{ "best_global_step": null, "best_metric": null, "best_model_checkpoint": null, "epoch": 0.06709833260643473, "eval_steps": 500, "global_step": 2000, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.00033549166303217364, "grad_norm": 3.6124119758605957, "learning_rate": 2.011173184357542e-06, "loss": 2.9620466232299805, "step": 10 }, { "epoch": 0.0006709833260643473, "grad_norm": 0.8180733323097229, "learning_rate": 4.245810055865922e-06, "loss": 2.254135513305664, "step": 20 }, { "epoch": 0.0010064749890965209, "grad_norm": 1.8416152000427246, "learning_rate": 6.4804469273743025e-06, "loss": 2.308770179748535, "step": 30 }, { "epoch": 0.0013419666521286946, "grad_norm": 1.6899038553237915, "learning_rate": 8.715083798882683e-06, "loss": 2.354534149169922, "step": 40 }, { "epoch": 0.0016774583151608683, "grad_norm": 1.0635626316070557, "learning_rate": 1.0949720670391061e-05, "loss": 1.9643959045410155, "step": 50 }, { "epoch": 0.0020129499781930417, "grad_norm": 1.7144725322723389, "learning_rate": 1.3184357541899443e-05, "loss": 2.196229934692383, "step": 60 }, { "epoch": 0.0023484416412252154, "grad_norm": 2.0055930614471436, "learning_rate": 1.5418994413407823e-05, "loss": 1.9873594284057616, "step": 70 }, { "epoch": 0.002683933304257389, "grad_norm": 1.3090643882751465, "learning_rate": 1.7653631284916203e-05, "loss": 1.7420753479003905, "step": 80 }, { "epoch": 0.003019424967289563, "grad_norm": 0.6108576655387878, "learning_rate": 1.9888268156424583e-05, "loss": 1.8236627578735352, "step": 90 }, { "epoch": 0.0033549166303217365, "grad_norm": 0.6574695706367493, "learning_rate": 2.212290502793296e-05, "loss": 1.7359764099121093, "step": 100 }, { "epoch": 0.0036904082933539102, "grad_norm": 0.8230994939804077, "learning_rate": 2.4357541899441343e-05, "loss": 1.5833864212036133, "step": 110 }, { "epoch": 0.0040258999563860835, "grad_norm": 0.9543447494506836, "learning_rate": 2.6592178770949723e-05, "loss": 1.51551513671875, "step": 120 }, { "epoch": 0.004361391619418257, "grad_norm": 0.9667573571205139, "learning_rate": 2.88268156424581e-05, "loss": 1.4613374710083007, "step": 130 }, { "epoch": 0.004696883282450431, "grad_norm": 1.9220093488693237, "learning_rate": 3.106145251396648e-05, "loss": 1.5392029762268067, "step": 140 }, { "epoch": 0.005032374945482605, "grad_norm": 0.7170810699462891, "learning_rate": 3.329608938547486e-05, "loss": 1.5076921463012696, "step": 150 }, { "epoch": 0.005367866608514778, "grad_norm": 0.8078820705413818, "learning_rate": 3.553072625698324e-05, "loss": 1.7222694396972655, "step": 160 }, { "epoch": 0.005703358271546952, "grad_norm": 0.809903085231781, "learning_rate": 3.776536312849162e-05, "loss": 1.8752283096313476, "step": 170 }, { "epoch": 0.006038849934579126, "grad_norm": 0.7261088490486145, "learning_rate": 4e-05, "loss": 1.3927306175231933, "step": 180 }, { "epoch": 0.006374341597611299, "grad_norm": 1.5483784675598145, "learning_rate": 4.223463687150838e-05, "loss": 1.4321404457092286, "step": 190 }, { "epoch": 0.006709833260643473, "grad_norm": 0.7559241056442261, "learning_rate": 4.4469273743016757e-05, "loss": 1.325460147857666, "step": 200 }, { "epoch": 0.007045324923675647, "grad_norm": 1.563735008239746, "learning_rate": 4.670391061452514e-05, "loss": 1.372646427154541, "step": 210 }, { "epoch": 0.0073808165867078205, "grad_norm": 0.752616822719574, "learning_rate": 4.8938547486033523e-05, "loss": 1.1150728225708009, "step": 220 }, { "epoch": 