": 0.8964, "step": 50 }, { "epoch": 0.022783761391880698, "grad_norm": 3.2642671855507692, "learning_rate": 2.2727272727272728e-06, "loss": 0.8971, "step": 55 }, { "epoch": 0.024855012427506214, "grad_norm": 3.028992014741691, "learning_rate": 2.479338842975207e-06, "loss": 0.8834, "step": 60 }, { "epoch": 0.026926263463131733, "grad_norm": 3.0178958695400913, "learning_rate": 2.6859504132231405e-06, "loss": 0.89, "step": 65 }, { "epoch": 0.02899751449875725, "grad_norm": 3.0567240270236007, "learning_rate": 2.8925619834710743e-06, "loss": 0.8763, "step": 70 }, { "epoch": 0.03106876553438277, "grad_norm": 3.0134392244191592, "learning_rate": 3.0991735537190086e-06, "loss": 0.8727, "step": 75 }, { "epoch": 0.033140016570008285, "grad_norm": 3.1789130886506203, "learning_rate": 3.3057851239669424e-06, "loss": 0.8673, "step": 80 }, { "epoch": 0.035211267605633804, "grad_norm": 3.090296320228619, "learning_rate": 3.5123966942148763e-06, "loss": 0.8596, "step": 85 }, { "epoch": 0.037282518641259324, "grad_norm": 3.149440632258299, "learning_rate": 3.71900826446281e-06, "loss": 0.8639, "step": 90 }, { "epoch": 0.03935376967688484, "grad_norm": 3.5929598755253003, "learning_rate": 3.925619834710744e-06, "loss": 0.858, "step": 95 }, { "epoch": 0.041425020712510356, "grad_norm": 3.085751766768924, "learning_rate": 4.132231404958678e-06, "loss": 0.8604, "step": 100 }, { "epoch": 0.043496271748135876, "grad_norm": 2.9869409408875867, "learning_rate": 4.338842975206612e-06, "loss": 0.8489, "step": 105 }, { "epoch": 0.045567522783761395, "grad_norm": 3.1074262498950778, "learning_rate": 4.5454545454545455e-06, "loss": 0.853, "step": 110 }, { "epoch": 0.04763877381938691, "grad_norm": 3.0520548052266108, "learning_rate": 4.75206611570248e-06, "loss": 0.8297, "step": 115 }, { "epoch": 0.04971002485501243, "grad_norm": 3.2445636865019347, "learning_rate": 4.958677685950414e-06, "loss": 0.839, "step": 120 }, { "epoch": 0.05178127589063795, "grad_norm": 3.1656798892394487, "learning_rate": 5.165289256198347e-06, "loss": 0.8421, "step": 125 }, { "epoch": 0.053852526926263466, "grad_norm": 2.8975007450636077, "learning_rate": 5.371900826446281e-06, "loss": 0.8447, "step": 130 }, { "epoch": 0.05592377796188898, "grad_norm": 3.1177625956552335, "learning_rate": 5.578512396694216e-06, "loss": 0.8341, "step": 135 }, { "epoch": 0.0579950289975145, "grad_norm": 3.1336120071315787, "learning_rate": 5.785123966942149e-06, "loss": 0.8397, "step": 140 }, { "epoch": 0.06006628003314002, "grad_norm": 3.309572907378494, "learning_rate": 5.991735537190083e-06, "loss": 0.8364, "step": 145 }, { "epoch": 0.06213753106876554, "grad_norm": 3.217107728350845, "learning_rate": 6.198347107438017e-06, "loss": 0.8405, "step": 150 }, { "epoch": 0.06420878210439106, "grad_norm": 2.9897980255799963, "learning_rate": 6.404958677685951e-06, "loss": 0.8332, "step": 155 }, { "epoch": 0.06628003314001657, "grad_norm": 3.105748326570053, "learning_rate": 6.611570247933885e-06, "loss": 0.837, "step": 160 }, { "epoch": 0.06835128417564208, "grad_norm": 2.9859815275040495, "learning_rate": 6.818181818181818e-06, "loss": 0.8309, "step": 165 }, { "epoch": 0.07042253521126761, "grad_norm": 3.128043179840772, "learning_rate": 7.0247933884297525e-06, "loss": 0.8147, "step": 170 }, { "epoch": 0.07249378624689312, "grad_norm": 3.2732056517181225, "learning_rate": 7.231404958677687e-06, "loss": 0.8333, "step": 175 }, { "epoch": 0.07456503728251865, "grad_norm": 3.2472063047978907, "learning_rate": 7.43801652892562e-06, "loss": 0.8291, "step": 180 }, { "epoch": 0.07663628831814416, "grad_norm": 3.282709196994602, "learning_rate": 7.644628099173555e-06, "loss": 0.8232, "step": 185 }, { "epoch": 0.07870753935376967, "grad_norm": 3.075253294075126, "learning_rate": 7.851239669421489e-06, "loss": 0.8193, "step": 190 }, { "epoch": 0.0807787903893952, "grad_norm": 3.0128837025123802, "learning_rate": 8.057851239669421e-06, "loss": 0.805, "step": 195 }, { "epoch": 0.08285004142502071, "grad_norm": 3.138564437194576, "learning_rate": 8.264462809917356e-06, "loss": 0.8087, "step": 200 }, { "epoch": 0.08492129246064622, "grad_norm": 3.4541810128498027, "learning_rate": 8.47107438016529e-06, "loss": 0.8076, "step": 205 }, { "epoch": 0.08699254349627175, "grad_norm": 3.0091577486317997, "learning_rate": 8.677685950413224e-06, "loss": 0.798, "step": 210 }, { "epoch": 0.08906379453189726, "grad_norm": 2.9445387744983895, "learning_rate": 8.884297520661158e-06, "loss": 0.8247, "step": 215 }, { "epoch": 0.09113504556752279, "grad_norm": 3.086638916429387, "learning_rate": 9.090909090909091e-06, "loss": 0.8204, "step": 220 }, { "epoch": 0.0932062966031483, "grad_norm": 2.9414208321363464, "learning_rate": 9.297520661157025e-06, "loss": 0.8113, "step": 225 }, { "epoch": 0.09527754763877382, "grad_norm": 3.1629151517479457, "learning_rate": 9.50413223140496e-06, "loss": 0.8033, "step": 230 }, { "epoch": 0.09734879867439934, "grad_norm": 2.9398734489839486, "learning_rate": 9.710743801652894e-06, "loss": 0.8019, "step": 235 }, { "epoch": 0.09942004971002485, "grad_norm": 3.145214350675458, "learning_rate": 9.917355371900828e-06, "loss": 0.8111, "step": 240 }, { "epoch": 0.10149130074565037, "grad_norm": 3.0149570428972012, "learning_rate": 9.999952928077044e-06, "loss": 0.8048, "step": 245 }, { "epoch": 0.1035625517812759, "grad_norm": 3.6918461332621053, "learning_rate": 9.999665269535307e-06, "loss": 0.7907, "step": 250 }, { "epoch": 0.1056338028169014, "grad_norm": 2.862006152795109, "learning_rate": 9.99911611854702e-06, "loss": 0.8058, "step": 255 }, { "epoch": 0.10770505385252693, "grad_norm": 2.999784427296385, "learning_rate": 9.998305503833872e-06, "loss": 0.8027, "step": 260 }, { "epoch": 0.10977630488815245, "grad_norm": 3.450350629969025, "learning_rate": 9.997233467792626e-06, "loss": 0.8068, "step": 265 }, { "epoch": 0.11184755592377796, "grad_norm": 3.083075255621663, "learning_rate": 9.995900066492902e-06, "loss": 0.7843, "step": 270 }, { "epoch": 0.11391880695940348, "grad_norm": 2.9762658508243103, "learning_rate": 9.994305369674242e-06, "loss": 0.7936, "step": 275 }, { "epoch": 0.115990057995029, "grad_norm": 3.1879318634864595, "learning_rate": 9.992449460742464e-06, "loss": 0.7695, "step": 280 }, { "epoch": 0.11806130903065451, "grad_norm": 2.9365396671861634, "learning_rate": 9.9903324367653e-06, "loss": 0.777, "step": 285 }, { "epoch": 0.12013256006628004, "grad_norm": 3.044542938179647, "learning_rate": 9.98795440846732e-06, "loss": 0.7705, "step": 290 }, { "epoch": 0.12220381110190555, "grad_norm": 2.9528885604414628, "learning_rate": 9.985315500224135e-06, "loss": 0.7773, "step": 295 }, { "epoch": 0.12427506213753108, "grad_norm": 3.0190471449546283, "learning_rate": 9.982415850055902e-06, "loss": 0.7667, "step": 300 }, { "epoch": 0.1263463131731566, "grad_norm": 2.963236127631455, "learning_rate": 9.979255609620095e-06, "loss": 0.7777, "step": 305 }, { "epoch": 0.12841756420878211, "grad_norm": 2.858761800732949, "learning_rate": 9.975834944203581e-06, "loss": 0.7874, "step": 310 }, { "epoch": 0.1304888152444076, "grad_norm": 3.014790563180228, "learning_rate": 9.972154032713973e-06, "loss": 0.7599, "step": 315 }, { "epoch": 0.13256006628003314, "grad_norm": 3.0276324603888933, "learning_rate": 9.968213067670265e-06, "loss": 0.7775, "step": 320 }, { "epoch": 0.13463131731565867, "grad_norm": 2.7516711927688937, "learning_rate": 9.964012255192776e-06, "loss": 0.7542, "step": 325 }, { "epoch": 0.13670256835128416, "grad_norm": 3.0176825448587055, "learning_rate": 9.959551814992364e-06, "loss": 0.7431, "step": 330 }, { "epoch": 0.1387738193869097, "grad_norm": 2.929681661466665, "learning_rate": 9.954831980358928e-06, "loss": 0.7464, "step": 335 }, { "epoch": 0.14084507042253522, "grad_norm": 2.950087392840952, "learning_rate": 9.949852998149217e-06, "loss": 0.7608, "step": 340 }, { "epoch": 0.14291632145816072, "grad_norm": 2.803389049814336, "learning_rate": 9.944615128773911e-06, "loss": 0.7526, "step": 345 }, { "epoch": 0.14498757249378624, "grad_norm": 