{ "best_metric": null, "best_model_checkpoint": null, "epoch": 1.0, "eval_steps": 500, "global_step": 1549, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.0006455777921239509, "grad_norm": 16.205452234411737, "learning_rate": 1.2903225806451614e-07, "loss": 1.8573, "step": 1 }, { "epoch": 0.0032278889606197547, "grad_norm": 14.995431561267777, "learning_rate": 6.451612903225807e-07, "loss": 1.8993, "step": 5 }, { "epoch": 0.006455777921239509, "grad_norm": 10.81513181649353, "learning_rate": 1.2903225806451614e-06, "loss": 1.8257, "step": 10 }, { "epoch": 0.009683666881859263, "grad_norm": 10.205458746998783, "learning_rate": 1.935483870967742e-06, "loss": 1.7098, "step": 15 }, { "epoch": 0.012911555842479019, "grad_norm": 9.227538444236034, "learning_rate": 2.580645161290323e-06, "loss": 1.63, "step": 20 }, { "epoch": 0.016139444803098774, "grad_norm": 8.636180793854093, "learning_rate": 3.225806451612903e-06, "loss": 1.6054, "step": 25 }, { "epoch": 0.019367333763718526, "grad_norm": 7.836281445290913, "learning_rate": 3.870967741935484e-06, "loss": 1.554, "step": 30 }, { "epoch": 0.022595222724338282, "grad_norm": 7.718242026474227, "learning_rate": 4.516129032258065e-06, "loss": 1.5009, "step": 35 }, { "epoch": 0.025823111684958037, "grad_norm": 7.637693613009242, "learning_rate": 5.161290322580646e-06, "loss": 1.5568, "step": 40 }, { "epoch": 0.029051000645577793, "grad_norm": 8.037677797603621, "learning_rate": 5.806451612903226e-06, "loss": 1.509, "step": 45 }, { "epoch": 0.03227888960619755, "grad_norm": 8.050943021309022, "learning_rate": 6.451612903225806e-06, "loss": 1.5483, "step": 50 }, { "epoch": 0.035506778566817304, "grad_norm": 7.8773672608999075, "learning_rate": 7.096774193548388e-06, "loss": 1.5449, "step": 55 }, { "epoch": 0.03873466752743705, "grad_norm": 7.8185673315827104, "learning_rate": 7.741935483870968e-06, "loss": 1.5615, "step": 60 }, { "epoch": 0.04196255648805681, "grad_norm": 7.288430315557615, "learning_rate": 8.387096774193549e-06, "loss": 1.5535, "step": 65 }, { "epoch": 0.045190445448676564, "grad_norm": 7.4125851014724224, "learning_rate": 9.03225806451613e-06, "loss": 1.56, "step": 70 }, { "epoch": 0.04841833440929632, "grad_norm": 7.384090809487316, "learning_rate": 9.67741935483871e-06, "loss": 1.5751, "step": 75 }, { "epoch": 0.051646223369916075, "grad_norm": 7.186612923240028, "learning_rate": 1.0322580645161291e-05, "loss": 1.5353, "step": 80 }, { "epoch": 0.05487411233053583, "grad_norm": 7.54719691241193, "learning_rate": 1.096774193548387e-05, "loss": 1.536, "step": 85 }, { "epoch": 0.058102001291155586, "grad_norm": 6.841634960153724, "learning_rate": 1.1612903225806453e-05, "loss": 1.5638, "step": 90 }, { "epoch": 0.06132989025177534, "grad_norm": 6.884784528712181, "learning_rate": 1.2258064516129034e-05, "loss": 1.5449, "step": 95 }, { "epoch": 0.0645577792123951, "grad_norm": 7.5067298597661525, "learning_rate": 1.2903225806451613e-05, "loss": 1.595, "step": 100 }, { "epoch": 0.06778566817301485, "grad_norm": 7.371893992584374, "learning_rate": 1.3548387096774194e-05, "loss": 1.6045, "step": 105 }, { "epoch": 0.07101355713363461, "grad_norm": 7.220506075154664, "learning_rate": 1.4193548387096776e-05, "loss": 1.5886, "step": 110 }, { "epoch": 0.07424144609425436, "grad_norm": 7.354995573259938, "learning_rate": 1.4838709677419357e-05, "loss": 1.6884, "step": 115 }, { "epoch": 0.0774693350548741, "grad_norm": 7.431127341541042, "learning_rate": 1.5483870967741936e-05, "loss": 1.5783, "step": 120 }, { "epoch": 0.08069722401549387, "grad_norm": 7.617961920752755, "learning_rate": 1.6129032258064517e-05, "loss": 1.5722, "step": 125 }, { "epoch": 0.08392511297611362, "grad_norm": 7.2187575554924495, "learning_rate": 1.6774193548387098e-05, "loss": 1.6404, "step": 130 }, { "epoch": 0.08715300193673338, "grad_norm": 8.229669273322479, "learning_rate": 1.741935483870968e-05, "loss": 1.6631, "step": 135 }, { "epoch": 0.09038089089735313, "grad_norm": 7.475319901543287, "learning_rate": 1.806451612903226e-05, "loss": 1.6931, "step": 140 }, { "epoch": 0.09360877985797289, "grad_norm": 7.238180827010263, "learning_rate": 1.870967741935484e-05, "loss": 1.6595, "step": 145 }, { "epoch": 0.09683666881859264, "grad_norm": 7.477385100319548, "learning_rate": 1.935483870967742e-05, "loss": 1.7362, "step": 150 }, { "epoch": 0.1000645577792124, "grad_norm": 6.8926903445205125, "learning_rate": 2e-05, "loss": 1.7156, "step": 155 }, { "epoch": 0.10329244673983215, "grad_norm": 7.118422267427338, "learning_rate": 1.9999365137586883e-05, "loss": 1.7117, "step": 160 }, { "epoch": 0.1065203357004519, "grad_norm": 7.359581007823435, "learning_rate": 1.9997460630957587e-05, "loss": 1.6915, "step": 165 }, { "epoch": 0.10974822466107166, "grad_norm": 7.06877768743029, "learning_rate": 1.9994286721932043e-05, "loss": 1.7439, "step": 170 }, { "epoch": 0.11297611362169141, "grad_norm": 7.218247396787645, "learning_rate": 1.9989843813509366e-05, "loss": 1.7124, "step": 175 }, { "epoch": 0.11620400258231117, "grad_norm": 16.159481189289234, "learning_rate": 1.998413246981666e-05, "loss": 1.7058, "step": 180 }, { "epoch": 0.11943189154293092, "grad_norm": 46.181125374261654, "learning_rate": 1.9977153416037424e-05, "loss": 1.7839, "step": 185 }, { "epoch": 0.12265978050355068, "grad_norm": 