0.007716308249739994, "grad_norm": 0.8065235614776611, "learning_rate": 5.11731843575419e-05, "loss": 1.1660142898559571, "step": 230 }, { "epoch": 0.008051799912772167, "grad_norm": 0.9588292241096497, "learning_rate": 5.3407821229050284e-05, "loss": 1.1108501434326172, "step": 240 }, { "epoch": 0.008387291575804342, "grad_norm": 0.8693965077400208, "learning_rate": 5.564245810055866e-05, "loss": 1.4471724510192872, "step": 250 }, { "epoch": 0.008722783238836514, "grad_norm": 2.0879530906677246, "learning_rate": 5.787709497206704e-05, "loss": 1.2001781463623047, "step": 260 }, { "epoch": 0.009058274901868689, "grad_norm": 0.8522306084632874, "learning_rate": 6.011173184357543e-05, "loss": 1.363035297393799, "step": 270 }, { "epoch": 0.009393766564900862, "grad_norm": 1.0152027606964111, "learning_rate": 6.23463687150838e-05, "loss": 1.2856069564819337, "step": 280 }, { "epoch": 0.009729258227933036, "grad_norm": NaN, "learning_rate": 6.458100558659218e-05, "loss": 2.133226013183594, "step": 290 }, { "epoch": 0.01006474989096521, "grad_norm": NaN, "learning_rate": 6.681564245810056e-05, "loss": 5.05937385559082, "step": 300 }, { "epoch": 0.010400241553997384, "grad_norm": NaN, "learning_rate": 6.905027932960895e-05, "loss": 4.477165985107422, "step": 310 }, { "epoch": 0.010735733217029557, "grad_norm": 3.5620813369750977, "learning_rate": 7.128491620111732e-05, "loss": 2.7552057266235352, "step": 320 }, { "epoch": 0.011071224880061731, "grad_norm": NaN, "learning_rate": 7.35195530726257e-05, "loss": 2.6008926391601563, "step": 330 }, { "epoch": 0.011406716543093904, "grad_norm": NaN, "learning_rate": 7.575418994413408e-05, "loss": 13.484027099609374, "step": 340 }, { "epoch": 0.011742208206126079, "grad_norm": NaN, "learning_rate": 7.798882681564245e-05, "loss": 17.163206481933592, "step": 350 }, { "epoch": 0.012077699869158251, "grad_norm": NaN, "learning_rate": 8.022346368715084e-05, "loss": 8.245307922363281, "step": 360 }, { "epoch": 0.012413191532190426, "grad_norm": NaN, "learning_rate": 8.245810055865922e-05, "loss": 8.971550750732423, "step": 370 }, { "epoch": 0.012748683195222599, "grad_norm": NaN, "learning_rate": 8.46927374301676e-05, "loss": 8.085272979736327, "step": 380 }, { "epoch": 0.013084174858254772, "grad_norm": NaN, "learning_rate": 8.692737430167597e-05, "loss": 2.434987258911133, "step": 390 }, { "epoch": 0.013419666521286946, "grad_norm": NaN, "learning_rate": 8.916201117318435e-05, "loss": 17.522901916503905, "step": 400 }, { "epoch": 0.013755158184319119, "grad_norm": NaN, "learning_rate": 9.139664804469274e-05, "loss": 9.243440246582031, "step": 410 }, { "epoch": 0.014090649847351294, "grad_norm": NaN, "learning_rate": 9.363128491620112e-05, "loss": 5.988158798217773, "step": 420 }, { "epoch": 0.014426141510383466, "grad_norm": NaN, "learning_rate": 9.58659217877095e-05, "loss": 9.994813537597656, "step": 430 }, { "epoch": 0.014761633173415641, "grad_norm": NaN, "learning_rate": 9.810055865921788e-05, "loss": 3.905954360961914, "step": 440 }, { "epoch": 0.015097124836447814, "grad_norm": NaN, "learning_rate": 0.00010033519553072626, "loss": 4.835385513305664, "step": 450 }, { "epoch": 0.015432616499479988, "grad_norm": NaN, "learning_rate": 0.00010256983240223464, "loss": 2.324123764038086, "step": 460 }, { "epoch": 0.015768108162512163, "grad_norm": NaN, "learning_rate": 0.00010480446927374301, "loss": 9.202623748779297, "step": 470 }, { "epoch": 