2.892400417564368, "learning_rate": 9.939118646184007e-06, "loss": 0.7598, "step": 350 }, { "epoch": 0.14705882352941177, "grad_norm": 2.7919619010346666, "learning_rate": 9.933363837856485e-06, "loss": 0.7444, "step": 355 }, { "epoch": 0.1491300745650373, "grad_norm": 3.001830415960542, "learning_rate": 9.927351004779275e-06, "loss": 0.754, "step": 360 }, { "epoch": 0.1512013256006628, "grad_norm": 2.8555947108782047, "learning_rate": 9.921080461435522e-06, "loss": 0.7405, "step": 365 }, { "epoch": 0.15327257663628832, "grad_norm": 3.2248860327041178, "learning_rate": 9.914552535787122e-06, "loss": 0.7521, "step": 370 }, { "epoch": 0.15534382767191385, "grad_norm": 2.8634095201562944, "learning_rate": 9.90776756925758e-06, "loss": 0.7469, "step": 375 }, { "epoch": 0.15741507870753935, "grad_norm": 2.8847896604213243, "learning_rate": 9.900725916714157e-06, "loss": 0.7364, "step": 380 }, { "epoch": 0.15948632974316487, "grad_norm": 2.754954378494284, "learning_rate": 9.893427946449297e-06, "loss": 0.735, "step": 385 }, { "epoch": 0.1615575807787904, "grad_norm": 2.8463922565130657, "learning_rate": 9.885874040161373e-06, "loss": 0.7261, "step": 390 }, { "epoch": 0.1636288318144159, "grad_norm": 3.1933841338221396, "learning_rate": 9.878064592934723e-06, "loss": 0.7422, "step": 395 }, { "epoch": 0.16570008285004142, "grad_norm": 2.942331997917926, "learning_rate": 9.87000001321898e-06, "loss": 0.7224, "step": 400 }, { "epoch": 0.16777133388566695, "grad_norm": 2.7181370214808056, "learning_rate": 9.86168072280772e-06, "loss": 0.7289, "step": 405 }, { "epoch": 0.16984258492129245, "grad_norm": 2.664236544985896, "learning_rate": 9.853107156816393e-06, "loss": 0.7224, "step": 410 }, { "epoch": 0.17191383595691798, "grad_norm": 2.8278158668775064, "learning_rate": 9.844279763659566e-06, "loss": 0.7259, "step": 415 }, { "epoch": 0.1739850869925435, "grad_norm": 2.734121406292853, "learning_rate": 9.835199005027477e-06, "loss": 0.7159, "step": 420 }, { "epoch": 0.176056338028169, "grad_norm": 2.81662912645137, "learning_rate": 9.825865355861878e-06, "loss": 0.7116, "step": 425 }, { "epoch": 0.17812758906379453, "grad_norm": 2.7120179060153062, "learning_rate": 9.816279304331202e-06, "loss": 0.7236, "step": 430 }, { "epoch": 0.18019884009942005, "grad_norm": 3.005629026035039, "learning_rate": 9.806441351805025e-06, "loss": 0.723, "step": 435 }, { "epoch": 0.18227009113504558, "grad_norm": 2.720661996007401, "learning_rate": 9.79635201282785e-06, "loss": 0.7017, "step": 440 }, { "epoch": 0.18434134217067108, "grad_norm": 2.59980263448589, "learning_rate": 9.786011815092193e-06, "loss": 0.7061, "step": 445 }, { "epoch": 0.1864125932062966, "grad_norm": 2.9245413298738288, "learning_rate": 9.775421299410977e-06, "loss": 0.7254, "step": 450 }, { "epoch": 0.18848384424192213, "grad_norm": 2.804321911647625, "learning_rate": 9.764581019689255e-06, "loss": 0.6994, "step": 455 }, { "epoch": 0.19055509527754763, "grad_norm": 2.707915894172781, "learning_rate": 9.753491542895237e-06, "loss": 0.6941, "step": 460 }, { "epoch": 0.19262634631317316, "grad_norm": 2.9464922653669547, "learning_rate": 9.742153449030639e-06, "loss": 0.722, "step": 465 }, { "epoch": 0.19469759734879868, "grad_norm": 3.0813805567917316, "learning_rate": 9.730567331100333e-06, "loss": 0.7128, "step": 470 }, { "epoch": 0.19676884838442418, "grad_norm": 2.736601573318271, "learning_rate": 9.71873379508136e-06, "loss": 0.6924, "step": 475 }, { "epoch": 0.1988400994200497, "grad_norm": 2.744708064841264, "learning_rate": 9.706653459891207e-06, "loss": 0.7117, "step": 480 }, { "epoch": 0.20091135045567524, "grad_norm": 2.8038033966759777, "learning_rate": 9.694326957355452e-06, "loss": 0.6871, "step": 485 }, { "epoch": 0.20298260149130073, "grad_norm": 2.927433426929469, "learning_rate": 9.681754932174719e-06, "loss": 0.697, "step": 490 }, { "epoch": 0.20505385252692626, "grad_norm": 2.7528052712466438, "learning_rate": 9.668938041890952e-06, "loss": 0.6682, "step": 495 }, { "epoch": 0.2071251035625518, "grad_norm": 2.8027902784232266, "learning_rate": 9.655876956853025e-06, "loss": 0.6806, "step": 500 }, { "epoch": 0.2091963545981773, "grad_norm": 2.8677700330766838, "learning_rate": 9.64257236018169e-06, "loss": 0.6867, "step": 505 }, { "epoch": 0.2112676056338028, "grad_norm": 3.5468687443321896, "learning_rate": 9.629024947733836e-06, "loss": 0.6857, "step": 510 }, { "epoch": 0.21333885666942834, "grad_norm": 2.7277449914632066, "learning_rate": 9.615235428066106e-06, "loss": 0.675, "step": 515 }, { "epoch": 0.21541010770505387, "grad_norm": 2.858255659188691, "learning_rate": 9.601204522397826e-06, "loss": 0.6767, "step": 520 }, { "epoch": 0.21748135874067936, "grad_norm": 2.9887839025346095, "learning_rate": 9.586932964573298e-06, "loss": 0.6805, "step": 525 }, { "epoch": 0.2195526097763049, "grad_norm": 2.7629036489215446, "learning_rate": 9.572421501023403e-06, "loss": 0.6512, "step": 530 }, { "epoch": 0.22162386081193042, "grad_norm": 2.97216245301744, "learning_rate": 9.557670890726576e-06, "loss": 0.6772, "step": 535 }, { "epoch": 0.22369511184755592, "grad_norm": 2.680188998412034, "learning_rate": 9.5426819051691e-06, "loss": 0.659, "step": 540 }, { "epoch": 0.22576636288318144, "grad_norm": 2.996121643522832, "learning_rate": 9.527455328304756e-06, "loss": 0.6811, "step": 545 }, { "epoch": 0.22783761391880697, "grad_norm": 3.092632018194836, "learning_rate": 9.511991956513828e-06, "loss": 0.6637, "step": 550 }, { "epoch": 0.22990886495443247, "grad_norm": 3.0336085537233233, "learning_rate": 9.496292598561445e-06, "loss": 0.6577, "step": 555 }, { "epoch": 0.231980115990058, "grad_norm": 2.870159051940467, "learning_rate": 9.480358075555278e-06, "loss": 0.684, "step": 560 }, { "epoch": 0.23405136702568352, "grad_norm": 2.9239194773904535, "learning_rate": 9.464189220902603e-06, "loss": 0.6718, "step": 565 }, { "epoch": 0.23612261806130902, "grad_norm": 2.645519279429444, "learning_rate": 9.447786880266706e-06, "loss": 0.6491, "step": 570 }, { "epoch": 0.23819386909693455, "grad_norm": 2.6967942243273573, "learning_rate": 9.431151911522656e-06, "loss": 0.6477, "step": 575 }, { "epoch": 0.24026512013256007, "grad_norm": 2.7528580762215387, "learning_rate": 9.414285184712432e-06, "loss": 0.6626, "step": 580 }, { "epoch": 0.24233637116818557, "grad_norm": 2.7483048673874313, "learning_rate": 9.397187581999424e-06, "loss": 0.6467, "step": 585 }, { "epoch": 0.2444076222038111, "grad_norm": 3.038026877579559, "learning_rate": 9.37985999762229e-06, "loss": 0.6469, "step": 590 }, { "epoch": 0.24647887323943662, "grad_norm": 2.615989610347169, "learning_rate": 9.362303337848188e-06, "loss": 0.6264, "step": 595 }, { "epoch": 0.24855012427506215, "grad_norm": 2.819797507137102, "learning_rate": 9.344518520925377e-06, "loss": 0.6514, "step": 600 }, { "epoch": 0.2506213753106877, "grad_norm": 2.9708673929402383, "learning_rate": 9.326506477035179e-06, "loss": 0.65, "step": 605 }, { "epoch": 0.2526926263463132, "grad_norm": 3.0927367826052836, "learning_rate": 9.308268148243355e-06, "loss": 0.6635, "step": 610 }, { "epoch": 0.2547638773819387, "grad_norm": 2.761723676907011, "learning_rate": 9.289804488450805e-06, "loss": 0.638, "step": 615 }, { "epoch": 0.25683512841756423, "grad_norm": 2.7990342734643736, "learning_rate": 9.271116463343692e-06, "loss": 0.6493, "step": 620 }, { "epoch": 0.25890637945318973, "grad_norm": 3.0340511918514195, "learning_rate": 9.25220505034293e-06, "loss": 0.6317, "step": 625 }, { "epoch": 0.2609776304888152, "grad_norm": 2.976081215633119, "learning_rate": 9.23307123855307e-06, "loss": 0.6397, "step": 630 }, { "epoch": 0.2630488815244408, "grad_norm": 3.003798009542892, "learning_rate": 9.213716028710558e-06, "loss": 0.6128, "step": 635 }, { "epoch": 0.2651201325600663, "grad_norm": 2.655163338826258, "learning_rate": 9.194140433131397e-06, "loss": 0.6273, "step": 640 }, { "epoch": 0.2671913835956918, "grad_norm": 2.8606088566026657, "learning_rate": 9.174345475658208e-06, "loss": 0.6332, "step": 645 }, { "epoch": 