41.37204715355036, "learning_rate": 1.9968907538319433e-05, "loss": 1.917, "step": 190 }, { "epoch": 0.12588766946417043, "grad_norm": 44.987565321564276, "learning_rate": 1.9959395883662257e-05, "loss": 1.7653, "step": 195 }, { "epoch": 0.1291155584247902, "grad_norm": 7.194696914719683, "learning_rate": 1.99486196597843e-05, "loss": 1.7191, "step": 200 }, { "epoch": 0.13234344738540993, "grad_norm": 7.430734307814263, "learning_rate": 1.9936580234969464e-05, "loss": 1.7557, "step": 205 }, { "epoch": 0.1355713363460297, "grad_norm": 7.334778943984345, "learning_rate": 1.9923279137893405e-05, "loss": 1.7207, "step": 210 }, { "epoch": 0.13879922530664945, "grad_norm": 6.935862923382574, "learning_rate": 1.990871805742944e-05, "loss": 1.6912, "step": 215 }, { "epoch": 0.14202711426726922, "grad_norm": 6.43836756283986, "learning_rate": 1.9892898842434106e-05, "loss": 1.7097, "step": 220 }, { "epoch": 0.14525500322788895, "grad_norm": 6.790579150198959, "learning_rate": 1.98758235015124e-05, "loss": 1.6824, "step": 225 }, { "epoch": 0.1484828921885087, "grad_norm": 7.563145193822757, "learning_rate": 1.9857494202762758e-05, "loss": 1.7204, "step": 230 }, { "epoch": 0.15171078114912848, "grad_norm": 7.21569143328697, "learning_rate": 1.983791327350174e-05, "loss": 1.724, "step": 235 }, { "epoch": 0.1549386701097482, "grad_norm": 7.396066704475681, "learning_rate": 1.9817083199968552e-05, "loss": 1.74, "step": 240 }, { "epoch": 0.15816655907036797, "grad_norm": 6.409702062362999, "learning_rate": 1.979500662700934e-05, "loss": 1.733, "step": 245 }, { "epoch": 0.16139444803098774, "grad_norm": 7.33040263293043, "learning_rate": 1.977168635774138e-05, "loss": 1.7073, "step": 250 }, { "epoch": 0.1646223369916075, "grad_norm": 6.627407014857698, "learning_rate": 1.974712535319716e-05, "loss": 1.7714, "step": 255 }, { "epoch": 0.16785022595222723, "grad_norm": 9.128235977291943, "learning_rate": 1.97213267319484e-05, "loss": 1.7289, "step": 260 }, { "epoch": 0.171078114912847, "grad_norm": 10.132426302191169, "learning_rate": 1.969429376971009e-05, "loss": 1.7112, "step": 265 }, { "epoch": 0.17430600387346676, "grad_norm": 7.187125458351554, "learning_rate": 1.9666029898924558e-05, "loss": 1.7521, "step": 270 }, { "epoch": 0.17753389283408652, "grad_norm": 6.559644342179301, "learning_rate": 1.9636538708325642e-05, "loss": 1.6834, "step": 275 }, { "epoch": 0.18076178179470626, "grad_norm": 6.619411966067338, "learning_rate": 1.9605823942483034e-05, "loss": 1.7152, "step": 280 }, { "epoch": 0.18398967075532602, "grad_norm": 7.081708830235818, "learning_rate": 1.9573889501326803e-05, "loss": 1.7742, "step": 285 }, { "epoch": 0.18721755971594578, "grad_norm": 6.868160684535405, "learning_rate": 1.9540739439652222e-05, "loss": 1.6998, "step": 290 }, { "epoch": 0.19044544867656552, "grad_norm": 6.1971536722827185, "learning_rate": 1.9506377966604923e-05, "loss": 1.7291, "step": 295 }, { "epoch": 0.19367333763718528, "grad_norm": 6.757970184040331, "learning_rate": 1.9470809445146447e-05, "loss": 1.7305, "step": 300 }, { "epoch": 0.19690122659780504, "grad_norm": 7.044564037259735, "learning_rate": 1.9434038391500266e-05, "loss": 1.7215, "step": 305 }, { "epoch": 0.2001291155584248, "grad_norm": 7.414383701728508, "learning_rate": 1.9396069474578348e-05, "loss": 1.6677, "step": 310 }, { "epoch": 0.20335700451904454, "grad_norm": 6.557964172050999, "learning_rate": 1.935690751538834e-05, "loss": 1.7939, "step": 315 }, { "epoch": 0.2065848934796643, "grad_norm": 6.33082377097435, "learning_rate": 1.9316557486421423e-05, "loss": 1.7408, "step": 320 }, { "epoch": 0.20981278244028406, "grad_norm": 6.73298193200644, "learning_rate": 1.927502451102095e-05, "loss": 1.6857, "step": 325 }, { "epoch": 0.2130406714009038, "grad_norm": 7.006395729787068, "learning_rate": 1.9232313862731915e-05, "loss": 1.6956, "step": 330 }, { "epoch": 0.21626856036152356, "grad_norm": 6.4834753162658805, "learning_rate": 1.918843096463137e-05, "loss": 1.6794, "step": 335 }, { "epoch": 0.21949644932214332, "grad_norm": 6.987943551728841, "learning_rate": 1.914338138863983e-05, "loss": 1.6969, "step": 340 }, { "epoch": 0.22272433828276308, "grad_norm": 6.192316163330726, "learning_rate": 1.9097170854813797e-05, "loss": 1.7381, "step": 345 }, { "epoch": 0.22595222724338282, "grad_norm": 6.4383979807985465, "learning_rate": 1.904980523061948e-05, "loss": 1.7072, "step": 350 }, { "epoch": 0.22918011620400258, "grad_norm": 6.443512513966274, "learning_rate": 1.9001290530187768e-05, "loss": 1.7401, "step": 355 }, { "epoch": 0.23240800516462234, "grad_norm": 5.964542231058296, "learning_rate": 1.8951632913550625e-05, "loss": 1.7035, "step": 360 }, { "epoch": 0.23563589412524208, "grad_norm": 7.1697046567958935, "learning_rate": 1.8900838685858913e-05, "loss": 1.7233, "step": 365 }, { "epoch": 0.23886378308586184, "grad_norm": 6.169546810862376, "learning_rate": 1.884891429658182e-05, "loss": 1.7021, "step": 370 }, { "epoch": 0.2420916720464816, "grad_norm": 5.973896098846117, "learning_rate": 1.8795866338687968e-05, "loss": 1.7463, "step": 375 }, { "epoch": 0.24531956100710137, "grad_norm": 6.896426991389762, "learning_rate": 1.8741701547808272e-05, "loss": 1.6499, "step": 380 }, { "epoch": 0.2485474499677211, "grad_norm": 6.952076945810176, "learning_rate": 1.868642680138069e-05, "loss": 