0.016103599825544334, "grad_norm": NaN, "learning_rate": 0.0001070391061452514, "loss": 13.691998291015626, "step": 480 }, { "epoch": 0.01643909148857651, "grad_norm": NaN, "learning_rate": 0.0001092737430167598, "loss": 10.514191436767579, "step": 490 }, { "epoch": 0.016774583151608683, "grad_norm": NaN, "learning_rate": 0.00011150837988826817, "loss": 6.2412151336669925, "step": 500 }, { "epoch": 0.017110074814640858, "grad_norm": NaN, "learning_rate": 0.00011374301675977655, "loss": 2.3255378723144533, "step": 510 }, { "epoch": 0.01744556647767303, "grad_norm": NaN, "learning_rate": 0.00011597765363128493, "loss": 2.0067920684814453, "step": 520 }, { "epoch": 0.017781058140705203, "grad_norm": NaN, "learning_rate": 0.0001182122905027933, "loss": 60.400030517578124, "step": 530 }, { "epoch": 0.018116549803737378, "grad_norm": NaN, "learning_rate": 0.00012044692737430168, "loss": 40.79320373535156, "step": 540 }, { "epoch": 0.018452041466769552, "grad_norm": NaN, "learning_rate": 0.00012268156424581004, "loss": 55.823065185546874, "step": 550 }, { "epoch": 0.018787533129801724, "grad_norm": NaN, "learning_rate": 0.00012491620111731845, "loss": 6.039075469970703, "step": 560 }, { "epoch": 0.019123024792833898, "grad_norm": NaN, "learning_rate": 0.00012715083798882682, "loss": 127.98883056640625, "step": 570 }, { "epoch": 0.019458516455866073, "grad_norm": NaN, "learning_rate": 0.0001293854748603352, "loss": 7.4943595886230465, "step": 580 }, { "epoch": 0.019794008118898244, "grad_norm": NaN, "learning_rate": 0.00013162011173184358, "loss": 87.36739501953124, "step": 590 }, { "epoch": 0.02012949978193042, "grad_norm": NaN, "learning_rate": 0.00013385474860335195, "loss": 12.410279846191406, "step": 600 }, { "epoch": 0.020464991444962593, "grad_norm": NaN, "learning_rate": 0.00013608938547486036, "loss": 40.074404907226565, "step": 610 }, { "epoch": 0.020800483107994767, "grad_norm": NaN, "learning_rate": 0.00013832402234636873, "loss": 17.221456909179686, "step": 620 }, { "epoch": 0.02113597477102694, "grad_norm": NaN, "learning_rate": 0.0001405586592178771, "loss": 38.3494140625, "step": 630 }, { "epoch": 0.021471466434059113, "grad_norm": NaN, "learning_rate": 0.00014279329608938549, "loss": 5.291226577758789, "step": 640 }, { "epoch": 0.021806958097091288, "grad_norm": NaN, "learning_rate": 0.00014502793296089386, "loss": 6.93237533569336, "step": 650 }, { "epoch": 0.022142449760123462, "grad_norm": NaN, "learning_rate": 0.00014726256983240224, "loss": 5.8972515106201175, "step": 660 }, { "epoch": 0.022477941423155633, "grad_norm": NaN, "learning_rate": 0.00014949720670391064, "loss": 40.401693725585936, "step": 670 }, { "epoch": 0.022813433086187808, "grad_norm": NaN, "learning_rate": 0.00015173184357541902, "loss": 9.994586181640624, "step": 680 }, { "epoch": 0.023148924749219982, "grad_norm": NaN, "learning_rate": 0.0001539664804469274, "loss": 1.4739145278930663, "step": 690 }, { "epoch": 0.023484416412252157, "grad_norm": NaN, "learning_rate": 0.00015620111731843577, "loss": 6.606394958496094, "step": 700 }, { "epoch": 0.023819908075284328, "grad_norm": NaN, "learning_rate": 0.00015843575418994415, "loss": 26.84160461425781, "step": 710 }, { "epoch": 0.024155399738316503, "grad_norm": NaN, "learning_rate": 0.00016067039106145253, "loss": 7.266958618164063, "step": 720 }, { "epoch": 0.024490891401348677, "grad_norm": NaN, "learning_rate": 0.0001629050279329609, "loss": 0.5109624862670898, "step": 730 }, { "epoch": 