0.26926263463131733, "grad_norm": 2.8317445925324862, "learning_rate": 9.154332191606671e-06, "loss": 0.6539, "step": 650 }, { "epoch": 0.27133388566694283, "grad_norm": 2.7049443755335636, "learning_rate": 9.134101627711384e-06, "loss": 0.6227, "step": 655 }, { "epoch": 0.27340513670256833, "grad_norm": 2.6491560573079433, "learning_rate": 9.113654842071114e-06, "loss": 0.6232, "step": 660 }, { "epoch": 0.2754763877381939, "grad_norm": 2.570081912799733, "learning_rate": 9.092992904093451e-06, "loss": 0.6193, "step": 665 }, { "epoch": 0.2775476387738194, "grad_norm": 2.776252306360059, "learning_rate": 9.072116894438885e-06, "loss": 0.6082, "step": 670 }, { "epoch": 0.2796188898094449, "grad_norm": 2.600188968920606, "learning_rate": 9.051027904964279e-06, "loss": 0.611, "step": 675 }, { "epoch": 0.28169014084507044, "grad_norm": 2.6237462760702805, "learning_rate": 9.029727038665765e-06, "loss": 0.6155, "step": 680 }, { "epoch": 0.28376139188069593, "grad_norm": 2.7793821267332706, "learning_rate": 9.008215409621053e-06, "loss": 0.6113, "step": 685 }, { "epoch": 0.28583264291632143, "grad_norm": 2.568985635589286, "learning_rate": 8.986494142931168e-06, "loss": 0.6111, "step": 690 }, { "epoch": 0.287903893951947, "grad_norm": 2.862973856951621, "learning_rate": 8.964564374661597e-06, "loss": 0.6147, "step": 695 }, { "epoch": 0.2899751449875725, "grad_norm": 2.693156935597711, "learning_rate": 8.94242725178288e-06, "loss": 0.6119, "step": 700 }, { "epoch": 0.292046396023198, "grad_norm": 2.722980667225857, "learning_rate": 8.920083932110608e-06, "loss": 0.6051, "step": 705 }, { "epoch": 0.29411764705882354, "grad_norm": 2.5478479825945506, "learning_rate": 8.89753558424488e-06, "loss": 0.6005, "step": 710 }, { "epoch": 0.29618889809444904, "grad_norm": 2.7631628768587118, "learning_rate": 8.874783387509181e-06, "loss": 0.5847, "step": 715 }, { "epoch": 0.2982601491300746, "grad_norm": 2.7857659030181297, "learning_rate": 8.851828531888692e-06, "loss": 0.5916, "step": 720 }, { "epoch": 0.3003314001657001, "grad_norm": 2.745002755561951, "learning_rate": 8.828672217968055e-06, "loss": 0.5903, "step": 725 }, { "epoch": 0.3024026512013256, "grad_norm": 2.6664489727061906, "learning_rate": 8.805315656868587e-06, "loss": 0.5897, "step": 730 }, { "epoch": 0.30447390223695114, "grad_norm": 2.734961652522829, "learning_rate": 8.781760070184933e-06, "loss": 0.5907, "step": 735 }, { "epoch": 0.30654515327257664, "grad_norm": 2.5760271183900745, "learning_rate": 8.75800668992117e-06, "loss": 0.5783, "step": 740 }, { "epoch": 0.30861640430820214, "grad_norm": 2.5392711770670413, "learning_rate": 8.734056758426367e-06, "loss": 0.6151, "step": 745 }, { "epoch": 0.3106876553438277, "grad_norm": 2.8981464315657592, "learning_rate": 8.709911528329623e-06, "loss": 0.6023, "step": 750 }, { "epoch": 0.3127589063794532, "grad_norm": 2.5242992774227693, "learning_rate": 8.685572262474538e-06, "loss": 0.5891, "step": 755 }, { "epoch": 0.3148301574150787, "grad_norm": 2.6784870054813257, "learning_rate": 8.661040233853166e-06, "loss": 0.577, "step": 760 }, { "epoch": 0.31690140845070425, "grad_norm": 2.8736188958860396, "learning_rate": 8.636316725539445e-06, "loss": 0.6014, "step": 765 }, { "epoch": 0.31897265948632975, "grad_norm": 2.9168628625784403, "learning_rate": 8.611403030622074e-06, "loss": 0.5794, "step": 770 }, { "epoch": 0.32104391052195524, "grad_norm": 2.7036097538774784, "learning_rate": 8.586300452136895e-06, "loss": 0.6009, "step": 775 }, { "epoch": 0.3231151615575808, "grad_norm": 3.00542942619399, "learning_rate": 8.561010302998734e-06, "loss": 0.5921, "step": 780 }, { "epoch": 0.3251864125932063, "grad_norm": 2.6783322273581867, "learning_rate": 8.535533905932739e-06, "loss": 0.5832, "step": 785 }, { "epoch": 0.3272576636288318, "grad_norm": 2.5976810097932233, "learning_rate": 8.509872593405189e-06, "loss": 0.5754, "step": 790 }, { "epoch": 0.32932891466445735, "grad_norm": 2.5768066352748775, "learning_rate": 8.484027707553818e-06, "loss": 0.5702, "step": 795 }, { "epoch": 0.33140016570008285, "grad_norm": 2.6290931317600212, "learning_rate": 8.458000600117604e-06, "loss": 0.5685, "step": 800 }, { "epoch": 0.33347141673570835, "grad_norm": 2.6532094232697534, "learning_rate": 8.43179263236608e-06, "loss": 0.5614, "step": 805 }, { "epoch": 0.3355426677713339, "grad_norm": 2.6681787622121216, "learning_rate": 8.40540517502813e-06, "loss": 0.5674, "step": 810 }, { "epoch": 0.3376139188069594, "grad_norm": 2.802675377347152, "learning_rate": 8.378839608220304e-06, "loss": 0.5702, "step": 815 }, { "epoch": 0.3396851698425849, "grad_norm": 2.6653083491338037, "learning_rate": 8.35209732137463e-06, "loss": 0.564, "step": 820 }, { "epoch": 0.34175642087821045, "grad_norm": 2.6040328931386876, "learning_rate": 8.32517971316595e-06, "loss": 0.5638, "step": 825 }, { "epoch": 0.34382767191383595, "grad_norm": 2.727412029325625, "learning_rate": 8.298088191438753e-06, "loss": 0.5674, "step": 830 }, { "epoch": 0.34589892294946145, "grad_norm": 2.6428555995518606, "learning_rate": 8.270824173133563e-06, "loss": 0.5513, "step": 835 }, { "epoch": 0.347970173985087, "grad_norm": 2.5321677401385774, "learning_rate": 8.243389084212808e-06, "loss": 0.5575, "step": 840 }, { "epoch": 0.3500414250207125, "grad_norm": 2.5780005638043466, "learning_rate": 8.215784359586257e-06, "loss": 0.5502, "step": 845 }, { "epoch": 0.352112676056338, "grad_norm": 2.648281328508928, "learning_rate": 8.188011443035962e-06, "loss": 0.5537, "step": 850 }, { "epoch": 0.35418392709196356, "grad_norm": 2.7895654555486, "learning_rate": 8.160071787140742e-06, "loss": 0.5608, "step": 855 }, { "epoch": 0.35625517812758906, "grad_norm": 27.22295564927489, "learning_rate": 8.131966853200226e-06, "loss": 0.558, "step": 860 }, { "epoch": 0.35832642916321455, "grad_norm": 2.789019951462418, "learning_rate": 8.103698111158405e-06, "loss": 0.5556, "step": 865 }, { "epoch": 0.3603976801988401, "grad_norm": 2.9443726960703502, "learning_rate": 8.075267039526764e-06, "loss": 0.572, "step": 870 }, { "epoch": 0.3624689312344656, "grad_norm": 2.614192265112768, "learning_rate": 8.046675125306948e-06, "loss": 0.5404, "step": 875 }, { "epoch": 0.36454018227009116, "grad_norm": 2.737445983536856, "learning_rate": 8.017923863912989e-06, "loss": 0.554, "step": 880 }, { "epoch": 0.36661143330571666, "grad_norm": 2.508756520376147, "learning_rate": 7.989014759093095e-06, "loss": 0.5409, "step": 885 }, { "epoch": 0.36868268434134216, "grad_norm": 2.5666123747864633, "learning_rate": 7.959949322850994e-06, "loss": 0.5491, "step": 890 }, { "epoch": 0.3707539353769677, "grad_norm": 2.8084429686477757, "learning_rate": 7.930729075366867e-06, "loss": 0.5487, "step": 895 }, { "epoch": 0.3728251864125932, "grad_norm": 2.6381550938386895, "learning_rate": 7.901355544917827e-06, "loss": 0.5357, "step": 900 }, { "epoch": 0.3748964374482187, "grad_norm": 2.657165337623562, "learning_rate": 7.87183026779799e-06, "loss": 0.5422, "step": 905 }, { "epoch": 0.37696768848384427, "grad_norm": 2.4730595975113423, "learning_rate": 7.842154788238124e-06, "loss": 0.5472, "step": 910 }, { "epoch": 0.37903893951946976, "grad_norm": 2.660750141652071, "learning_rate": 7.812330658324884e-06, "loss": 0.5348, "step": 915 }, { "epoch": 0.38111019055509526, "grad_norm": 2.5624322891454154, "learning_rate": 7.782359437919644e-06, "loss": 0.529, "step": 920 }, { "epoch": 0.3831814415907208, "grad_norm": 2.711216565213947, "learning_rate": 7.75224269457689e-06, "loss": 0.5385, "step": 925 }, { "epoch": 0.3852526926263463, "grad_norm": 2.740529364057834, "learning_rate": 7.721982003462255e-06, "loss": 0.5547, "step": 930 }, { "epoch": 0.3873239436619718, "grad_norm": 2.6396154905702978, "learning_rate": 7.691578947270122e-06, "loss": 0.5395, "step": 935 }, { "epoch": 0.38939519469759737, "grad_norm": 2.653006866640713, "learning_rate": 7.661035116140856e-06, "loss": 0.5457, "step": 940 }, { "epoch": 0.39146644573322287, "grad_norm": 2.5458936112330957, "learning_rate": 7.63035210757763e-06, "loss": 0.5255, "step": 945 }, { "epoch": 0.39353769676884837, "grad_norm": 2.5845437613279225, "learning_rate": 7.599531526362873e-06, "loss": 0.5318, "step": 950 }, { "epoch": 0.3956089478044739, "grad_norm": 2.7236464764396002, "learning_rate": 7.568574984474335e-06, "loss": 0.5275, "step": 955 }, { "epoch": 0.3976801988400994, "grad_norm": 2.6448733889793297, "learning_rate": 7.537484101000787e-06, "loss": 0.5346, "step": 960 }, { "epoch": 0.3997514498757249, "grad_norm": 2.7220135623319623, "learning_rate": 7.506260502057325e-06, "loss": 0.5237, "step": 965 }, { "epoch": 0.40182270091135047, "grad_norm": 2.675354838421343, "learning_rate": 7.474905820700334e-06, "loss": 0.5209, "step": 970 }, { "epoch": 0.40389395194697597, "grad_norm": 2.6000873366499984, "learning_rate": 7.443421696842066e-06, "loss": 0.5274, "step": 975 }, { "epoch": 0.40596520298260147, "grad_norm": 2.578395638536851, "learning_rate": 7.411809777164873e-06, "loss": 0.5032, "step": 980 }, { "epoch": 0.408036454018227, "grad_norm": 2.5797458480654156, "learning_rate": 7.380071715035089e-06, "loss": 0.5065, "step": 985 }, { "epoch": 0.4101077050538525, "grad_norm": 2.490847130434567, "learning_rate": 7.3482091704165405e-06, "loss": 0.5167, "step": 990 }, { "epoch": 0.412178956089478, "grad_norm": 2.653640432329004, "learning_rate": 7.316223809783745e-06, "loss": 0.5359, "step": 995 }, { "epoch": 0.4142502071251036, "grad_norm": 2.4167845003588724, "learning_rate": 7.284117306034733e-06, "loss": 0.5144, "step": 1000 }, { "epoch": 0.4163214581607291, "grad_norm": 2.463374241422698, "learning_rate": 7.2518913384035685e-06, "loss": 0.502, "step": 1005 }, { "epoch": 0.4183927091963546, "grad_norm": 2.457094856070288, "learning_rate": 7.219547592372512e-06, "loss": 0.5122, "step": 1010 }, { "epoch": 0.4204639602319801, "grad_norm": 2.5981381889389255, "learning_rate": 7.187087759583869e-06, "loss": 0.5098, "step": 1015 }, { "epoch": 0.4225352112676056, "grad_norm": 2.708667740555934, "learning_rate": 7.15451353775151e-06, "loss": 0.5081, "step": 1020 }, { "epoch": 0.4246064623032311, "grad_norm": 2.5153495881301473, "learning_rate": 7.121826630572084e-06, "loss": 0.5087, "step": 1025 }, { "epoch": 0.4266777133388567, "grad_norm": 2.587890800949317, "learning_rate": 7.089028747635908e-06, "loss": 0.5116, "step": 1030 }, { "epoch": 0.4287489643744822, "grad_norm": 2.6075326057642663, "learning_rate": 7.056121604337554e-06, "loss": 0.4922, "step": 1035 }, { "epoch": 0.43082021541010773, "grad_norm": 2.5809881464924596, "learning_rate": 7.023106921786118e-06, "loss": 0.485, "step": 1040 }, { "epoch": 0.43289146644573323, "grad_norm": 2.5900481862569245, "learning_rate": 6.9899864267152275e-06, "loss": 0.5143, "step": 1045 }, { "epoch": 0.43496271748135873, "grad_norm": 2.516175280346361, "learning_rate": 6.956761851392706e-06, "loss": 0.5052, "step": 1050 }, { "epoch": 0.4370339685169843, "grad_norm": 2.6806235578645183, "learning_rate": 6.9234349335299835e-06, "loss": 0.5074, "step": 1055 }, { "epoch": 0.4391052195526098, "grad_norm": 2.7284511939045597, "learning_rate": 6.890007416191209e-06, "loss": 0.503, "step": 1060 }, { "epoch": 0.4411764705882353, "grad_norm": 2.477603303058047, "learning_rate": 6.8564810477020835e-06, "loss": 0.506, "step": 1065 }, { "epoch": 0.44324772162386084, "grad_norm": 2.653270109326483, "learning_rate": 6.822857581558423e-06, "loss": 0.4986, "step": 1070 }, { "epoch": 0.44531897265948633, "grad_norm": 2.5988281793679597, "learning_rate": 6.789138776334441e-06, "loss": 0.5045, "step": 1075 }, { "epoch": 0.44739022369511183, "grad_norm": 2.5298868654842934, "learning_rate": 6.7553263955907755e-06, "loss": 0.4897, "step": 1080 }, { "epoch": 0.4494614747307374, "grad_norm": 2.6705115368242143, "learning_rate": 6.721422207782249e-06, "loss": 0.4909, "step": 1085 }, { "epoch": 0.4515327257663629, "grad_norm": 2.8067497531424475, "learning_rate": 6.687427986165379e-06, "loss": 0.4772, "step": 1090 }, { "epoch": 0.4536039768019884, "grad_norm": 2.4779791652714525, "learning_rate": 6.653345508705629e-06, "loss": 0.4894, "step": 1095 }, { "epoch": 0.45567522783761394, "grad_norm": 2.600863340470681, "learning_rate": 6.6191765579844205e-06, "loss": 0.4846, "step": 1100 }, { "epoch": 0.45774647887323944, "grad_norm": 2.6188828334911674, "learning_rate": 6.584922921105894e-06, "loss": 0.4824, "step": 1105 }, { "epoch": 0.45981772990886494, "grad_norm": 2.5005489988116607, "learning_rate": 6.550586389603451e-06, "loss": 0.4772, "step": 1110 }, { "epoch": 0.4618889809444905, "grad_norm": 2.5140230692930303, "learning_rate": 6.5161687593460395e-06, "loss": 0.4758, "step": 1115 }, { "epoch": 0.463960231980116, "grad_norm": 2.630578433194268, "learning_rate": 6.481671830444243e-06, "loss": 0.4823, "step": 1120 }, { "epoch": 0.4660314830157415, "grad_norm": 2.543874733832436, "learning_rate": 6.447097407156114e-06, "loss": 0.4904, "step": 1125 }, { "epoch": 0.46810273405136704, "grad_norm": 2.553101924169542, "learning_rate": 6.412447297792818e-06, "loss": 0.4789, "step": 1130 }, { "epoch": 0.47017398508699254, "grad_norm": 2.4731076235508844, "learning_rate": 6.377723314624057e-06, "loss": 0.4746, "step": 1135 }, { "epoch": 0.47224523612261804, "grad_norm": 2.5022077096791624, "learning_rate": 6.3429272737832726e-06, "loss": 0.4667, "step": 1140 }, { "epoch": 0.4743164871582436, "grad_norm": 2.5543373787283534, "learning_rate": 6.308060995172673e-06, "loss": 0.4915, "step": 1145 }, { "epoch": 0.4763877381938691, "grad_norm": 2.622546687803893, "learning_rate": 6.273126302368037e-06, "loss": 0.4705, "step": 1150 }, { "epoch": 0.4784589892294946, "grad_norm": 2.629390222971599, "learning_rate": 6.238125022523343e-06, "loss": 0.4729, "step": 1155 }, { "epoch": 0.48053024026512015, "grad_norm": 2.7927865993974605, "learning_rate": 6.203058986275207e-06, "loss": 0.4692, "step": 1160 }, { "epoch": 0.48260149130074564, "grad_norm": 2.5414535005126484, "learning_rate": 6.1679300276471285e-06, "loss": 0.466, "step": 1165 }, { "epoch": 0.48467274233637114, "grad_norm": 2.8013812147684805, "learning_rate": 6.132739983953579e-06, "loss": 0.4698, "step": 1170 }, { "epoch": 0.4867439933719967, "grad_norm": 2.5102043448323705, "learning_rate": 6.097490695703896e-06, "loss": 0.4767, "step": 1175 }, { "epoch": 0.4888152444076222, "grad_norm": 2.5792793701605494, "learning_rate": 6.062184006506027e-06, "loss": 0.4724, "step": 1180 }, { "epoch": 0.4908864954432477, "grad_norm": 2.6887265457748577, "learning_rate": 6.026821762970102e-06, "loss": 0.4711, "step": 1185 }, { "epoch": 0.49295774647887325, "grad_norm": 2.511638299103864, "learning_rate": 5.991405814611855e-06, "loss": 0.4696, "step": 1190 }, { "epoch": 0.49502899751449875, "grad_norm": 2.4500612981641243, "learning_rate": 5.955938013755888e-06, "loss": 0.4657, "step": 1195 }, { "epoch": 0.4971002485501243, "grad_norm": 2.534965922427365, "learning_rate": 5.920420215438794e-06, "loss": 0.4533, "step": 1200 }, { "epoch": 0.4991714995857498, "grad_norm": 2.5938753967673027, "learning_rate": 5.8848542773121285e-06, "loss": 0.4665, "step": 1205 }, { "epoch": 0.5012427506213754, "grad_norm": 2.627073645165619, "learning_rate": 5.849242059545259e-06, "loss": 0.4775, "step": 1210 }, { "epoch": 0.5033140016570008, "grad_norm": 2.53636109370232, "learning_rate": 5.81358542472807e-06, "loss": 0.45, "step": 1215 }, { "epoch": 0.5053852526926264, "grad_norm": 2.7509884648190144, "learning_rate": 5.777886237773542e-06, "loss": 0.4821, "step": 1220 }, { "epoch": 0.5074565037282519, "grad_norm": 2.4871275513398508, "learning_rate": 5.742146365820223e-06, "loss": 0.4499, "step": 1225 }, { "epoch": 0.5095277547638773, "grad_norm": 3.024696572327163, "learning_rate": 5.706367678134562e-06, "loss": 0.4469, "step": 1230 }, { "epoch": 0.5115990057995029, "grad_norm": 2.4038144658191567, "learning_rate": 5.670552046013151e-06, "loss": 0.457, "step": 1235 }, { "epoch": 0.5136702568351285, "grad_norm": 2.6556357162533875, "learning_rate": 5.634701342684852e-06, "loss": 0.4562, "step": 1240 }, { "epoch": 0.5157415078707539, "grad_norm": 