1.767, "step": 385 }, { "epoch": 0.25177533892834086, "grad_norm": 6.18518307255409, "learning_rate": 1.863004911777701e-05, "loss": 1.7078, "step": 390 }, { "epoch": 0.2550032278889606, "grad_norm": 6.632738286453584, "learning_rate": 1.8572575655411683e-05, "loss": 1.6845, "step": 395 }, { "epoch": 0.2582311168495804, "grad_norm": 5.978535399494513, "learning_rate": 1.851401371183291e-05, "loss": 1.707, "step": 400 }, { "epoch": 0.26145900581020015, "grad_norm": 6.13506677347622, "learning_rate": 1.8454370722796052e-05, "loss": 1.6807, "step": 405 }, { "epoch": 0.26468689477081986, "grad_norm": 6.556694455290259, "learning_rate": 1.8393654261319504e-05, "loss": 1.7744, "step": 410 }, { "epoch": 0.2679147837314396, "grad_norm": 6.113175455632477, "learning_rate": 1.8331872036723103e-05, "loss": 1.7065, "step": 415 }, { "epoch": 0.2711426726920594, "grad_norm": 6.482825433419425, "learning_rate": 1.8269031893649306e-05, "loss": 1.6784, "step": 420 }, { "epoch": 0.27437056165267915, "grad_norm": 6.329309102633813, "learning_rate": 1.8205141811067073e-05, "loss": 1.683, "step": 425 }, { "epoch": 0.2775984506132989, "grad_norm": 6.208972725984303, "learning_rate": 1.814020990125881e-05, "loss": 1.6445, "step": 430 }, { "epoch": 0.28082633957391867, "grad_norm": 5.818695993515501, "learning_rate": 1.807424440879031e-05, "loss": 1.7113, "step": 435 }, { "epoch": 0.28405422853453843, "grad_norm": 6.38696318289984, "learning_rate": 1.8007253709463915e-05, "loss": 1.6578, "step": 440 }, { "epoch": 0.28728211749515814, "grad_norm": 6.315382160526404, "learning_rate": 1.7939246309255028e-05, "loss": 1.6857, "step": 445 }, { "epoch": 0.2905100064557779, "grad_norm": 6.233507637482026, "learning_rate": 1.78702308432321e-05, "loss": 1.7347, "step": 450 }, { "epoch": 0.29373789541639767, "grad_norm": 6.294349426994083, "learning_rate": 1.7800216074460183e-05, "loss": 1.7043, "step": 455 }, { "epoch": 0.2969657843770174, "grad_norm": 6.343968862796106, "learning_rate": 1.772921089288829e-05, "loss": 1.7059, "step": 460 }, { "epoch": 0.3001936733376372, "grad_norm": 6.673007692244266, "learning_rate": 1.7657224314220604e-05, "loss": 1.7047, "step": 465 }, { "epoch": 0.30342156229825695, "grad_norm": 6.729119057620871, "learning_rate": 1.7584265478771737e-05, "loss": 1.6781, "step": 470 }, { "epoch": 0.3066494512588767, "grad_norm": 6.495304769382025, "learning_rate": 1.7510343650306155e-05, "loss": 1.708, "step": 475 }, { "epoch": 0.3098773402194964, "grad_norm": 6.271850518966485, "learning_rate": 1.7435468214861933e-05, "loss": 1.6428, "step": 480 }, { "epoch": 0.3131052291801162, "grad_norm": 6.423477074617556, "learning_rate": 1.7359648679559006e-05, "loss": 1.6194, "step": 485 }, { "epoch": 0.31633311814073595, "grad_norm": 6.221443392917989, "learning_rate": 1.7282894671391996e-05, "loss": 1.7025, "step": 490 }, { "epoch": 0.3195610071013557, "grad_norm": 5.846396784880404, "learning_rate": 1.720521593600787e-05, "loss": 1.7269, "step": 495 }, { "epoch": 0.32278889606197547, "grad_norm": 6.477559026734868, "learning_rate": 1.7126622336468514e-05, "loss": 1.6395, "step": 500 }, { "epoch": 0.32601678502259523, "grad_norm": 6.055139296691825, "learning_rate": 1.7047123851998374e-05, "loss": 1.6782, "step": 505 }, { "epoch": 0.329244673983215, "grad_norm": 6.118162992939965, "learning_rate": 1.6966730576717388e-05, "loss": 1.682, "step": 510 }, { "epoch": 0.33247256294383476, "grad_norm": 5.5534801726338525, "learning_rate": 1.6885452718359306e-05, "loss": 1.6267, "step": 515 }, { "epoch": 0.33570045190445447, "grad_norm": 5.43602711879506, "learning_rate": 1.6803300596975586e-05, "loss": 1.6452, "step": 520 }, { "epoch": 0.33892834086507423, "grad_norm": 7.206960139551292, "learning_rate": 1.6720284643625035e-05, "loss": 1.6583, "step": 525 }, { "epoch": 0.342156229825694, "grad_norm": 6.427854787428326, "learning_rate": 1.6636415399049347e-05, "loss": 1.6091, "step": 530 }, { "epoch": 0.34538411878631375, "grad_norm": 5.816051751586562, "learning_rate": 1.6551703512334716e-05, "loss": 1.6913, "step": 535 }, { "epoch": 0.3486120077469335, "grad_norm": 5.927556526774363, "learning_rate": 1.6466159739559712e-05, "loss": 1.6738, "step": 540 }, { "epoch": 0.3518398967075533, "grad_norm": 6.455088888441903, "learning_rate": 1.6379794942429534e-05, "loss": 1.648, "step": 545 }, { "epoch": 0.35506778566817304, "grad_norm": 6.240988706855586, "learning_rate": 1.629262008689689e-05, "loss": 1.6927, "step": 550 }, { "epoch": 0.35829567462879275, "grad_norm": 5.86555967170564, "learning_rate": 1.62046462417696e-05, "loss": 1.6388, "step": 555 }, { "epoch": 0.3615235635894125, "grad_norm": 5.66373254985077, "learning_rate": 1.611588457730519e-05, "loss": 1.6947, "step": 560 }, { "epoch": 0.3647514525500323, "grad_norm": 5.979046700601131, "learning_rate": 1.6026346363792565e-05, "loss": 1.6829, "step": 565 }, { "epoch": 0.36797934151065204, "grad_norm": 5.727328551303314, "learning_rate": 1.5936042970120976e-05, "loss": 1.6646, "step": 570 }, { "epoch": 0.3712072304712718, "grad_norm": 6.089199758516902, "learning_rate": 1.5844985862336516e-05, "loss": 1.6665, "step": 575 }, { "epoch": 0.37443511943189156, "grad_norm": 5.587005635034525, "learning_rate": 1.5753186602186207e-05, "loss": 1.6417, "step": 580 }, { "epoch": 