0.024826383064380852, "grad_norm": NaN, "learning_rate": 0.00016513966480446928, "loss": 9.11468734741211, "step": 740 }, { "epoch": 0.025161874727413023, "grad_norm": NaN, "learning_rate": 0.00016737430167597766, "loss": 4.641835021972656, "step": 750 }, { "epoch": 0.025497366390445197, "grad_norm": NaN, "learning_rate": 0.00016960893854748606, "loss": 13.905538940429688, "step": 760 }, { "epoch": 0.025832858053477372, "grad_norm": NaN, "learning_rate": 0.00017184357541899444, "loss": 51.2526611328125, "step": 770 }, { "epoch": 0.026168349716509543, "grad_norm": NaN, "learning_rate": 0.0001740782122905028, "loss": 44.471441650390624, "step": 780 }, { "epoch": 0.026503841379541718, "grad_norm": NaN, "learning_rate": 0.0001763128491620112, "loss": 19.767466735839843, "step": 790 }, { "epoch": 0.026839333042573892, "grad_norm": NaN, "learning_rate": 0.00017854748603351957, "loss": 59.8121826171875, "step": 800 }, { "epoch": 0.027174824705606067, "grad_norm": NaN, "learning_rate": 0.00018078212290502794, "loss": 9.256180572509766, "step": 810 }, { "epoch": 0.027510316368638238, "grad_norm": NaN, "learning_rate": 0.00018301675977653632, "loss": 8.733799743652344, "step": 820 }, { "epoch": 0.027845808031670412, "grad_norm": NaN, "learning_rate": 0.0001852513966480447, "loss": 32.57587585449219, "step": 830 }, { "epoch": 0.028181299694702587, "grad_norm": NaN, "learning_rate": 0.00018748603351955307, "loss": 17.352330017089844, "step": 840 }, { "epoch": 0.02851679135773476, "grad_norm": NaN, "learning_rate": 0.00018972067039106148, "loss": 16.099330139160156, "step": 850 }, { "epoch": 0.028852283020766933, "grad_norm": NaN, "learning_rate": 0.00019195530726256985, "loss": 0.0, "step": 860 }, { "epoch": 0.029187774683799107, "grad_norm": NaN, "learning_rate": 0.00019418994413407823, "loss": 0.08051624894142151, "step": 870 }, { "epoch": 0.029523266346831282, "grad_norm": NaN, "learning_rate": 0.0001964245810055866, "loss": 0.06978185772895813, "step": 880 }, { "epoch": 0.029858758009863456, "grad_norm": NaN, "learning_rate": 0.00019865921787709498, "loss": 1.4936031341552733, "step": 890 }, { "epoch": 0.030194249672895628, "grad_norm": NaN, "learning_rate": 0.00019997232982844494, "loss": 4.048176193237305, "step": 900 }, { "epoch": 0.030529741335927802, "grad_norm": NaN, "learning_rate": 0.0001999031543995573, "loss": 0.108348548412323, "step": 910 }, { "epoch": 0.030865232998959977, "grad_norm": NaN, "learning_rate": 0.00019983397897066962, "loss": 1.5282353401184081, "step": 920 }, { "epoch": 0.03120072466199215, "grad_norm": NaN, "learning_rate": 0.00019976480354178198, "loss": 0.0, "step": 930 }, { "epoch": 0.031536216325024326, "grad_norm": NaN, "learning_rate": 0.0001996956281128943, "loss": 251.467236328125, "step": 940 }, { "epoch": 0.0318717079880565, "grad_norm": NaN, "learning_rate": 0.00019962645268400666, "loss": 82.037890625, "step": 950 }, { "epoch": 0.03220719965108867, "grad_norm": NaN, "learning_rate": 0.00019955727725511898, "loss": 0.0, "step": 960 }, { "epoch": 0.032542691314120846, "grad_norm": NaN, "learning_rate": 0.0001994881018262313, "loss": 0.0, "step": 970 }, { "epoch": 0.03287818297715302, "grad_norm": NaN, "learning_rate": 0.00019941892639734366, "loss": 0.3229848861694336, "step": 980 }, { "epoch": 0.03321367464018519, "grad_norm": NaN, "learning_rate": 0.00019934975096845602, "loss": 4.599651336669922, "step": 990 }, { "epoch": 0.033549166303217366, "grad_norm": NaN, "learning_rate": 