2.703587191311131, "learning_rate": 5.598817443212813e-06, "loss": 0.4522, "step": 1245 }, { "epoch": 0.5178127589063795, "grad_norm": 2.463355539359599, "learning_rate": 5.562902224396416e-06, "loss": 0.4461, "step": 1250 }, { "epoch": 0.519884009942005, "grad_norm": 2.497969768284715, "learning_rate": 5.526957564673098e-06, "loss": 0.453, "step": 1255 }, { "epoch": 0.5219552609776305, "grad_norm": 2.4098686946994423, "learning_rate": 5.49098534402012e-06, "loss": 0.4453, "step": 1260 }, { "epoch": 0.524026512013256, "grad_norm": 2.587788264342658, "learning_rate": 5.454987443856235e-06, "loss": 0.4579, "step": 1265 }, { "epoch": 0.5260977630488816, "grad_norm": 2.4712478775850224, "learning_rate": 5.418965746943281e-06, "loss": 0.4489, "step": 1270 }, { "epoch": 0.528169014084507, "grad_norm": 2.370937535314608, "learning_rate": 5.3829221372877175e-06, "loss": 0.4388, "step": 1275 }, { "epoch": 0.5302402651201326, "grad_norm": 2.462884882416935, "learning_rate": 5.34685850004208e-06, "loss": 0.4459, "step": 1280 }, { "epoch": 0.5323115161557581, "grad_norm": 2.4476459022909967, "learning_rate": 5.310776721406392e-06, "loss": 0.4406, "step": 1285 }, { "epoch": 0.5343827671913836, "grad_norm": 2.587472505335473, "learning_rate": 5.2746786885295034e-06, "loss": 0.4383, "step": 1290 }, { "epoch": 0.5364540182270091, "grad_norm": 2.5278245670262924, "learning_rate": 5.238566289410396e-06, "loss": 0.4411, "step": 1295 }, { "epoch": 0.5385252692626347, "grad_norm": 2.362318734406345, "learning_rate": 5.2024414127994325e-06, "loss": 0.445, "step": 1300 }, { "epoch": 0.5405965202982601, "grad_norm": 2.314271295243484, "learning_rate": 5.166305948099574e-06, "loss": 0.4397, "step": 1305 }, { "epoch": 0.5426677713338857, "grad_norm": 2.650324457889945, "learning_rate": 5.13016178526756e-06, "loss": 0.4431, "step": 1310 }, { "epoch": 0.5447390223695112, "grad_norm": 2.463519397971866, "learning_rate": 5.094010814715062e-06, "loss": 0.4454, "step": 1315 }, { "epoch": 0.5468102734051367, "grad_norm": 2.5313743411672394, "learning_rate": 5.057854927209804e-06, "loss": 0.45, "step": 1320 }, { "epoch": 0.5488815244407622, "grad_norm": 2.6755963743637974, "learning_rate": 5.0216960137766805e-06, "loss": 0.4264, "step": 1325 }, { "epoch": 0.5509527754763878, "grad_norm": 2.427631997009141, "learning_rate": 4.985535965598843e-06, "loss": 0.4384, "step": 1330 }, { "epoch": 0.5530240265120132, "grad_norm": 2.5060197767889067, "learning_rate": 4.949376673918802e-06, "loss": 0.4321, "step": 1335 }, { "epoch": 0.5550952775476388, "grad_norm": 2.3159927224227737, "learning_rate": 4.913220029939491e-06, "loss": 0.4228, "step": 1340 }, { "epoch": 0.5571665285832643, "grad_norm": 2.481751099037594, "learning_rate": 4.877067924725368e-06, "loss": 0.4359, "step": 1345 }, { "epoch": 0.5592377796188898, "grad_norm": 2.5647460359628864, "learning_rate": 4.840922249103506e-06, "loss": 0.4219, "step": 1350 }, { "epoch": 0.5613090306545153, "grad_norm": 2.6429112668685946, "learning_rate": 4.804784893564697e-06, "loss": 0.4356, "step": 1355 }, { "epoch": 0.5633802816901409, "grad_norm": 2.54142690113186, "learning_rate": 4.7686577481645745e-06, "loss": 0.4334, "step": 1360 }, { "epoch": 0.5654515327257663, "grad_norm": 2.4782181638293648, "learning_rate": 4.732542702424759e-06, "loss": 0.4308, "step": 1365 }, { "epoch": 0.5675227837613919, "grad_norm": 2.383597108320401, "learning_rate": 4.696441645234042e-06, "loss": 0.4272, "step": 1370 }, { "epoch": 0.5695940347970174, "grad_norm": 2.3828375155581996, "learning_rate": 4.660356464749578e-06, "loss": 0.4266, "step": 1375 }, { "epoch": 0.5716652858326429, "grad_norm": 2.451369542654729, "learning_rate": 4.624289048298147e-06, "loss": 0.4103, "step": 1380 }, { "epoch": 0.5737365368682684, "grad_norm": 2.409118595637492, "learning_rate": 4.588241282277428e-06, "loss": 0.4286, "step": 1385 }, { "epoch": 0.575807787903894, "grad_norm": 2.434308902065985, "learning_rate": 4.55221505205734e-06, "loss": 0.4149, "step": 1390 }, { "epoch": 0.5778790389395194, "grad_norm": 2.3190173742008375, "learning_rate": 4.516212241881448e-06, "loss": 0.4237, "step": 1395 }, { "epoch": 0.579950289975145, "grad_norm": 2.4445623701164907, "learning_rate": 4.480234734768393e-06, "loss": 0.4232, "step": 1400 }, { "epoch": 0.5820215410107705, "grad_norm": 2.3474856012459293, "learning_rate": 4.444284412413418e-06, "loss": 0.4089, "step": 1405 }, { "epoch": 0.584092792046396, "grad_norm": 2.3965073516929225, "learning_rate": 4.408363155089952e-06, "loss": 0.4077, "step": 1410 }, { "epoch": 0.5861640430820215, "grad_norm": 2.419566324160256, "learning_rate": 4.3724728415512585e-06, "loss": 0.408, "step": 1415 }, { "epoch": 0.5882352941176471, "grad_norm": 2.407231073280321, "learning_rate": 4.3366153489321855e-06, "loss": 0.4045, "step": 1420 }, { "epoch": 0.5903065451532725, "grad_norm": 2.4248404044481755, "learning_rate": 4.30079255265098e-06, "loss": 0.401, "step": 1425 }, { "epoch": 0.5923777961888981, "grad_norm": 2.4509147233492024, "learning_rate": 4.265006326311199e-06, "loss": 0.4135, "step": 1430 }, { "epoch": 0.5944490472245236, "grad_norm": 2.506327837624517, "learning_rate": 4.229258541603723e-06, "loss": 0.4025, "step": 1435 }, { "epoch": 0.5965202982601492, "grad_norm": 2.3288288213604114, "learning_rate": 4.1935510682088545e-06, "loss": 0.4131, "step": 1440 }, { "epoch": 0.5985915492957746, "grad_norm": 2.5535667086951483, "learning_rate": 4.157885773698535e-06, "loss": 0.4224, "step": 1445 }, { "epoch": 0.6006628003314002, "grad_norm": 2.3980759908272957, "learning_rate": 4.122264523438668e-06, "loss": 0.4181, "step": 1450 }, { "epoch": 0.6027340513670257, "grad_norm": 2.6382797118011907, "learning_rate": 4.086689180491554e-06, "loss": 0.4126, "step": 1455 }, { "epoch": 0.6048053024026512, "grad_norm": 2.370459943519768, "learning_rate": 4.051161605518453e-06, "loss": 0.4071, "step": 1460 }, { "epoch": 0.6068765534382767, "grad_norm": 2.6231604916349243, "learning_rate": 4.015683656682255e-06, "loss": 0.3949, "step": 1465 }, { "epoch": 0.6089478044739023, "grad_norm": 2.3593887618428835, "learning_rate": 3.980257189550316e-06, "loss": 0.4072, "step": 1470 }, { "epoch": 0.6110190555095277, "grad_norm": 2.5041108931455724, "learning_rate": 3.94488405699739e-06, "loss": 0.413, "step": 1475 }, { "epoch": 0.6130903065451533, "grad_norm": 2.458377689355407, "learning_rate": 3.909566109108727e-06, "loss": 0.4053, "step": 1480 }, { "epoch": 0.6151615575807788, "grad_norm": 2.5609088224080114, "learning_rate": 3.874305193083313e-06, "loss": 0.4097, "step": 1485 }, { "epoch": 0.6172328086164043, "grad_norm": 2.353213081621768, "learning_rate": 3.839103153137247e-06, "loss": 0.4037, "step": 1490 }, { "epoch": 0.6193040596520298, "grad_norm": 2.4362505512889765, "learning_rate": 3.803961830407297e-06, "loss": 0.4033, "step": 1495 }, { "epoch": 0.6213753106876554, "grad_norm": 2.321841989912693, "learning_rate": 3.768883062854598e-06, "loss": 0.3929, "step": 1500 }, { "epoch": 0.6234465617232808, "grad_norm": 2.394226657041569, "learning_rate": 3.7338686851685267e-06, "loss": 0.3915, "step": 1505 }, { "epoch": 0.6255178127589064, "grad_norm": 2.4125632375573196, "learning_rate": 3.6989205286707398e-06, "loss": 0.4003, "step": 1510 }, { "epoch": 0.6275890637945319, "grad_norm": 2.4436823556352114, "learning_rate": 3.664040421219393e-06, "loss": 0.3893, "step": 1515 }, { "epoch": 0.6296603148301574, "grad_norm": 2.5097377765923126, "learning_rate": 3.6292301871135425e-06, "loss": 0.3872, "step": 1520 }, { "epoch": 0.6317315658657829, "grad_norm": 2.3913150951864055, "learning_rate": 3.59449164699773e-06, "loss": 0.4087, "step": 1525 }, { "epoch": 0.6338028169014085, "grad_norm": 2.421329521004043, "learning_rate": 3.55982661776676e-06, "loss": 0.3943, "step": 1530 }, { "epoch": 0.6358740679370339, "grad_norm": 2.4850817809686245, "learning_rate": 3.5252369124706697e-06, "loss": 0.4008, "step": 1535 }, { "epoch": 0.6379453189726595, "grad_norm": 2.5103504729138244, "learning_rate": 3.4907243402199013e-06, "loss": 