{ "best_global_step": 4980, "best_metric": 0.8463534876410834, "best_model_checkpoint": "modernbert-llm-router/checkpoint-4980", "epoch": 10.0, "eval_steps": 500, "global_step": 4980, "is_hyper_param_search": false, "is_local_process_zero": true, "is_world_process_zero": true, "log_history": [ { "epoch": 0.020090406830738324, "grad_norm": 67.4950942993164, "learning_rate": 9.036144578313253e-07, "loss": 11.30099105834961, "step": 10 }, { "epoch": 0.04018081366147665, "grad_norm": 35.74208450317383, "learning_rate": 1.9076305220883537e-06, "loss": 11.624376678466797, "step": 20 }, { "epoch": 0.06027122049221497, "grad_norm": 124.8450698852539, "learning_rate": 2.911646586345382e-06, "loss": 11.913236999511719, "step": 30 }, { "epoch": 0.0803616273229533, "grad_norm": 139.30108642578125, "learning_rate": 3.91566265060241e-06, "loss": 11.9268798828125, "step": 40 }, { "epoch": 0.10045203415369161, "grad_norm": 56.38514709472656, "learning_rate": 4.919678714859438e-06, "loss": 11.812648010253906, "step": 50 }, { "epoch": 0.12054244098442994, "grad_norm": 46.214725494384766, "learning_rate": 5.9236947791164665e-06, "loss": 11.75150146484375, "step": 60 }, { "epoch": 0.14063284781516824, "grad_norm": 39.07476806640625, "learning_rate": 6.927710843373494e-06, "loss": 11.663333129882812, "step": 70 }, { "epoch": 0.1607232546459066, "grad_norm": 89.72721099853516, "learning_rate": 7.931726907630523e-06, "loss": 11.748873138427735, "step": 80 }, { "epoch": 0.1808136614766449, "grad_norm": 76.43763732910156, "learning_rate": 8.93574297188755e-06, "loss": 11.390589904785156, "step": 90 }, { "epoch": 0.20090406830738322, "grad_norm": 113.93096160888672, "learning_rate": 9.939759036144579e-06, "loss": 11.199761962890625, "step": 100 }, { "epoch": 0.22099447513812154, "grad_norm": 47.393863677978516, "learning_rate": 1.0943775100401607e-05, "loss": 11.138442993164062, "step": 110 }, { "epoch": 0.24108488196885988, "grad_norm": 38.745670318603516, "learning_rate": 1.1947791164658636e-05, "loss": 11.002056121826172, "step": 120 }, { "epoch": 0.26117528879959817, "grad_norm": 44.2335319519043, "learning_rate": 1.2951807228915663e-05, "loss": 10.726869201660156, "step": 130 }, { "epoch": 0.2812656956303365, "grad_norm": 69.25237274169922, "learning_rate": 1.395582329317269e-05, "loss": 10.937381744384766, "step": 140 }, { "epoch": 0.30135610246107486, "grad_norm": 37.501251220703125, "learning_rate": 1.495983935742972e-05, "loss": 10.933692932128906, "step": 150 }, { "epoch": 0.3214465092918132, "grad_norm": 44.67572784423828, "learning_rate": 1.5963855421686745e-05, "loss": 10.68414535522461, "step": 160 }, { "epoch": 0.3415369161225515, "grad_norm": 94.95555877685547, "learning_rate": 1.6967871485943776e-05, "loss": 10.574811553955078, "step": 170 }, { "epoch": 0.3616273229532898, "grad_norm": 61.77016067504883, "learning_rate": 1.7971887550200802e-05, "loss": 10.465885162353516, "step": 180 }, { "epoch": 0.3817177297840281, "grad_norm": 62.27002716064453, "learning_rate": 1.8975903614457833e-05, "loss": 10.8569091796875, "step": 190 }, { "epoch": 0.40180813661476644, "grad_norm": 