0.00019928057553956837, "loss": 2.3171388626098635, "step": 1000 }, { "epoch": 0.03388465796624954, "grad_norm": NaN, "learning_rate": 0.0001992114001106807, "loss": 44.60954895019531, "step": 1010 }, { "epoch": 0.034220149629281715, "grad_norm": NaN, "learning_rate": 0.00019914222468179305, "loss": 1.6406478881835938, "step": 1020 }, { "epoch": 0.034555641292313886, "grad_norm": NaN, "learning_rate": 0.00019907304925290538, "loss": 1.0902439117431642, "step": 1030 }, { "epoch": 0.03489113295534606, "grad_norm": NaN, "learning_rate": 0.00019900387382401773, "loss": 9.517413330078124, "step": 1040 }, { "epoch": 0.035226624618378236, "grad_norm": NaN, "learning_rate": 0.00019893469839513006, "loss": 91.74754028320312, "step": 1050 }, { "epoch": 0.03556211628141041, "grad_norm": NaN, "learning_rate": 0.0001988655229662424, "loss": 161.57200927734374, "step": 1060 }, { "epoch": 0.03589760794444258, "grad_norm": NaN, "learning_rate": 0.00019879634753735474, "loss": 1.9749420166015625, "step": 1070 }, { "epoch": 0.036233099607474756, "grad_norm": NaN, "learning_rate": 0.00019872717210846707, "loss": 0.03762787282466888, "step": 1080 }, { "epoch": 0.03656859127050693, "grad_norm": NaN, "learning_rate": 0.00019865799667957942, "loss": 38.657388305664064, "step": 1090 }, { "epoch": 0.036904082933539105, "grad_norm": NaN, "learning_rate": 0.00019858882125069175, "loss": 5.60150375366211, "step": 1100 }, { "epoch": 0.037239574596571276, "grad_norm": NaN, "learning_rate": 0.0001985196458218041, "loss": 13.85815887451172, "step": 1110 }, { "epoch": 0.03757506625960345, "grad_norm": NaN, "learning_rate": 0.00019845047039291643, "loss": 38.748410034179685, "step": 1120 }, { "epoch": 0.037910557922635625, "grad_norm": NaN, "learning_rate": 0.00019838129496402878, "loss": 65.22340698242188, "step": 1130 }, { "epoch": 0.038246049585667796, "grad_norm": NaN, "learning_rate": 0.00019831211953514114, "loss": 0.8500317573547364, "step": 1140 }, { "epoch": 0.03858154124869997, "grad_norm": NaN, "learning_rate": 0.00019824294410625347, "loss": 143.4577880859375, "step": 1150 }, { "epoch": 0.038917032911732145, "grad_norm": NaN, "learning_rate": 0.00019817376867736582, "loss": 0.38392589092254636, "step": 1160 }, { "epoch": 0.039252524574764316, "grad_norm": NaN, "learning_rate": 0.00019810459324847815, "loss": 1.582177734375, "step": 1170 }, { "epoch": 0.03958801623779649, "grad_norm": NaN, "learning_rate": 0.0001980354178195905, "loss": 0.924138355255127, "step": 1180 }, { "epoch": 0.039923507900828666, "grad_norm": NaN, "learning_rate": 0.00019796624239070283, "loss": 0.0, "step": 1190 }, { "epoch": 0.04025899956386084, "grad_norm": NaN, "learning_rate": 0.00019789706696181518, "loss": 0.15006412267684938, "step": 1200 }, { "epoch": 0.040594491226893015, "grad_norm": NaN, "learning_rate": 0.0001978278915329275, "loss": 0.0, "step": 1210 }, { "epoch": 0.040929982889925186, "grad_norm": NaN, "learning_rate": 0.00019775871610403986, "loss": 0.032241082191467284, "step": 1220 }, { "epoch": 0.04126547455295736, "grad_norm": NaN, "learning_rate": 0.0001976895406751522, "loss": 0.8006097793579101, "step": 1230 }, { "epoch": 0.041600966215989535, "grad_norm": NaN, "learning_rate": 0.00019762036524626452, "loss": 3.051334571838379, "step": 1240 }, { "epoch": 0.041936457879021706, "grad_norm": NaN, "learning_rate": 0.00019755118981737687, "loss": 34.96420593261719, "step": 1250 }, { "epoch": 0.04227194954205388, "grad_norm": NaN, "learning_rate": 