0.3776630083925113, "grad_norm": 6.050996843101115, "learning_rate": 1.5660656845650027e-05, "loss": 1.5796, "step": 585 }, { "epoch": 0.38089089735313103, "grad_norm": 6.080615404268494, "learning_rate": 1.556740834146087e-05, "loss": 1.6976, "step": 590 }, { "epoch": 0.3841187863137508, "grad_norm": 6.474714539476243, "learning_rate": 1.547345292961282e-05, "loss": 1.6356, "step": 595 }, { "epoch": 0.38734667527437056, "grad_norm": 5.877661742364028, "learning_rate": 1.5378802539857775e-05, "loss": 1.6992, "step": 600 }, { "epoch": 0.3905745642349903, "grad_norm": 5.866696710467355, "learning_rate": 1.52834691901907e-05, "loss": 1.6606, "step": 605 }, { "epoch": 0.3938024531956101, "grad_norm": 6.398661395189826, "learning_rate": 1.5187464985323681e-05, "loss": 1.7004, "step": 610 }, { "epoch": 0.39703034215622984, "grad_norm": 6.109162698783035, "learning_rate": 1.5090802115148956e-05, "loss": 1.664, "step": 615 }, { "epoch": 0.4002582311168496, "grad_norm": 5.731699946494037, "learning_rate": 1.4993492853191118e-05, "loss": 1.6559, "step": 620 }, { "epoch": 0.4034861200774693, "grad_norm": 5.4571384796165185, "learning_rate": 1.4895549555048751e-05, "loss": 1.6327, "step": 625 }, { "epoch": 0.4067140090380891, "grad_norm": 5.872513791622213, "learning_rate": 1.4796984656825572e-05, "loss": 1.625, "step": 630 }, { "epoch": 0.40994189799870884, "grad_norm": 5.288501071612407, "learning_rate": 1.4697810673551408e-05, "loss": 1.6659, "step": 635 }, { "epoch": 0.4131697869593286, "grad_norm": 6.468751146768027, "learning_rate": 1.4598040197593128e-05, "loss": 1.7126, "step": 640 }, { "epoch": 0.41639767591994836, "grad_norm": 5.698799707780423, "learning_rate": 1.4497685897055758e-05, "loss": 1.5823, "step": 645 }, { "epoch": 0.4196255648805681, "grad_norm": 5.654573938892979, "learning_rate": 1.4396760514173976e-05, "loss": 1.6498, "step": 650 }, { "epoch": 0.4228534538411879, "grad_norm": 6.976746797511936, "learning_rate": 1.4295276863694205e-05, "loss": 1.6113, "step": 655 }, { "epoch": 0.4260813428018076, "grad_norm": 5.235970407365906, "learning_rate": 1.4193247831247499e-05, "loss": 1.7006, "step": 660 }, { "epoch": 0.42930923176242736, "grad_norm": 6.140392016522079, "learning_rate": 1.4090686371713403e-05, "loss": 1.6836, "step": 665 }, { "epoch": 0.4325371207230471, "grad_norm": 5.45721311029038, "learning_rate": 1.3987605507575053e-05, "loss": 1.6306, "step": 670 }, { "epoch": 0.4357650096836669, "grad_norm": 6.83263868068613, "learning_rate": 1.3884018327265683e-05, "loss": 1.7172, "step": 675 }, { "epoch": 0.43899289864428664, "grad_norm": 5.843200304850912, "learning_rate": 1.3779937983506746e-05, "loss": 1.6762, "step": 680 }, { "epoch": 0.4422207876049064, "grad_norm": 5.57641828737366, "learning_rate": 1.3675377691637879e-05, "loss": 1.6778, "step": 685 }, { "epoch": 0.44544867656552617, "grad_norm": 5.738260096617323, "learning_rate": 1.3570350727938925e-05, "loss": 1.6378, "step": 690 }, { "epoch": 0.4486765655261459, "grad_norm": 6.357451662380971, "learning_rate": 1.3464870427944208e-05, "loss": 1.6041, "step": 695 }, { "epoch": 0.45190445448676564, "grad_norm": 5.484551406388904, "learning_rate": 1.3358950184749284e-05, "loss": 1.6612, "step": 700 }, { "epoch": 0.4551323434473854, "grad_norm": 5.827167388471347, "learning_rate": 1.3252603447310396e-05, "loss": 1.5759, "step": 705 }, { "epoch": 0.45836023240800516, "grad_norm": 5.980523013123908, "learning_rate": 1.3145843718736809e-05, "loss": 1.6716, "step": 710 }, { "epoch": 0.4615881213686249, "grad_norm": 6.134764370156555, "learning_rate": 1.3038684554576308e-05, "loss": 1.6406, "step": 715 }, { "epoch": 0.4648160103292447, "grad_norm": 5.487517622123662, "learning_rate": 1.2931139561094007e-05, "loss": 1.5756, "step": 720 }, { "epoch": 0.46804389928986445, "grad_norm": 5.4981090259389696, "learning_rate": 1.2823222393544717e-05, "loss": 1.5797, "step": 725 }, { "epoch": 0.47127178825048416, "grad_norm": 5.219388647345398, "learning_rate": 1.2714946754439117e-05, "loss": 1.5944, "step": 730 }, { "epoch": 0.4744996772111039, "grad_norm": 5.824820667094204, "learning_rate": 1.2606326391803915e-05, "loss": 1.58, "step": 735 }, { "epoch": 0.4777275661717237, "grad_norm": 5.786554762407817, "learning_rate": 1.249737509743622e-05, "loss": 1.6459, "step": 740 }, { "epoch": 0.48095545513234345, "grad_norm": 5.8901639628553095, "learning_rate": 1.2388106705152361e-05, "loss": 1.5922, "step": 745 }, { "epoch": 0.4841833440929632, "grad_norm": 5.320173777546997, "learning_rate": 1.2278535089031377e-05, "loss": 1.6169, "step": 750 }, { "epoch": 0.48741123305358297, "grad_norm": 5.377921836454134, "learning_rate": 1.2168674161653395e-05, "loss": 1.5759, "step": 755 }, { "epoch": 0.49063912201420273, "grad_norm": 5.5810578215639435, "learning_rate": 1.2058537872333104e-05, "loss": 1.5469, "step": 760 }, { "epoch": 0.49386701097482244, "grad_norm": 4.880835940718014, "learning_rate": 1.1948140205348592e-05, "loss": 1.5735, "step": 765 }, { "epoch": 0.4970948999354422, "grad_norm": 5.615682640085302, "learning_rate": 1.1837495178165706e-05, "loss": 1.5648, "step": 770 }, { "epoch": 0.500322788896062, "grad_norm": 5.322385655290283, "learning_rate": 1.1726616839658237e-05, "loss": 1.6223, "step": 775 }, { "epoch": 0.5035506778566817, "grad_norm": 5.372959800238378, "learning_rate": 