44.70588684082031, "learning_rate": 1.997991967871486e-05, "loss": 10.475724792480468, "step": 200 }, { "epoch": 0.42189854344550476, "grad_norm": 48.619590759277344, "learning_rate": 2.098393574297189e-05, "loss": 10.236911010742187, "step": 210 }, { "epoch": 0.4419889502762431, "grad_norm": 54.244956970214844, "learning_rate": 2.1987951807228917e-05, "loss": 10.250703430175781, "step": 220 }, { "epoch": 0.4620793571069814, "grad_norm": 35.33909225463867, "learning_rate": 2.2991967871485944e-05, "loss": 9.963737487792969, "step": 230 }, { "epoch": 0.48216976393771976, "grad_norm": 50.2829704284668, "learning_rate": 2.399598393574297e-05, "loss": 9.986483001708985, "step": 240 }, { "epoch": 0.5022601707684581, "grad_norm": 41.656951904296875, "learning_rate": 2.5e-05, "loss": 9.945632934570312, "step": 250 }, { "epoch": 0.5223505775991963, "grad_norm": 50.9932746887207, "learning_rate": 2.600401606425703e-05, "loss": 9.356922149658203, "step": 260 }, { "epoch": 0.5424409844299347, "grad_norm": 44.50615692138672, "learning_rate": 2.7008032128514062e-05, "loss": 9.761817169189452, "step": 270 }, { "epoch": 0.562531391260673, "grad_norm": 60.5576057434082, "learning_rate": 2.8012048192771085e-05, "loss": 9.114958190917969, "step": 280 }, { "epoch": 0.5826217980914113, "grad_norm": 49.95737838745117, "learning_rate": 2.9016064257028112e-05, "loss": 9.187503051757812, "step": 290 }, { "epoch": 0.6027122049221497, "grad_norm": 40.03938293457031, "learning_rate": 3.0020080321285143e-05, "loss": 9.588552093505859, "step": 300 }, { "epoch": 0.622802611752888, "grad_norm": 31.86073875427246, "learning_rate": 3.102409638554217e-05, "loss": 8.846249389648438, "step": 310 }, { "epoch": 0.6428930185836264, "grad_norm": 27.552488327026367, "learning_rate": 3.20281124497992e-05, "loss": 9.372589111328125, "step": 320 }, { "epoch": 0.6629834254143646, "grad_norm": 75.73005676269531, "learning_rate": 3.303212851405623e-05, "loss": 9.259957122802735, "step": 330 }, { "epoch": 0.683073832245103, "grad_norm": 39.76576614379883, "learning_rate": 3.4036144578313254e-05, "loss": 8.952153778076172, "step": 340 }, { "epoch": 0.7031642390758412, "grad_norm": 34.058433532714844, "learning_rate": 3.504016064257029e-05, "loss": 8.938674926757812, "step": 350 }, { "epoch": 0.7232546459065796, "grad_norm": 45.72063064575195, "learning_rate": 3.604417670682731e-05, "loss": 9.18985824584961, "step": 360 }, { "epoch": 0.7433450527373179, "grad_norm": 44.90036392211914, "learning_rate": 3.704819277108434e-05, "loss": 8.677542877197265, "step": 370 }, { "epoch": 0.7634354595680563, "grad_norm": 32.45265197753906, "learning_rate": 3.805220883534137e-05, "loss": 8.847957611083984, "step": 380 }, { "epoch": 0.7835258663987946, "grad_norm": 35.051700592041016, "learning_rate": 3.9056224899598395e-05, "loss": 8.041068267822265, "step": 390 }, { "epoch": 0.8036162732295329, "grad_norm": 23.613466262817383, "learning_rate": 4.006024096385542e-05, "loss": 8.380730438232423, "step": 400 }, { "epoch": 0.8237066800602713, "grad_norm": 49.00188446044922, "learning_rate": 