0.00019748201438848922, "loss": 6.979457092285156, "step": 1260 }, { "epoch": 0.042607441205086055, "grad_norm": NaN, "learning_rate": 0.00019741283895960158, "loss": 0.0935477614402771, "step": 1270 }, { "epoch": 0.042942932868118226, "grad_norm": NaN, "learning_rate": 0.0001973436635307139, "loss": 0.0, "step": 1280 }, { "epoch": 0.043278424531150404, "grad_norm": NaN, "learning_rate": 0.00019727448810182626, "loss": 1.5331109046936036, "step": 1290 }, { "epoch": 0.043613916194182575, "grad_norm": NaN, "learning_rate": 0.00019720531267293859, "loss": 0.0, "step": 1300 }, { "epoch": 0.043949407857214746, "grad_norm": NaN, "learning_rate": 0.00019713613724405094, "loss": 0.690937614440918, "step": 1310 }, { "epoch": 0.044284899520246924, "grad_norm": NaN, "learning_rate": 0.00019706696181516327, "loss": 8.563715362548828, "step": 1320 }, { "epoch": 0.044620391183279096, "grad_norm": NaN, "learning_rate": 0.0001969977863862756, "loss": 4.255525207519531, "step": 1330 }, { "epoch": 0.04495588284631127, "grad_norm": NaN, "learning_rate": 0.00019692861095738795, "loss": 81.31243286132812, "step": 1340 }, { "epoch": 0.045291374509343445, "grad_norm": NaN, "learning_rate": 0.00019685943552850027, "loss": 0.7501660823822022, "step": 1350 }, { "epoch": 0.045626866172375616, "grad_norm": NaN, "learning_rate": 0.00019679026009961263, "loss": 2.5992816925048827, "step": 1360 }, { "epoch": 0.04596235783540779, "grad_norm": NaN, "learning_rate": 0.00019672108467072496, "loss": 5.559530639648438, "step": 1370 }, { "epoch": 0.046297849498439965, "grad_norm": NaN, "learning_rate": 0.0001966519092418373, "loss": 1.6652551651000977, "step": 1380 }, { "epoch": 0.046633341161472136, "grad_norm": NaN, "learning_rate": 0.00019658273381294964, "loss": 0.2407153844833374, "step": 1390 }, { "epoch": 0.046968832824504314, "grad_norm": NaN, "learning_rate": 0.000196513558384062, "loss": 26.583578491210936, "step": 1400 }, { "epoch": 0.047304324487536485, "grad_norm": NaN, "learning_rate": 0.00019644438295517434, "loss": 7.983282470703125, "step": 1410 }, { "epoch": 0.047639816150568656, "grad_norm": NaN, "learning_rate": 0.00019637520752628667, "loss": 0.07818608880043029, "step": 1420 }, { "epoch": 0.047975307813600834, "grad_norm": NaN, "learning_rate": 0.00019630603209739903, "loss": 1.7374027252197266, "step": 1430 }, { "epoch": 0.048310799476633005, "grad_norm": NaN, "learning_rate": 0.00019623685666851135, "loss": 0.5990512847900391, "step": 1440 }, { "epoch": 0.048646291139665176, "grad_norm": NaN, "learning_rate": 0.0001961676812396237, "loss": 234.4718994140625, "step": 1450 }, { "epoch": 0.048981782802697355, "grad_norm": NaN, "learning_rate": 0.00019609850581073603, "loss": 9.876602935791016, "step": 1460 }, { "epoch": 0.049317274465729526, "grad_norm": NaN, "learning_rate": 0.0001960293303818484, "loss": 0.0, "step": 1470 }, { "epoch": 0.049652766128761704, "grad_norm": NaN, "learning_rate": 0.00019596015495296071, "loss": 0.11305934190750122, "step": 1480 }, { "epoch": 0.049988257791793875, "grad_norm": NaN, "learning_rate": 0.00019589097952407304, "loss": 2.2805992126464845, "step": 1490 }, { "epoch": 0.050323749454826046, "grad_norm": NaN, "learning_rate": 0.0001958218040951854, "loss": 2.134381103515625, "step": 1500 }, { "epoch": 0.050659241117858224, "grad_norm": NaN, "learning_rate": 0.00019575262866629772, "loss": 0.33266749382019045, "step": 1510 }, { "epoch": 0.050994732780890395, "grad_norm": NaN, "learning_rate": 