1.1615519268324101e-05, "loss": 1.5339, "step": 780 }, { "epoch": 0.5067785668173015, "grad_norm": 5.8491464237293, "learning_rate": 1.1504216570497737e-05, "loss": 1.5575, "step": 785 }, { "epoch": 0.5100064557779213, "grad_norm": 5.292821692941134, "learning_rate": 1.1392722878559012e-05, "loss": 1.6182, "step": 790 }, { "epoch": 0.513234344738541, "grad_norm": 5.798146550880112, "learning_rate": 1.1281052349138793e-05, "loss": 1.5844, "step": 795 }, { "epoch": 0.5164622336991608, "grad_norm": 5.6823764366973935, "learning_rate": 1.116921916132143e-05, "loss": 1.5739, "step": 800 }, { "epoch": 0.5196901226597805, "grad_norm": 5.761134241104277, "learning_rate": 1.1057237514844423e-05, "loss": 1.6409, "step": 805 }, { "epoch": 0.5229180116204003, "grad_norm": 4.938806993669054, "learning_rate": 1.0945121628295437e-05, "loss": 1.5921, "step": 810 }, { "epoch": 0.5261459005810201, "grad_norm": 15.683819077262335, "learning_rate": 1.0832885737306922e-05, "loss": 1.7035, "step": 815 }, { "epoch": 0.5293737895416397, "grad_norm": 5.4993649210417965, "learning_rate": 1.0720544092748599e-05, "loss": 1.5382, "step": 820 }, { "epoch": 0.5326016785022595, "grad_norm": 5.092222218274809, "learning_rate": 1.0608110958917982e-05, "loss": 1.6136, "step": 825 }, { "epoch": 0.5358295674628792, "grad_norm": 4.930191624792412, "learning_rate": 1.04956006117292e-05, "loss": 1.5622, "step": 830 }, { "epoch": 0.539057456423499, "grad_norm": 5.399945563067967, "learning_rate": 1.0383027336900356e-05, "loss": 1.5412, "step": 835 }, { "epoch": 0.5422853453841188, "grad_norm": 5.781669659732203, "learning_rate": 1.0270405428139633e-05, "loss": 1.6486, "step": 840 }, { "epoch": 0.5455132343447385, "grad_norm": 5.519605623300351, "learning_rate": 1.0157749185330384e-05, "loss": 1.6219, "step": 845 }, { "epoch": 0.5487411233053583, "grad_norm": 6.008340474166314, "learning_rate": 1.0045072912715443e-05, "loss": 1.6015, "step": 850 }, { "epoch": 0.551969012265978, "grad_norm": 5.131256451670003, "learning_rate": 9.932390917080874e-06, "loss": 1.566, "step": 855 }, { "epoch": 0.5551969012265978, "grad_norm": 5.419158342369302, "learning_rate": 9.81971750593941e-06, "loss": 1.5701, "step": 860 }, { "epoch": 0.5584247901872176, "grad_norm": 5.354220565411314, "learning_rate": 9.707066985713795e-06, "loss": 1.5487, "step": 865 }, { "epoch": 0.5616526791478373, "grad_norm": 4.995550545914696, "learning_rate": 9.594453659920241e-06, "loss": 1.5052, "step": 870 }, { "epoch": 0.5648805681084571, "grad_norm": 5.224319860529777, "learning_rate": 9.48189182735231e-06, "loss": 1.5371, "step": 875 }, { "epoch": 0.5681084570690769, "grad_norm": 5.240828267758849, "learning_rate": 9.369395780265323e-06, "loss": 1.5537, "step": 880 }, { "epoch": 0.5713363460296966, "grad_norm": 5.4919915569394915, "learning_rate": 9.256979802561675e-06, "loss": 1.5706, "step": 885 }, { "epoch": 0.5745642349903163, "grad_norm": 5.198809451347601, "learning_rate": 9.144658167977134e-06, "loss": 1.5988, "step": 890 }, { "epoch": 0.577792123950936, "grad_norm": 5.389465699869633, "learning_rate": 9.032445138268493e-06, "loss": 1.5407, "step": 895 }, { "epoch": 0.5810200129115558, "grad_norm": 5.495352080530079, "learning_rate": 8.920354961402723e-06, "loss": 1.5559, "step": 900 }, { "epoch": 0.5842479018721756, "grad_norm": 5.612791353311329, "learning_rate": 8.808401869747858e-06, "loss": 1.5855, "step": 905 }, { "epoch": 0.5874757908327953, "grad_norm": 5.400883996398841, "learning_rate": 8.696600078265876e-06, "loss": 1.5122, "step": 910 }, { "epoch": 0.5907036797934151, "grad_norm": 4.832336508421307, "learning_rate": 8.584963782707812e-06, "loss": 1.5118, "step": 915 }, { "epoch": 0.5939315687540349, "grad_norm": 5.0951094528676455, "learning_rate": 8.473507157811254e-06, "loss": 1.4892, "step": 920 }, { "epoch": 0.5971594577146546, "grad_norm": 5.8252974300330225, "learning_rate": 8.362244355500583e-06, "loss": 1.5714, "step": 925 }, { "epoch": 0.6003873466752744, "grad_norm": 5.236089319233509, "learning_rate": 8.251189503090023e-06, "loss": 1.5833, "step": 930 }, { "epoch": 0.6036152356358941, "grad_norm": 5.343216112400599, "learning_rate": 8.140356701489892e-06, "loss": 1.4814, "step": 935 }, { "epoch": 0.6068431245965139, "grad_norm": 4.908961690980711, "learning_rate": 8.029760023416168e-06, "loss": 1.5093, "step": 940 }, { "epoch": 0.6100710135571337, "grad_norm": 5.245691260381996, "learning_rate": 7.919413511603636e-06, "loss": 1.5963, "step": 945 }, { "epoch": 0.6132989025177534, "grad_norm": 5.621910081780513, "learning_rate": 7.809331177022847e-06, "loss": 1.5196, "step": 950 }, { "epoch": 0.6165267914783732, "grad_norm": 5.8427500582760175, "learning_rate": 7.699526997101121e-06, "loss": 1.5567, "step": 955 }, { "epoch": 0.6197546804389928, "grad_norm": 5.683875417006101, "learning_rate": 7.590014913947778e-06, "loss": 1.5644, "step": 960 }, { "epoch": 0.6229825693996126, "grad_norm": 5.458609295388963, "learning_rate": 7.4808088325839e-06, "loss": 1.523, "step": 965 }, { "epoch": 0.6262104583602324, "grad_norm": 5.991795522009256, "learning_rate": 7.3719226191767526e-06, "loss": 1.5572, "step": 970 }, { "epoch": 0.6294383473208521, "grad_norm": 5.104396720609387, "learning_rate": 7.263370099279173e-06, "loss": 1.5125, "step": 975 }, { "epoch": 