0.3996, "step": 1540 }, { "epoch": 0.640016570008285, "grad_norm": 2.333429180578666, "learning_rate": 3.4562907060906908e-06, "loss": 0.3829, "step": 1545 }, { "epoch": 0.6420878210439105, "grad_norm": 2.298002592819971, "learning_rate": 3.4219378110306523e-06, "loss": 0.3902, "step": 1550 }, { "epoch": 0.644159072079536, "grad_norm": 2.3995879040330306, "learning_rate": 3.3876674517645815e-06, "loss": 0.3864, "step": 1555 }, { "epoch": 0.6462303231151616, "grad_norm": 2.545531405797542, "learning_rate": 3.353481420700495e-06, "loss": 0.3971, "step": 1560 }, { "epoch": 0.648301574150787, "grad_norm": 2.529902275281575, "learning_rate": 3.319381505835868e-06, "loss": 0.3766, "step": 1565 }, { "epoch": 0.6503728251864126, "grad_norm": 2.3457843434005903, "learning_rate": 3.285369490664133e-06, "loss": 0.3896, "step": 1570 }, { "epoch": 0.6524440762220381, "grad_norm": 2.405826242826769, "learning_rate": 3.251447154081394e-06, "loss": 0.3876, "step": 1575 }, { "epoch": 0.6545153272576636, "grad_norm": 2.425548539422475, "learning_rate": 3.2176162702933816e-06, "loss": 0.3776, "step": 1580 }, { "epoch": 0.6565865782932891, "grad_norm": 2.4563539237764, "learning_rate": 3.183878608722669e-06, "loss": 0.3899, "step": 1585 }, { "epoch": 0.6586578293289147, "grad_norm": 2.5401846592132253, "learning_rate": 3.150235933916115e-06, "loss": 0.3908, "step": 1590 }, { "epoch": 0.6607290803645401, "grad_norm": 2.3303608755993395, "learning_rate": 3.1166900054525873e-06, "loss": 0.3869, "step": 1595 }, { "epoch": 0.6628003314001657, "grad_norm": 2.5209044310957225, "learning_rate": 3.0832425778509235e-06, "loss": 0.3743, "step": 1600 }, { "epoch": 0.6648715824357913, "grad_norm": 2.3848882437290895, "learning_rate": 3.049895400478174e-06, "loss": 0.3888, "step": 1605 }, { "epoch": 0.6669428334714167, "grad_norm": 2.2538857098179044, "learning_rate": 3.0166502174581012e-06, "loss": 0.3727, "step": 1610 }, { "epoch": 0.6690140845070423, "grad_norm": 2.5398259928326468, "learning_rate": 2.983508767579956e-06, "loss": 0.3886, "step": 1615 }, { "epoch": 0.6710853355426678, "grad_norm": 2.193753932249887, "learning_rate": 2.950472784207544e-06, "loss": 0.3688, "step": 1620 }, { "epoch": 0.6731565865782932, "grad_norm": 2.3262424473941152, "learning_rate": 2.917543995188562e-06, "loss": 0.3887, "step": 1625 }, { "epoch": 0.6752278376139188, "grad_norm": 2.4490551076339244, "learning_rate": 2.8847241227642255e-06, "loss": 0.38, "step": 1630 }, { "epoch": 0.6772990886495444, "grad_norm": 2.627771985681211, "learning_rate": 2.852014883479198e-06, "loss": 0.3834, "step": 1635 }, { "epoch": 0.6793703396851698, "grad_norm": 2.458138461877051, "learning_rate": 2.819417988091814e-06, "loss": 0.387, "step": 1640 }, { "epoch": 0.6814415907207954, "grad_norm": 2.324046202446707, "learning_rate": 2.786935141484586e-06, "loss": 0.3736, "step": 1645 }, { "epoch": 0.6835128417564209, "grad_norm": 2.319423463375523, "learning_rate": 2.754568042575061e-06, "loss": 0.3774, "step": 1650 }, { "epoch": 0.6855840927920464, "grad_norm": 2.386940183493821, "learning_rate": 2.7223183842269442e-06, "loss": 0.3656, "step": 1655 }, { "epoch": 0.6876553438276719, "grad_norm": 2.610446369166422, "learning_rate": 2.6901878531615677e-06, "loss": 0.3739, "step": 1660 }, { "epoch": 0.6897265948632975, "grad_norm": 2.405549008304295, "learning_rate": 2.658178129869672e-06, "loss": 0.3693, "step": 1665 }, { "epoch": 0.6917978458989229, "grad_norm": 2.440171669255355, "learning_rate": 2.6262908885235046e-06, "loss": 0.3848, "step": 1670 }, { "epoch": 0.6938690969345485, "grad_norm": 2.408510614925366, "learning_rate": 2.594527796889265e-06, "loss": 0.3711, "step": 1675 }, { "epoch": 0.695940347970174, "grad_norm": 2.324663610569316, "learning_rate": 2.5628905162398797e-06, "loss": 0.3794, "step": 1680 }, { "epoch": 0.6980115990057995, "grad_norm": 2.426600175758576, "learning_rate": 2.531380701268108e-06, "loss": 0.381, "step": 1685 }, { "epoch": 0.700082850041425, "grad_norm": 2.3687651420347393, "learning_rate": 2.5000000000000015e-06, "loss": 0.3724, "step": 1690 }, { "epoch": 0.7021541010770506, "grad_norm": 2.250317385085415, "learning_rate": 2.4687500537087027e-06, "loss": 0.3642, "step": 1695 }, { "epoch": 0.704225352112676, "grad_norm": 2.417150876534642, "learning_rate": 2.4376324968286154e-06, "loss": 0.3756, "step": 1700 }, { "epoch": 0.7062966031483016, "grad_norm": 2.5665361403239326, "learning_rate": 2.40664895686991e-06, "loss": 0.3681, "step": 1705 }, { "epoch": 0.7083678541839271, "grad_norm": 2.3819469973191882, "learning_rate": 2.375801054333409e-06, "loss": 0.3832, "step": 1710 }, { "epoch": 0.7104391052195526, "grad_norm": 2.4138353900787486, "learning_rate": 2.345090402625822e-06, "loss": 0.3664, "step": 1715 }, { "epoch": 0.7125103562551781, "grad_norm": 2.240263366899742, "learning_rate": 2.3145186079753685e-06, "loss": 0.3752, "step": 1720 }, { "epoch": 0.7145816072908037, "grad_norm": 2.443304293091326, "learning_rate": 2.2840872693477694e-06, "loss": 0.3698, "step": 1725 }, { "epoch": 0.7166528583264291, "grad_norm": 2.446467351621279, "learning_rate": 2.253797978362617e-06, "loss": 0.3607, "step": 1730 }, { "epoch": 0.7187241093620547, "grad_norm": 2.332781107184885, "learning_rate": 2.2236523192101264e-06, "loss": 0.3682, "step": 1735 }, { "epoch": 0.7207953603976802, "grad_norm": 2.343467120103924, "learning_rate": 2.193651868568285e-06, "loss": 0.3823, "step": 1740 }, { "epoch": 0.7228666114333057, "grad_norm": 2.286930822598269, "learning_rate": 2.16379819552038e-06, "loss": 0.3505, "step": 1745 }, { "epoch": 0.7249378624689312, "grad_norm": 2.4677518708963486, "learning_rate": 2.1340928614729445e-06, "loss": 0.3603, "step": 1750 }, { "epoch": 0.7270091135045568, "grad_norm": 2.2651030544335624, "learning_rate": 2.1045374200740863e-06, "loss": 0.3565, "step": 1755 }, { "epoch": 0.7290803645401823, "grad_norm": 2.257135100168291, "learning_rate": 2.075133417132223e-06, "loss": 0.3575, "step": 1760 }, { "epoch": 0.7311516155758078, "grad_norm": 2.443982416520075, "learning_rate": 2.045882390535248e-06, "loss": 0.355, "step": 1765 }, { "epoch": 0.7332228666114333, "grad_norm": 2.544965427000505, "learning_rate": 2.016785870170079e-06, "loss": 0.3558, "step": 1770 }, { "epoch": 0.7352941176470589, "grad_norm": 2.3886166273574703, "learning_rate": 1.987845377842656e-06, "loss": 0.3618, "step": 1775 }, { "epoch": 0.7373653686826843, "grad_norm": 2.516664427256793, "learning_rate": 1.9590624271983406e-06, "loss": 0.3593, "step": 1780 }, { "epoch": 0.7394366197183099, "grad_norm": 2.241847431735805, "learning_rate": 1.9304385236427505e-06, "loss": 0.3492, "step": 1785 }, { "epoch": 0.7415078707539354, "grad_norm": 2.525059418750423, "learning_rate": 1.9019751642630252e-06, "loss": 0.3632, "step": 1790 }, { "epoch": 0.7435791217895609, "grad_norm": 2.381378062146871, "learning_rate": 1.8736738377495196e-06, "loss": 0.3557, "step": 1795 }, { "epoch": 0.7456503728251864, "grad_norm": 2.140601268055052, "learning_rate": 1.8455360243179537e-06, "loss": 0.3505, "step": 1800 }, { "epoch": 0.747721623860812, "grad_norm": 2.4626763240941023, "learning_rate": 1.8175631956319823e-06, "loss": 0.3469, "step": 1805 }, { "epoch": 0.7497928748964374, "grad_norm": 2.367339887107846, "learning_rate": 1.7897568147262323e-06, "loss": 0.3549, "step": 1810 }, { "epoch": 0.751864125932063, "grad_norm": 2.375934298904185, "learning_rate": 1.7621183359297817e-06, "loss": 0.3547, "step": 1815 }, { "epoch": 0.7539353769676885, "grad_norm": 2.422742465121297, "learning_rate": 1.7346492047900897e-06, "loss": 0.3588, "step": 1820 }, { "epoch": 0.756006628003314, "grad_norm": 2.4412685846007314, "learning_rate": 1.7073508579973996e-06, "loss": 0.3607, "step": 1825 }, { "epoch": 0.7580778790389395, "grad_norm": 2.3302198271275443, "learning_rate": 1.6802247233095914e-06, "loss": 0.3558, "step": 1830 }, { "epoch": 0.7601491300745651, "grad_norm": 2.4252217743179147, "learning_rate": 1.6532722194775108e-06, "loss": 0.3536, "step": 1835 }, { "epoch": 0.7622203811101905, "grad_norm": 