0.00019568345323741008, "loss": 301.7185791015625, "step": 1520 }, { "epoch": 0.051330224443922566, "grad_norm": NaN, "learning_rate": 0.00019561427780852243, "loss": 158.175146484375, "step": 1530 }, { "epoch": 0.051665716106954744, "grad_norm": NaN, "learning_rate": 0.00019554510237963476, "loss": 0.3448620319366455, "step": 1540 }, { "epoch": 0.052001207769986915, "grad_norm": NaN, "learning_rate": 0.0001954759269507471, "loss": 0.07021299600601197, "step": 1550 }, { "epoch": 0.052336699433019086, "grad_norm": NaN, "learning_rate": 0.00019540675152185947, "loss": 2.3782209396362304, "step": 1560 }, { "epoch": 0.052672191096051264, "grad_norm": NaN, "learning_rate": 0.0001953375760929718, "loss": 33.55213623046875, "step": 1570 }, { "epoch": 0.053007682759083435, "grad_norm": NaN, "learning_rate": 0.00019526840066408412, "loss": 431.45224609375, "step": 1580 }, { "epoch": 0.05334317442211561, "grad_norm": NaN, "learning_rate": 0.00019519922523519647, "loss": 45.88771362304688, "step": 1590 }, { "epoch": 0.053678666085147785, "grad_norm": NaN, "learning_rate": 0.0001951300498063088, "loss": 27.831903076171876, "step": 1600 }, { "epoch": 0.054014157748179956, "grad_norm": NaN, "learning_rate": 0.00019506087437742115, "loss": 1.7415506362915039, "step": 1610 }, { "epoch": 0.054349649411212134, "grad_norm": NaN, "learning_rate": 0.00019499169894853348, "loss": 0.0, "step": 1620 }, { "epoch": 0.054685141074244305, "grad_norm": NaN, "learning_rate": 0.00019492252351964584, "loss": 23.286405944824217, "step": 1630 }, { "epoch": 0.055020632737276476, "grad_norm": NaN, "learning_rate": 0.00019485334809075816, "loss": 0.0, "step": 1640 }, { "epoch": 0.055356124400308654, "grad_norm": NaN, "learning_rate": 0.00019478417266187052, "loss": 42.256170654296874, "step": 1650 }, { "epoch": 0.055691616063340825, "grad_norm": NaN, "learning_rate": 0.00019471499723298284, "loss": 0.09685954451560974, "step": 1660 }, { "epoch": 0.056027107726373, "grad_norm": NaN, "learning_rate": 0.0001946458218040952, "loss": 30.406533813476564, "step": 1670 }, { "epoch": 0.056362599389405174, "grad_norm": NaN, "learning_rate": 0.00019457664637520755, "loss": 6.177334594726562, "step": 1680 }, { "epoch": 0.056698091052437345, "grad_norm": NaN, "learning_rate": 0.00019450747094631988, "loss": 1.717080307006836, "step": 1690 }, { "epoch": 0.05703358271546952, "grad_norm": NaN, "learning_rate": 0.00019443829551743223, "loss": 16.319992065429688, "step": 1700 }, { "epoch": 0.057369074378501694, "grad_norm": NaN, "learning_rate": 0.00019436912008854456, "loss": 1.2412324905395509, "step": 1710 }, { "epoch": 0.057704566041533865, "grad_norm": NaN, "learning_rate": 0.0001942999446596569, "loss": 0.0, "step": 1720 }, { "epoch": 0.05804005770456604, "grad_norm": NaN, "learning_rate": 0.00019423076923076924, "loss": 16.714073181152344, "step": 1730 }, { "epoch": 0.058375549367598215, "grad_norm": NaN, "learning_rate": 0.0001941615938018816, "loss": 4.676777648925781, "step": 1740 }, { "epoch": 0.058711041030630386, "grad_norm": NaN, "learning_rate": 0.00019409241837299392, "loss": 0.1248945951461792, "step": 1750 }, { "epoch": 0.059046532693662564, "grad_norm": NaN, "learning_rate": 0.00019402324294410625, "loss": 0.0, "step": 1760 }, { "epoch": 0.059382024356694735, "grad_norm": NaN, "learning_rate": 0.0001939540675152186, "loss": 1.0300786972045899, "step": 1770 }, { "epoch": 0.05971751601972691, "grad_norm": NaN, "learning_rate": 