0.6326662362814719, "grad_norm": 5.179959578065037, "learning_rate": 7.155165056074111e-06, "loss": 1.5097, "step": 980 }, { "epoch": 0.6358941252420917, "grad_norm": 5.547151238761799, "learning_rate": 7.0473212286245316e-06, "loss": 1.581, "step": 985 }, { "epoch": 0.6391220142027114, "grad_norm": 5.906714474067254, "learning_rate": 6.9398523101289475e-06, "loss": 1.5799, "step": 990 }, { "epoch": 0.6423499031633312, "grad_norm": 5.211200331104552, "learning_rate": 6.832771946182741e-06, "loss": 1.5565, "step": 995 }, { "epoch": 0.6455777921239509, "grad_norm": 5.268610977952413, "learning_rate": 6.72609373304556e-06, "loss": 1.4848, "step": 1000 }, { "epoch": 0.6488056810845707, "grad_norm": 5.439250857230896, "learning_rate": 6.619831215914974e-06, "loss": 1.5022, "step": 1005 }, { "epoch": 0.6520335700451905, "grad_norm": 5.360521278150201, "learning_rate": 6.5139978872065865e-06, "loss": 1.4935, "step": 1010 }, { "epoch": 0.6552614590058102, "grad_norm": 5.796210278315953, "learning_rate": 6.408607184840897e-06, "loss": 1.5625, "step": 1015 }, { "epoch": 0.65848934796643, "grad_norm": 5.020044853823784, "learning_rate": 6.303672490537022e-06, "loss": 1.4925, "step": 1020 }, { "epoch": 0.6617172369270498, "grad_norm": 5.291440134096366, "learning_rate": 6.199207128113614e-06, "loss": 1.5557, "step": 1025 }, { "epoch": 0.6649451258876695, "grad_norm": 5.239441257851841, "learning_rate": 6.095224361797087e-06, "loss": 1.582, "step": 1030 }, { "epoch": 0.6681730148482892, "grad_norm": 5.202258142662834, "learning_rate": 5.991737394537434e-06, "loss": 1.5321, "step": 1035 }, { "epoch": 0.6714009038089089, "grad_norm": 6.1919229333140375, "learning_rate": 5.888759366331798e-06, "loss": 1.5242, "step": 1040 }, { "epoch": 0.6746287927695287, "grad_norm": 5.057056436772678, "learning_rate": 5.786303352556088e-06, "loss": 1.4598, "step": 1045 }, { "epoch": 0.6778566817301485, "grad_norm": 5.148137854904367, "learning_rate": 5.684382362304723e-06, "loss": 1.5076, "step": 1050 }, { "epoch": 0.6810845706907682, "grad_norm": 5.515091391109832, "learning_rate": 5.583009336738874e-06, "loss": 1.5496, "step": 1055 }, { "epoch": 0.684312459651388, "grad_norm": 5.784777023225698, "learning_rate": 5.48219714744326e-06, "loss": 1.5131, "step": 1060 }, { "epoch": 0.6875403486120077, "grad_norm": 5.59776729212278, "learning_rate": 5.381958594791843e-06, "loss": 1.4729, "step": 1065 }, { "epoch": 0.6907682375726275, "grad_norm": 5.1330532599827485, "learning_rate": 5.282306406322502e-06, "loss": 1.5357, "step": 1070 }, { "epoch": 0.6939961265332473, "grad_norm": 5.530634545266258, "learning_rate": 5.1832532351210095e-06, "loss": 1.5159, "step": 1075 }, { "epoch": 0.697224015493867, "grad_norm": 5.190707271947593, "learning_rate": 5.084811658214421e-06, "loss": 1.5047, "step": 1080 }, { "epoch": 0.7004519044544868, "grad_norm": 5.554567104196739, "learning_rate": 4.986994174974155e-06, "loss": 1.5259, "step": 1085 }, { "epoch": 0.7036797934151066, "grad_norm": 5.540622719340587, "learning_rate": 4.889813205528895e-06, "loss": 1.4371, "step": 1090 }, { "epoch": 0.7069076823757263, "grad_norm": 5.532974890894428, "learning_rate": 4.793281089187603e-06, "loss": 1.4397, "step": 1095 }, { "epoch": 0.7101355713363461, "grad_norm": 5.084284858142072, "learning_rate": 4.697410082872741e-06, "loss": 1.4826, "step": 1100 }, { "epoch": 0.7133634602969657, "grad_norm": 5.374832286921831, "learning_rate": 4.602212359563988e-06, "loss": 1.5031, "step": 1105 }, { "epoch": 0.7165913492575855, "grad_norm": 5.436449921979155, "learning_rate": 4.50770000675262e-06, "loss": 1.482, "step": 1110 }, { "epoch": 0.7198192382182053, "grad_norm": 5.367567637926529, "learning_rate": 4.413885024906705e-06, "loss": 1.492, "step": 1115 }, { "epoch": 0.723047127178825, "grad_norm": 5.459559639213619, "learning_rate": 4.320779325947402e-06, "loss": 1.4527, "step": 1120 }, { "epoch": 0.7262750161394448, "grad_norm": 5.710733826769647, "learning_rate": 4.228394731736451e-06, "loss": 1.526, "step": 1125 }, { "epoch": 0.7295029051000645, "grad_norm": 4.911675403161043, "learning_rate": 4.136742972575132e-06, "loss": 1.5134, "step": 1130 }, { "epoch": 0.7327307940606843, "grad_norm": 5.602840040740436, "learning_rate": 4.045835685714848e-06, "loss": 1.4289, "step": 1135 }, { "epoch": 0.7359586830213041, "grad_norm": 5.035789822163729, "learning_rate": 3.955684413879499e-06, "loss": 1.4759, "step": 1140 }, { "epoch": 0.7391865719819238, "grad_norm": 5.094039088957984, "learning_rate": 3.866300603799876e-06, "loss": 1.4575, "step": 1145 }, { "epoch": 0.7424144609425436, "grad_norm": 5.49222076162649, "learning_rate": 3.77769560476026e-06, "loss": 1.4581, "step": 1150 }, { "epoch": 0.7456423499031634, "grad_norm": 5.715064526970072, "learning_rate": 3.689880667157344e-06, "loss": 1.5579, "step": 1155 }, { "epoch": 0.7488702388637831, "grad_norm": 5.524488815265337, "learning_rate": 3.602866941071773e-06, "loss": 1.4336, "step": 1160 }, { "epoch": 0.7520981278244029, "grad_norm": 5.364873008254881, "learning_rate": 3.516665474852369e-06, "loss": 1.4432, "step": 1165 }, { "epoch": 0.7553260167850226, "grad_norm": 5.2752700833072845, "learning_rate": 3.431287213713299e-06, "loss": 1.4944, "step": 1170 }, { "epoch": 0.7585539057456423, "grad_norm": 5.2004940717802, "learning_rate": 