4.106425702811245e-05, "loss": 8.580660247802735, "step": 410 }, { "epoch": 0.8437970868910095, "grad_norm": 41.14157485961914, "learning_rate": 4.206827309236948e-05, "loss": 8.429288482666015, "step": 420 }, { "epoch": 0.8638874937217479, "grad_norm": 33.39979553222656, "learning_rate": 4.307228915662651e-05, "loss": 8.59649887084961, "step": 430 }, { "epoch": 0.8839779005524862, "grad_norm": 99.59103393554688, "learning_rate": 4.407630522088354e-05, "loss": 8.490008544921874, "step": 440 }, { "epoch": 0.9040683073832245, "grad_norm": 32.883426666259766, "learning_rate": 4.5080321285140564e-05, "loss": 8.39789276123047, "step": 450 }, { "epoch": 0.9241587142139628, "grad_norm": 37.05418395996094, "learning_rate": 4.608433734939759e-05, "loss": 8.002466583251953, "step": 460 }, { "epoch": 0.9442491210447012, "grad_norm": 60.73507308959961, "learning_rate": 4.7088353413654624e-05, "loss": 8.742173767089843, "step": 470 }, { "epoch": 0.9643395278754395, "grad_norm": 54.933067321777344, "learning_rate": 4.8092369477911644e-05, "loss": 7.934970855712891, "step": 480 }, { "epoch": 0.9844299347061778, "grad_norm": 22.610998153686523, "learning_rate": 4.909638554216868e-05, "loss": 7.596905517578125, "step": 490 }, { "epoch": 1.0, "eval_accuracy": 0.7670682730923695, "eval_f1": 0.7665146369158211, "eval_loss": 0.5159338712692261, "eval_runtime": 338.3534, "eval_samples_per_second": 11.775, "eval_steps_per_second": 5.887, "step": 498 }, { "epoch": 1.0040180813661477, "grad_norm": 30.076736450195312, "learning_rate": 4.99888442659527e-05, "loss": 7.928907012939453, "step": 500 }, { "epoch": 1.024108488196886, "grad_norm": 27.150625228881836, "learning_rate": 4.98772869254797e-05, "loss": 7.893730163574219, "step": 510 }, { "epoch": 1.0441988950276242, "grad_norm": 43.56063461303711, "learning_rate": 4.9765729585006696e-05, "loss": 7.6407928466796875, "step": 520 }, { "epoch": 1.0642893018583626, "grad_norm": 37.67859649658203, "learning_rate": 4.9654172244533695e-05, "loss": 8.078261566162109, "step": 530 }, { "epoch": 1.084379708689101, "grad_norm": 38.437652587890625, "learning_rate": 4.9542614904060695e-05, "loss": 7.557135772705078, "step": 540 }, { "epoch": 1.1044701155198393, "grad_norm": 33.14951705932617, "learning_rate": 4.943105756358769e-05, "loss": 7.886659240722656, "step": 550 }, { "epoch": 1.1245605223505777, "grad_norm": 27.673179626464844, "learning_rate": 4.9319500223114686e-05, "loss": 7.672040557861328, "step": 560 }, { "epoch": 1.1446509291813158, "grad_norm": 30.745512008666992, "learning_rate": 4.920794288264168e-05, "loss": 7.915995025634766, "step": 570 }, { "epoch": 1.1647413360120542, "grad_norm": 86.4283218383789, "learning_rate": 4.909638554216868e-05, "loss": 7.516211700439453, "step": 580 }, { "epoch": 1.1848317428427926, "grad_norm": 25.24470329284668, "learning_rate": 4.898482820169568e-05, "loss": 7.094333648681641, "step": 590 }, { "epoch": 1.204922149673531, "grad_norm": 23.994327545166016, "learning_rate": 4.887327086122267e-05, "loss": 7.318421936035156, "step": 600 }, { "epoch": 1.2250125565042693, "grad_norm": 42.44085693359375, "learning_rate": 