0.00019388489208633093, "loss": 159.32357177734374, "step": 1780 }, { "epoch": 0.060053007682759084, "grad_norm": NaN, "learning_rate": 0.00019381571665744328, "loss": 0.1012919545173645, "step": 1790 }, { "epoch": 0.060388499345791255, "grad_norm": NaN, "learning_rate": 0.0001937465412285556, "loss": 1.9244558334350585, "step": 1800 }, { "epoch": 0.06072399100882343, "grad_norm": NaN, "learning_rate": 0.00019367736579966796, "loss": 18.52349853515625, "step": 1810 }, { "epoch": 0.061059482671855604, "grad_norm": NaN, "learning_rate": 0.00019360819037078032, "loss": 0.1813188076019287, "step": 1820 }, { "epoch": 0.061394974334887775, "grad_norm": NaN, "learning_rate": 0.00019353901494189264, "loss": 0.1522122859954834, "step": 1830 }, { "epoch": 0.06173046599791995, "grad_norm": NaN, "learning_rate": 0.000193469839513005, "loss": 8.574814605712891, "step": 1840 }, { "epoch": 0.062065957660952124, "grad_norm": NaN, "learning_rate": 0.00019340066408411733, "loss": 93.5122314453125, "step": 1850 }, { "epoch": 0.0624014493239843, "grad_norm": NaN, "learning_rate": 0.00019333148865522968, "loss": 2.2591997146606446, "step": 1860 }, { "epoch": 0.06273694098701647, "grad_norm": NaN, "learning_rate": 0.000193262313226342, "loss": 0.40584664344787597, "step": 1870 }, { "epoch": 0.06307243265004865, "grad_norm": NaN, "learning_rate": 0.00019319313779745436, "loss": 113.88292236328125, "step": 1880 }, { "epoch": 0.06340792431308082, "grad_norm": NaN, "learning_rate": 0.0001931239623685667, "loss": 9.488602447509766, "step": 1890 }, { "epoch": 0.063743415976113, "grad_norm": NaN, "learning_rate": 0.00019305478693967904, "loss": 0.36140780448913573, "step": 1900 }, { "epoch": 0.06407890763914517, "grad_norm": NaN, "learning_rate": 0.00019298561151079137, "loss": 0.5006577014923096, "step": 1910 }, { "epoch": 0.06441439930217734, "grad_norm": NaN, "learning_rate": 0.0001929164360819037, "loss": 5.155010604858399, "step": 1920 }, { "epoch": 0.06474989096520951, "grad_norm": NaN, "learning_rate": 0.00019284726065301605, "loss": 2.3952762603759767, "step": 1930 }, { "epoch": 0.06508538262824169, "grad_norm": NaN, "learning_rate": 0.0001927780852241284, "loss": 142.20489501953125, "step": 1940 }, { "epoch": 0.06542087429127386, "grad_norm": NaN, "learning_rate": 0.00019270890979524076, "loss": 5.1668048858642575, "step": 1950 }, { "epoch": 0.06575636595430603, "grad_norm": NaN, "learning_rate": 0.00019263973436635308, "loss": 2.7092329025268556, "step": 1960 }, { "epoch": 0.06609185761733821, "grad_norm": NaN, "learning_rate": 0.00019257055893746544, "loss": 62.072442626953126, "step": 1970 }, { "epoch": 0.06642734928037038, "grad_norm": NaN, "learning_rate": 0.00019250138350857777, "loss": 1.7524122238159179, "step": 1980 }, { "epoch": 0.06676284094340255, "grad_norm": NaN, "learning_rate": 0.00019243220807969012, "loss": 34.05416564941406, "step": 1990 }, { "epoch": 0.06709833260643473, "grad_norm": NaN, "learning_rate": 0.00019236303265080245, "loss": 0.31617584228515627, "step": 2000 } ], "logging_steps": 10, "max_steps": 29807, "num_input_tokens_seen": 0, "num_train_epochs": 1, "save_steps": 500, "stateful_callbacks": { "TrainerControl": { "args": { "should_epoch_stop": false, "should_evaluate": false, "should_log": false, "should_save": true, "should_training_stop": false }, "attributes": {} } }, "total_flos": 8.087844508096848e+16, "train_batch_size": 1, "trial_name": null, "trial_params": null }