3.3467429983443477e-06, "loss": 1.4047, "step": 1175 }, { "epoch": 0.7617817947062621, "grad_norm": 5.1840162953693545, "learning_rate": 3.2630435635344283e-06, "loss": 1.4254, "step": 1180 }, { "epoch": 0.7650096836668818, "grad_norm": 5.488420884341952, "learning_rate": 3.180199536808576e-06, "loss": 1.414, "step": 1185 }, { "epoch": 0.7682375726275016, "grad_norm": 5.189126496815558, "learning_rate": 3.0982214370785335e-06, "loss": 1.4575, "step": 1190 }, { "epoch": 0.7714654615881213, "grad_norm": 5.038917252480004, "learning_rate": 3.0171196733071405e-06, "loss": 1.5069, "step": 1195 }, { "epoch": 0.7746933505487411, "grad_norm": 5.1969535616381926, "learning_rate": 2.936904543186695e-06, "loss": 1.4508, "step": 1200 }, { "epoch": 0.7779212395093609, "grad_norm": 5.160164936057216, "learning_rate": 2.8575862318314087e-06, "loss": 1.4409, "step": 1205 }, { "epoch": 0.7811491284699806, "grad_norm": 5.3476935943523385, "learning_rate": 2.7791748104841876e-06, "loss": 1.4374, "step": 1210 }, { "epoch": 0.7843770174306004, "grad_norm": 5.370458539003402, "learning_rate": 2.7016802352378755e-06, "loss": 1.4268, "step": 1215 }, { "epoch": 0.7876049063912202, "grad_norm": 5.045239556202245, "learning_rate": 2.6251123457710726e-06, "loss": 1.4379, "step": 1220 }, { "epoch": 0.7908327953518399, "grad_norm": 5.271081605175723, "learning_rate": 2.5494808640988e-06, "loss": 1.474, "step": 1225 }, { "epoch": 0.7940606843124597, "grad_norm": 5.4078856513908296, "learning_rate": 2.4747953933380463e-06, "loss": 1.476, "step": 1230 }, { "epoch": 0.7972885732730794, "grad_norm": 5.765653151999692, "learning_rate": 2.4010654164884527e-06, "loss": 1.4782, "step": 1235 }, { "epoch": 0.8005164622336992, "grad_norm": 5.092525169561813, "learning_rate": 2.328300295228221e-06, "loss": 1.4497, "step": 1240 }, { "epoch": 0.8037443511943189, "grad_norm": 4.722681501392939, "learning_rate": 2.2565092687254486e-06, "loss": 1.466, "step": 1245 }, { "epoch": 0.8069722401549386, "grad_norm": 5.057426901667458, "learning_rate": 2.185701452464997e-06, "loss": 1.4358, "step": 1250 }, { "epoch": 0.8102001291155584, "grad_norm": 4.837982928648199, "learning_rate": 2.1158858370910905e-06, "loss": 1.4249, "step": 1255 }, { "epoch": 0.8134280180761781, "grad_norm": 5.165161107325633, "learning_rate": 2.047071287265735e-06, "loss": 1.4211, "step": 1260 }, { "epoch": 0.8166559070367979, "grad_norm": 5.068834680044366, "learning_rate": 1.9792665405431654e-06, "loss": 1.3746, "step": 1265 }, { "epoch": 0.8198837959974177, "grad_norm": 5.453220592450874, "learning_rate": 1.9124802062604066e-06, "loss": 1.456, "step": 1270 }, { "epoch": 0.8231116849580374, "grad_norm": 5.648842929433009, "learning_rate": 1.8467207644441243e-06, "loss": 1.4727, "step": 1275 }, { "epoch": 0.8263395739186572, "grad_norm": 5.304857997339736, "learning_rate": 1.7819965647339065e-06, "loss": 1.4979, "step": 1280 }, { "epoch": 0.829567462879277, "grad_norm": 5.45097229329167, "learning_rate": 1.718315825322071e-06, "loss": 1.4318, "step": 1285 }, { "epoch": 0.8327953518398967, "grad_norm": 5.021145599454475, "learning_rate": 1.6556866319102027e-06, "loss": 1.4988, "step": 1290 }, { "epoch": 0.8360232408005165, "grad_norm": 5.402016832769367, "learning_rate": 1.5941169366824705e-06, "loss": 1.4616, "step": 1295 }, { "epoch": 0.8392511297611362, "grad_norm": 5.399074896944535, "learning_rate": 1.5336145572959283e-06, "loss": 1.4384, "step": 1300 }, { "epoch": 0.842479018721756, "grad_norm": 5.471814490238626, "learning_rate": 1.4741871758878978e-06, "loss": 1.4333, "step": 1305 }, { "epoch": 0.8457069076823758, "grad_norm": 5.289307631746622, "learning_rate": 1.4158423381005294e-06, "loss": 1.4523, "step": 1310 }, { "epoch": 0.8489347966429954, "grad_norm": 5.020917216038537, "learning_rate": 1.3585874521227226e-06, "loss": 1.3762, "step": 1315 }, { "epoch": 0.8521626856036152, "grad_norm": 5.00624606287639, "learning_rate": 1.3024297877494973e-06, "loss": 1.4612, "step": 1320 }, { "epoch": 0.855390574564235, "grad_norm": 5.429810940921615, "learning_rate": 1.2473764754589123e-06, "loss": 1.4305, "step": 1325 }, { "epoch": 0.8586184635248547, "grad_norm": 5.1399015375442385, "learning_rate": 1.193434505506711e-06, "loss": 1.4399, "step": 1330 }, { "epoch": 0.8618463524854745, "grad_norm": 4.9707825715846665, "learning_rate": 1.1406107270387323e-06, "loss": 1.4398, "step": 1335 }, { "epoch": 0.8650742414460942, "grad_norm": 5.053643246086415, "learning_rate": 1.0889118472212702e-06, "loss": 1.4304, "step": 1340 }, { "epoch": 0.868302130406714, "grad_norm": 5.028185854558994, "learning_rate": 1.0383444303894453e-06, "loss": 1.4038, "step": 1345 }, { "epoch": 0.8715300193673338, "grad_norm": 5.112792724899338, "learning_rate": 9.889148972137097e-07, "loss": 1.4334, "step": 1350 }, { "epoch": 0.8747579083279535, "grad_norm": 5.1166189472841275, "learning_rate": 9.406295238846108e-07, "loss": 1.3857, "step": 1355 }, { "epoch": 0.8779857972885733, "grad_norm": 4.705706257850879, "learning_rate": 8.934944413158708e-07, "loss": 1.437, "step": 1360 }, { "epoch": 0.881213686249193, "grad_norm": 5.788807086151138, "learning_rate": 8.475156343659408e-07, "loss": 1.4031, "step": 1365 }, { "epoch": 0.8844415752098128, "grad_norm": 6.376811639197679, "learning_rate": 8.026989410780917e-07, "loss": 1.4084, "step": 