4.876171352074967e-05, "loss": 7.235833740234375, "step": 610 }, { "epoch": 1.2451029633350075, "grad_norm": 46.6234016418457, "learning_rate": 4.865015618027666e-05, "loss": 7.330026245117187, "step": 620 }, { "epoch": 1.2651933701657458, "grad_norm": 81.48997497558594, "learning_rate": 4.853859883980366e-05, "loss": 6.9850341796875, "step": 630 }, { "epoch": 1.2852837769964842, "grad_norm": 31.492443084716797, "learning_rate": 4.842704149933066e-05, "loss": 7.5037284851074215, "step": 640 }, { "epoch": 1.3053741838272224, "grad_norm": 37.36494827270508, "learning_rate": 4.831548415885765e-05, "loss": 7.257170104980469, "step": 650 }, { "epoch": 1.325464590657961, "grad_norm": 61.79890823364258, "learning_rate": 4.820392681838465e-05, "loss": 6.9138031005859375, "step": 660 }, { "epoch": 1.3455549974886991, "grad_norm": 33.589534759521484, "learning_rate": 4.8092369477911644e-05, "loss": 6.862760162353515, "step": 670 }, { "epoch": 1.3656454043194375, "grad_norm": 42.413116455078125, "learning_rate": 4.7980812137438644e-05, "loss": 6.8927162170410154, "step": 680 }, { "epoch": 1.3857358111501759, "grad_norm": 45.523651123046875, "learning_rate": 4.786925479696564e-05, "loss": 7.35535888671875, "step": 690 }, { "epoch": 1.405826217980914, "grad_norm": 22.36736297607422, "learning_rate": 4.775769745649264e-05, "loss": 6.857536315917969, "step": 700 }, { "epoch": 1.4259166248116524, "grad_norm": 26.58713722229004, "learning_rate": 4.764614011601964e-05, "loss": 7.037255096435547, "step": 710 }, { "epoch": 1.4460070316423907, "grad_norm": 53.9232292175293, "learning_rate": 4.7534582775546634e-05, "loss": 7.396176147460937, "step": 720 }, { "epoch": 1.4660974384731291, "grad_norm": 74.64452362060547, "learning_rate": 4.742302543507363e-05, "loss": 7.3621162414550785, "step": 730 }, { "epoch": 1.4861878453038675, "grad_norm": 21.768842697143555, "learning_rate": 4.7311468094600626e-05, "loss": 7.139886474609375, "step": 740 }, { "epoch": 1.5062782521346056, "grad_norm": 22.915559768676758, "learning_rate": 4.7199910754127625e-05, "loss": 6.710366058349609, "step": 750 }, { "epoch": 1.526368658965344, "grad_norm": 50.81713104248047, "learning_rate": 4.7088353413654624e-05, "loss": 7.143299102783203, "step": 760 }, { "epoch": 1.5464590657960824, "grad_norm": 21.456253051757812, "learning_rate": 4.697679607318162e-05, "loss": 6.581459045410156, "step": 770 }, { "epoch": 1.5665494726268205, "grad_norm": 51.19502639770508, "learning_rate": 4.6865238732708616e-05, "loss": 6.778679656982422, "step": 780 }, { "epoch": 1.5866398794575591, "grad_norm": 15.50610637664795, "learning_rate": 4.675368139223561e-05, "loss": 6.736427307128906, "step": 790 }, { "epoch": 1.6067302862882973, "grad_norm": 24.18048095703125, "learning_rate": 4.664212405176261e-05, "loss": 6.704109954833984, "step": 800 }, { "epoch": 1.6268206931190357, "grad_norm": 55.495052337646484, "learning_rate": 4.65305667112896e-05, "loss": 6.363135910034179, "step": 810 }, { "epoch": 1.646911099949774, "grad_norm": 47.925350189208984, "learning_rate": 4.64190093708166e-05, "loss": 