2.421023232685888, "learning_rate": 1.626494756170765e-06, "loss": 0.345, "step": 1840 }, { "epoch": 0.7642916321458161, "grad_norm": 2.4587370815071505, "learning_rate": 1.5998937339039889e-06, "loss": 0.3572, "step": 1845 }, { "epoch": 0.7663628831814416, "grad_norm": 2.600069310939224, "learning_rate": 1.5734705439636017e-06, "loss": 0.3485, "step": 1850 }, { "epoch": 0.7684341342170671, "grad_norm": 2.2951845887419955, "learning_rate": 1.5472265683350397e-06, "loss": 0.3451, "step": 1855 }, { "epoch": 0.7705053852526926, "grad_norm": 2.4341865952625996, "learning_rate": 1.5211631796304721e-06, "loss": 0.3483, "step": 1860 }, { "epoch": 0.7725766362883182, "grad_norm": 2.2916834594509843, "learning_rate": 1.495281741017016e-06, "loss": 0.3428, "step": 1865 }, { "epoch": 0.7746478873239436, "grad_norm": 2.388935089223608, "learning_rate": 1.46958360614543e-06, "loss": 0.3461, "step": 1870 }, { "epoch": 0.7767191383595692, "grad_norm": 2.47082510774388, "learning_rate": 1.4440701190793278e-06, "loss": 0.3529, "step": 1875 }, { "epoch": 0.7787903893951947, "grad_norm": 2.423140410139224, "learning_rate": 1.4187426142248723e-06, "loss": 0.3405, "step": 1880 }, { "epoch": 0.7808616404308202, "grad_norm": 2.390242453807471, "learning_rate": 1.3936024162609897e-06, "loss": 0.3533, "step": 1885 }, { "epoch": 0.7829328914664457, "grad_norm": 2.3504073769020297, "learning_rate": 1.3686508400700787e-06, "loss": 0.3524, "step": 1890 }, { "epoch": 0.7850041425020713, "grad_norm": 2.3819790982884808, "learning_rate": 1.3438891906692447e-06, "loss": 0.3364, "step": 1895 }, { "epoch": 0.7870753935376967, "grad_norm": 2.456552268130547, "learning_rate": 1.3193187631420462e-06, "loss": 0.3518, "step": 1900 }, { "epoch": 0.7891466445733223, "grad_norm": 2.316044921266805, "learning_rate": 1.2949408425707566e-06, "loss": 0.3392, "step": 1905 }, { "epoch": 0.7912178956089478, "grad_norm": 2.3687727225374493, "learning_rate": 1.2707567039691505e-06, "loss": 0.3549, "step": 1910 }, { "epoch": 0.7932891466445733, "grad_norm": 2.37413547937793, "learning_rate": 1.2467676122158224e-06, "loss": 0.3399, "step": 1915 }, { "epoch": 0.7953603976801988, "grad_norm": 2.392770322013118, "learning_rate": 1.222974821988024e-06, "loss": 0.3544, "step": 1920 }, { "epoch": 0.7974316487158244, "grad_norm": 2.3338156437204467, "learning_rate": 1.1993795776960498e-06, "loss": 0.3474, "step": 1925 }, { "epoch": 0.7995028997514498, "grad_norm": 2.4417705314717453, "learning_rate": 1.1759831134181504e-06, "loss": 0.3254, "step": 1930 }, { "epoch": 0.8015741507870754, "grad_norm": 2.392546498885362, "learning_rate": 1.1527866528359805e-06, "loss": 0.3442, "step": 1935 }, { "epoch": 0.8036454018227009, "grad_norm": 2.404079169272347, "learning_rate": 1.1297914091706086e-06, "loss": 0.3425, "step": 1940 }, { "epoch": 0.8057166528583264, "grad_norm": 2.235918195890308, "learning_rate": 1.1069985851190524e-06, "loss": 0.3403, "step": 1945 }, { "epoch": 0.8077879038939519, "grad_norm": 2.5509400903926696, "learning_rate": 1.0844093727913868e-06, "loss": 0.3445, "step": 1950 }, { "epoch": 0.8098591549295775, "grad_norm": 2.251496555771004, "learning_rate": 1.062024953648384e-06, "loss": 0.3373, "step": 1955 }, { "epoch": 0.8119304059652029, "grad_norm": 2.322434318657324, "learning_rate": 1.039846498439727e-06, "loss": 0.3412, "step": 1960 }, { "epoch": 0.8140016570008285, "grad_norm": 2.461118653046414, "learning_rate": 1.0178751671427755e-06, "loss": 0.3442, "step": 1965 }, { "epoch": 0.816072908036454, "grad_norm": 2.3596997050125377, "learning_rate": 9.961121089018933e-07, "loss": 0.3396, "step": 1970 }, { "epoch": 0.8181441590720795, "grad_norm": 2.320918191572435, "learning_rate": 9.745584619683524e-07, "loss": 0.3401, "step": 1975 }, { "epoch": 0.820215410107705, "grad_norm": 2.5354638519515476, "learning_rate": 9.532153536407923e-07, "loss": 0.3348, "step": 1980 }, { "epoch": 0.8222866611433306, "grad_norm": 2.3706820287148926, "learning_rate": 9.320839002062682e-07, "loss": 0.3423, "step": 1985 }, { "epoch": 0.824357912178956, "grad_norm": 2.604926485258956, "learning_rate": 9.111652068818621e-07, "loss": 0.3345, "step": 1990 }, { "epoch": 0.8264291632145816, "grad_norm": 2.2693641077313114, "learning_rate": 8.904603677568785e-07, "loss": 0.3261, "step": 1995 }, { "epoch": 0.8285004142502072, "grad_norm": 2.2514954275323773, "learning_rate": 8.699704657356195e-07, "loss": 0.3405, "step": 2000 }, { "epoch": 0.8305716652858326, "grad_norm": 2.469505862053808, "learning_rate": 8.496965724807516e-07, "loss": 0.326, "step": 2005 }, { "epoch": 0.8326429163214581, "grad_norm": 2.3460396844074887, "learning_rate": 8.296397483572515e-07, "loss": 0.3336, "step": 2010 }, { "epoch": 0.8347141673570837, "grad_norm": 2.4070250988641755, "learning_rate": 8.098010423769503e-07, "loss": 0.3394, "step": 2015 }, { "epoch": 0.8367854183927091, "grad_norm": 2.550190042326861, "learning_rate": 7.901814921436624e-07, "loss": 0.3341, "step": 2020 }, { "epoch": 0.8388566694283347, "grad_norm": 2.435590023140791, "learning_rate": 7.70782123798921e-07, "loss": 0.3344, "step": 2025 }, { "epoch": 0.8409279204639603, "grad_norm": 2.3760541012196525, "learning_rate": 7.516039519683105e-07, "loss": 0.3348, "step": 2030 }, { "epoch": 0.8429991714995857, "grad_norm": 2.48625212898728, "learning_rate": 7.326479797083963e-07, "loss": 0.334, "step": 2035 }, { "epoch": 0.8450704225352113, "grad_norm": 2.4594819667209413, "learning_rate": 7.139151984542636e-07, "loss": 0.3467, "step": 2040 }, { "epoch": 0.8471416735708368, "grad_norm": 2.266080954677498, "learning_rate": 6.954065879676653e-07, "loss": 0.3262, "step": 2045 }, { "epoch": 0.8492129246064622, "grad_norm": 2.4224473913562585, "learning_rate": 6.771231162857722e-07, "loss": 0.3265, "step": 2050 }, { "epoch": 0.8512841756420878, "grad_norm": 2.4134739342401765, "learning_rate": 6.590657396705525e-07, "loss": 0.3351, "step": 2055 }, { "epoch": 0.8533554266777134, "grad_norm": 2.395765196022134, "learning_rate": 6.412354025587509e-07, "loss": 0.3244, "step": 2060 }, { "epoch": 0.8554266777133389, "grad_norm": 2.422083056023904, "learning_rate": 6.236330375124921e-07, "loss": 0.3399, "step": 2065 }, { "epoch": 0.8574979287489644, "grad_norm": 2.3692888854226326, "learning_rate": 6.062595651705111e-07, "loss": 0.329, "step": 2070 }, { "epoch": 0.8595691797845899, "grad_norm": 2.366815967358674, "learning_rate": 5.891158941999959e-07, "loss": 0.3173, "step": 2075 }, { "epoch": 0.8616404308202155, "grad_norm": 2.402347297102058, "learning_rate": 5.722029212490666e-07, "loss": 0.3262, "step": 2080 }, { "epoch": 0.8637116818558409, "grad_norm": 2.394181767430833, "learning_rate": 5.555215308998779e-07, "loss": 0.3257, "step": 2085 }, { "epoch": 0.8657829328914665, "grad_norm": 2.4051959667125367, "learning_rate": 5.390725956223531e-07, "loss": 0.3294, "step": 2090 }, { "epoch": 0.867854183927092, "grad_norm": 2.5576493713299406, "learning_rate": 5.22856975728554e-07, "loss": 0.325, "step": 2095 }, { "epoch": 0.8699254349627175, "grad_norm": 2.378552611619228, "learning_rate": 5.068755193276798e-07, "loss": 0.3214, "step": 2100 }, { "epoch": 0.871996685998343, "grad_norm": 2.443557055438852, "learning_rate": 4.911290622817161e-07, "loss": 0.3312, "step": 2105 }, { "epoch": 0.8740679370339686, "grad_norm": 2.4627290970920277, "learning_rate": 4.756184281617121e-07, "loss": 0.3245, "step": 2110 }, { "epoch": 0.876139188069594, "grad_norm": 2.195083566590239, "learning_rate": 4.6034442820471037e-07, "loss": 0.3219, "step": 2115 }, { "epoch": 0.8782104391052196, "grad_norm": 2.4229393019650214, "learning_rate": 4.4530786127131575e-07, "loss": 0.3226, "step": 2120 }, { "epoch": 0.8802816901408451, "grad_norm": 2.4467401625565466, "learning_rate": 4.305095138039106e-07, "loss": 0.3194, "step": 2125 }, { "epoch": 0.8823529411764706, "grad_norm": 2.297282546881658, "learning_rate": 4.159501597855287e-07, "loss": 0.3225, "step": 2130 }, { "epoch": 0.8844241922120961, "grad_norm": 2.4986520919277546, "learning_rate": 4.0163056069936757e-07, "loss": 