1370 }, { "epoch": 0.8876694641704326, "grad_norm": 5.268830672903035, "learning_rate": 7.590500519391309e-07, "loss": 1.4988, "step": 1375 }, { "epoch": 0.8908973531310523, "grad_norm": 5.049110069527227, "learning_rate": 7.165745091568743e-07, "loss": 1.4573, "step": 1380 }, { "epoch": 0.8941252420916721, "grad_norm": 5.353866067530813, "learning_rate": 6.752777059564431e-07, "loss": 1.4051, "step": 1385 }, { "epoch": 0.8973531310522918, "grad_norm": 5.262463327229783, "learning_rate": 6.351648858954618e-07, "loss": 1.4635, "step": 1390 }, { "epoch": 0.9005810200129115, "grad_norm": 5.279272053499587, "learning_rate": 5.962411421982805e-07, "loss": 1.501, "step": 1395 }, { "epoch": 0.9038089089735313, "grad_norm": 6.166665329453942, "learning_rate": 5.585114171092665e-07, "loss": 1.4967, "step": 1400 }, { "epoch": 0.907036797934151, "grad_norm": 5.922366006208264, "learning_rate": 5.219805012652867e-07, "loss": 1.4908, "step": 1405 }, { "epoch": 0.9102646868947708, "grad_norm": 5.31947537122732, "learning_rate": 4.866530330874153e-07, "loss": 1.4639, "step": 1410 }, { "epoch": 0.9134925758553906, "grad_norm": 5.284266331508542, "learning_rate": 4.5253349819199375e-07, "loss": 1.3801, "step": 1415 }, { "epoch": 0.9167204648160103, "grad_norm": 5.00246174936465, "learning_rate": 4.1962622882107174e-07, "loss": 1.489, "step": 1420 }, { "epoch": 0.9199483537766301, "grad_norm": 5.196352989285751, "learning_rate": 3.8793540329233994e-07, "loss": 1.423, "step": 1425 }, { "epoch": 0.9231762427372499, "grad_norm": 5.636396405762381, "learning_rate": 3.574650454685902e-07, "loss": 1.3957, "step": 1430 }, { "epoch": 0.9264041316978696, "grad_norm": 5.7760912377631195, "learning_rate": 3.282190242468031e-07, "loss": 1.4413, "step": 1435 }, { "epoch": 0.9296320206584894, "grad_norm": 5.284630555099834, "learning_rate": 3.0020105306689973e-07, "loss": 1.4106, "step": 1440 }, { "epoch": 0.9328599096191091, "grad_norm": 5.215595343936084, "learning_rate": 2.7341468944023677e-07, "loss": 1.4156, "step": 1445 }, { "epoch": 0.9360877985797289, "grad_norm": 5.792924133971526, "learning_rate": 2.4786333449790753e-07, "loss": 1.4402, "step": 1450 }, { "epoch": 0.9393156875403487, "grad_norm": 5.1222262590925265, "learning_rate": 2.235502325588823e-07, "loss": 1.456, "step": 1455 }, { "epoch": 0.9425435765009683, "grad_norm": 5.10978965516164, "learning_rate": 2.0047847071807402e-07, "loss": 1.4556, "step": 1460 }, { "epoch": 0.9457714654615881, "grad_norm": 5.133920634072317, "learning_rate": 1.786509784543633e-07, "loss": 1.5004, "step": 1465 }, { "epoch": 0.9489993544222078, "grad_norm": 4.93946597689753, "learning_rate": 1.5807052725863025e-07, "loss": 1.4039, "step": 1470 }, { "epoch": 0.9522272433828276, "grad_norm": 5.19013537792188, "learning_rate": 1.3873973028185827e-07, "loss": 1.4215, "step": 1475 }, { "epoch": 0.9554551323434474, "grad_norm": 5.111399221550104, "learning_rate": 1.206610420033305e-07, "loss": 1.3986, "step": 1480 }, { "epoch": 0.9586830213040671, "grad_norm": 5.234642603752152, "learning_rate": 1.038367579189803e-07, "loss": 1.3943, "step": 1485 }, { "epoch": 0.9619109102646869, "grad_norm": 5.645148935175098, "learning_rate": 8.82690142499254e-08, "loss": 1.4748, "step": 1490 }, { "epoch": 0.9651387992253067, "grad_norm": 5.020357239881912, "learning_rate": 7.395978767122946e-08, "loss": 1.4324, "step": 1495 }, { "epoch": 0.9683666881859264, "grad_norm": 5.6120171308753894, "learning_rate": 6.091089506091386e-08, "loss": 1.4205, "step": 1500 }, { "epoch": 0.9715945771465462, "grad_norm": 5.898083266442407, "learning_rate": 4.9123993269271084e-08, "loss": 1.4123, "step": 1505 }, { "epoch": 0.9748224661071659, "grad_norm": 5.408173578697908, "learning_rate": 3.860057890848201e-08, "loss": 1.4376, "step": 1510 }, { "epoch": 0.9780503550677857, "grad_norm": 5.421313383210646, "learning_rate": 2.9341988162595593e-08, "loss": 1.4265, "step": 1515 }, { "epoch": 0.9812782440284055, "grad_norm": 5.55675456499392, "learning_rate": 2.1349396617862395e-08, "loss": 1.4463, "step": 1520 }, { "epoch": 0.9845061329890252, "grad_norm": 5.211225978985049, "learning_rate": 1.4623819113475102e-08, "loss": 1.4244, "step": 1525 }, { "epoch": 0.9877340219496449, "grad_norm": 5.824025695493701, "learning_rate": 9.166109612706031e-09, "loss": 1.4411, "step": 1530 }, { "epoch": 0.9909619109102646, "grad_norm": 4.826680454755765, "learning_rate": 4.976961094479427e-09, "loss": 1.4475, "step": 1535 }, { "epoch": 0.9941897998708844, "grad_norm": 5.614005751299077, "learning_rate": 2.0569054653840625e-09, "loss": 1.4278, "step": 1540 }, { "epoch": 0.9974176888315042, "grad_norm": 5.395704789347489, "learning_rate": 4.0631349213060555e-10, "loss": 1.3988, "step": 1545 }, { "epoch": 1.0, "eval_loss": 1.406965732574463, "eval_runtime": 263.0675, "eval_samples_per_second": 31.703, "eval_steps_per_second": 0.992, "step": 1549 }, { "epoch": 1.0, "step": 1549, "total_flos": 19248551362560.0, "train_loss": 1.5783487337492912, "train_runtime": 6620.0514, "train_samples_per_second": 7.485, "train_steps_per_second": 0.234 } ], "logging_steps": 5, "max_steps": 1549, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": true }, "attributes": {} } }, "total_flos": 19248551362560.0, "train_batch_size": 8, "trial_name": null, "trial_params": null }