0.3249, "step": 2135 }, { "epoch": 0.8864954432477217, "grad_norm": 2.4410175569101686, "learning_rate": 3.8755146548896784e-07, "loss": 0.3224, "step": 2140 }, { "epoch": 0.8885666942833471, "grad_norm": 2.3646965179891115, "learning_rate": 3.737136105190337e-07, "loss": 0.3188, "step": 2145 }, { "epoch": 0.8906379453189727, "grad_norm": 2.2852035693008155, "learning_rate": 3.6011771953693044e-07, "loss": 0.3192, "step": 2150 }, { "epoch": 0.8927091963545982, "grad_norm": 2.461714443250045, "learning_rate": 3.4676450363481937e-07, "loss": 0.3251, "step": 2155 }, { "epoch": 0.8947804473902237, "grad_norm": 2.4332621374559125, "learning_rate": 3.336546612124758e-07, "loss": 0.3332, "step": 2160 }, { "epoch": 0.8968516984258492, "grad_norm": 2.4270584250944753, "learning_rate": 3.20788877940757e-07, "loss": 0.3249, "step": 2165 }, { "epoch": 0.8989229494614748, "grad_norm": 2.368498504312502, "learning_rate": 3.081678267257404e-07, "loss": 0.3202, "step": 2170 }, { "epoch": 0.9009942004971002, "grad_norm": 2.557109469173219, "learning_rate": 2.9579216767352815e-07, "loss": 0.3144, "step": 2175 }, { "epoch": 0.9030654515327258, "grad_norm": 2.426732710855286, "learning_rate": 2.836625480557265e-07, "loss": 0.329, "step": 2180 }, { "epoch": 0.9051367025683513, "grad_norm": 2.283265212808633, "learning_rate": 2.7177960227558863e-07, "loss": 0.325, "step": 2185 }, { "epoch": 0.9072079536039768, "grad_norm": 2.4670574251327793, "learning_rate": 2.601439518348331e-07, "loss": 0.3156, "step": 2190 }, { "epoch": 0.9092792046396023, "grad_norm": 2.5891866035647575, "learning_rate": 2.487562053011422e-07, "loss": 0.3234, "step": 2195 }, { "epoch": 0.9113504556752279, "grad_norm": 2.541747164750298, "learning_rate": 2.376169582763288e-07, "loss": 0.3303, "step": 2200 }, { "epoch": 0.9134217067108533, "grad_norm": 2.362000199932235, "learning_rate": 2.2672679336518789e-07, "loss": 0.3186, "step": 2205 }, { "epoch": 0.9154929577464789, "grad_norm": 2.3439018450732743, "learning_rate": 2.1608628014502364e-07, "loss": 0.3255, "step": 2210 }, { "epoch": 0.9175642087821044, "grad_norm": 2.368576604401793, "learning_rate": 2.0569597513586004e-07, "loss": 0.3195, "step": 2215 }, { "epoch": 0.9196354598177299, "grad_norm": 2.4987692047008125, "learning_rate": 1.955564217713335e-07, "loss": 0.3258, "step": 2220 }, { "epoch": 0.9217067108533554, "grad_norm": 2.392386426466528, "learning_rate": 1.8566815037026897e-07, "loss": 0.3171, "step": 2225 }, { "epoch": 0.923777961888981, "grad_norm": 2.4830538565794975, "learning_rate": 1.7603167810894662e-07, "loss": 0.3251, "step": 2230 }, { "epoch": 0.9258492129246064, "grad_norm": 2.510592721078319, "learning_rate": 1.6664750899404892e-07, "loss": 0.3227, "step": 2235 }, { "epoch": 0.927920463960232, "grad_norm": 2.4157359437659034, "learning_rate": 1.5751613383630128e-07, "loss": 0.3286, "step": 2240 }, { "epoch": 0.9299917149958575, "grad_norm": 2.4107277513211507, "learning_rate": 1.4863803022480362e-07, "loss": 0.3247, "step": 2245 }, { "epoch": 0.932062966031483, "grad_norm": 2.5267067785032373, "learning_rate": 1.4001366250204762e-07, "loss": 0.3233, "step": 2250 }, { "epoch": 0.9341342170671085, "grad_norm": 2.528363627234817, "learning_rate": 1.3164348173963392e-07, "loss": 0.3309, "step": 2255 }, { "epoch": 0.9362054681027341, "grad_norm": 2.4201731535567514, "learning_rate": 1.235279257146804e-07, "loss": 0.3201, "step": 2260 }, { "epoch": 0.9382767191383595, "grad_norm": 2.5379780451413962, "learning_rate": 1.1566741888692168e-07, "loss": 0.3275, "step": 2265 }, { "epoch": 0.9403479701739851, "grad_norm": 2.3506867514458745, "learning_rate": 1.080623723765134e-07, "loss": 0.3237, "step": 2270 }, { "epoch": 0.9424192212096106, "grad_norm": 2.395967973806624, "learning_rate": 1.0071318394252849e-07, "loss": 0.3186, "step": 2275 }, { "epoch": 0.9444904722452361, "grad_norm": 2.476211995439103, "learning_rate": 9.362023796215036e-08, "loss": 0.3139, "step": 2280 }, { "epoch": 0.9465617232808616, "grad_norm": 2.5527910235724516, "learning_rate": 8.678390541057512e-08, "loss": 0.3229, "step": 2285 }, { "epoch": 0.9486329743164872, "grad_norm": 2.4883434947847443, "learning_rate": 8.020454384160437e-08, "loss": 0.3144, "step": 2290 }, { "epoch": 0.9507042253521126, "grad_norm": 2.39340887379046, "learning_rate": 7.388249736894615e-08, "loss": 0.3178, "step": 2295 }, { "epoch": 0.9527754763877382, "grad_norm": 2.715467150061724, "learning_rate": 6.78180966482156e-08, "loss": 0.3208, "step": 2300 }, { "epoch": 0.9548467274233637, "grad_norm": 2.460880017615995, "learning_rate": 6.201165885964311e-08, "loss": 0.3206, "step": 2305 }, { "epoch": 0.9569179784589892, "grad_norm": 2.3958409152518243, "learning_rate": 5.646348769148491e-08, "loss": 0.3139, "step": 2310 }, { "epoch": 0.9589892294946147, "grad_norm": 2.4325940811763576, "learning_rate": 5.117387332413737e-08, "loss": 0.3129, "step": 2315 }, { "epoch": 0.9610604805302403, "grad_norm": 2.3788015147228876, "learning_rate": 4.6143092414961396e-08, "loss": 0.3132, "step": 2320 }, { "epoch": 0.9631317315658657, "grad_norm": 2.3582504994533724, "learning_rate": 4.1371408083815126e-08, "loss": 0.3213, "step": 2325 }, { "epoch": 0.9652029826014913, "grad_norm": 2.4148423702111486, "learning_rate": 3.685906989928656e-08, "loss": 0.3158, "step": 2330 }, { "epoch": 0.9672742336371168, "grad_norm": 2.367783801927864, "learning_rate": 3.2606313865646276e-08, "loss": 0.3144, "step": 2335 }, { "epoch": 0.9693454846727423, "grad_norm": 2.5082498535965336, "learning_rate": 2.861336241050061e-08, "loss": 0.3172, "step": 2340 }, { "epoch": 0.9714167357083678, "grad_norm": 2.456984761177935, "learning_rate": 2.488042437315985e-08, "loss": 0.3255, "step": 2345 }, { "epoch": 0.9734879867439934, "grad_norm": 2.643990284496229, "learning_rate": 2.1407694993714755e-08, "loss": 0.3251, "step": 2350 }, { "epoch": 0.9755592377796188, "grad_norm": 2.436574599754285, "learning_rate": 1.8195355902824174e-08, "loss": 0.3163, "step": 2355 }, { "epoch": 0.9776304888152444, "grad_norm": 2.416424486326842, "learning_rate": 1.5243575112218744e-08, "loss": 0.3277, "step": 2360 }, { "epoch": 0.97970173985087, "grad_norm": 2.455184760551646, "learning_rate": 1.2552507005909042e-08, "loss": 0.3238, "step": 2365 }, { "epoch": 0.9817729908864954, "grad_norm": 2.394910295886536, "learning_rate": 1.0122292332114814e-08, "loss": 0.3173, "step": 2370 }, { "epoch": 0.9838442419221209, "grad_norm": 2.4595417259654164, "learning_rate": 7.953058195900864e-09, "loss": 0.3113, "step": 2375 }, { "epoch": 0.9859154929577465, "grad_norm": 2.3388096935609903, "learning_rate": 6.044918052531268e-09, "loss": 0.3167, "step": 2380 }, { "epoch": 0.987986743993372, "grad_norm": 2.5217563709354303, "learning_rate": 4.397971701533554e-09, "loss": 0.3143, "step": 2385 }, { "epoch": 0.9900579950289975, "grad_norm": 2.2511718651674486, "learning_rate": 3.0123052814812203e-09, "loss": 0.3237, "step": 2390 }, { "epoch": 0.992129246064623, "grad_norm": 2.404379084709477, "learning_rate": 1.887991265486222e-09, "loss": 0.3132, "step": 2395 }, { "epoch": 0.9942004971002486, "grad_norm": 2.4870530209979678, "learning_rate": 1.025088457409229e-09, "loss": 0.3167, "step": 2400 }, { "epoch": 0.996271748135874, "grad_norm": 2.473845135682151, "learning_rate": 4.2364198878597216e-10, "loss": 0.3329, "step": 2405 }, { "epoch": 0.9983429991714996, "grad_norm": 2.4174266492789096, "learning_rate": 8.368331646302353e-11, "loss": 0.3225, "step": 2410 }, { "epoch": 1.0, "eval_runtime": 3.4017, "eval_samples_per_second": 2.94, "eval_steps_per_second": 0.882, "step": 2414 }, { "epoch": 1.0, "step": 2414, "total_flos": 252721244405760.0, "train_loss": 0.5160956633614427, "train_runtime": 21392.9291, "train_samples_per_second": 1.805, "train_steps_per_second": 0.113 } ], "logging_steps": 5, "max_steps": 2414, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 100, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 252721244405760.0, "train_batch_size": 4, "trial_name": null, "trial_params": null }