6.810108184814453, "step": 820 }, { "epoch": 1.6670015067805122, "grad_norm": 54.57836151123047, "learning_rate": 4.63074520303436e-05, "loss": 7.001818084716797, "step": 830 }, { "epoch": 1.6870919136112508, "grad_norm": 27.17943000793457, "learning_rate": 4.619589468987059e-05, "loss": 6.451213836669922, "step": 840 }, { "epoch": 1.707182320441989, "grad_norm": 29.18775749206543, "learning_rate": 4.608433734939759e-05, "loss": 6.075239562988282, "step": 850 }, { "epoch": 1.7272727272727273, "grad_norm": 100.36605834960938, "learning_rate": 4.597278000892459e-05, "loss": 6.098962783813477, "step": 860 }, { "epoch": 1.7473631341034657, "grad_norm": 46.559486389160156, "learning_rate": 4.586122266845159e-05, "loss": 7.3000633239746096, "step": 870 }, { "epoch": 1.7674535409342038, "grad_norm": 55.62862014770508, "learning_rate": 4.574966532797859e-05, "loss": 6.430718231201172, "step": 880 }, { "epoch": 1.7875439477649422, "grad_norm": 40.10306167602539, "learning_rate": 4.563810798750558e-05, "loss": 6.49133071899414, "step": 890 }, { "epoch": 1.8076343545956806, "grad_norm": 26.214754104614258, "learning_rate": 4.552655064703258e-05, "loss": 6.711282348632812, "step": 900 }, { "epoch": 1.827724761426419, "grad_norm": 20.552804946899414, "learning_rate": 4.541499330655957e-05, "loss": 7.12545166015625, "step": 910 }, { "epoch": 1.8478151682571573, "grad_norm": 15.887333869934082, "learning_rate": 4.530343596608657e-05, "loss": 6.991852569580078, "step": 920 }, { "epoch": 1.8679055750878955, "grad_norm": 41.746009826660156, "learning_rate": 4.5191878625613564e-05, "loss": 6.388395690917969, "step": 930 }, { "epoch": 1.8879959819186338, "grad_norm": 60.416690826416016, "learning_rate": 4.5080321285140564e-05, "loss": 6.510835266113281, "step": 940 }, { "epoch": 1.9080863887493722, "grad_norm": 52.52122497558594, "learning_rate": 4.496876394466756e-05, "loss": 6.274535369873047, "step": 950 }, { "epoch": 1.9281767955801103, "grad_norm": 40.41902542114258, "learning_rate": 4.4857206604194555e-05, "loss": 6.65899887084961, "step": 960 }, { "epoch": 1.948267202410849, "grad_norm": 50.44690704345703, "learning_rate": 4.4745649263721555e-05, "loss": 6.682839202880859, "step": 970 }, { "epoch": 1.968357609241587, "grad_norm": 28.226612091064453, "learning_rate": 4.463409192324855e-05, "loss": 6.098558807373047, "step": 980 }, { "epoch": 1.9884480160723255, "grad_norm": 42.85635757446289, "learning_rate": 4.4522534582775546e-05, "loss": 6.307109832763672, "step": 990 }, { "epoch": 2.0, "eval_accuracy": 0.8049698795180723, "eval_f1": 0.8047252856433185, "eval_loss": 0.43348565697669983, "eval_runtime": 299.1884, "eval_samples_per_second": 13.316, "eval_steps_per_second": 6.658, "step": 996 }, { "epoch": 2.0080361627322953, "grad_norm": 18.02980613708496, "learning_rate": 4.4410977242302546e-05, "loss": 6.029669570922851, "step": 1000 }, { "epoch": 2.0281265695630335, "grad_norm": 42.156864166259766, "learning_rate": 4.4299419901829545e-05, "loss": 6.159435272216797, "step": 1010 }, { "epoch": 2.048216976393772, "grad_norm": 25.99110221862793, "learning_rate": 4.4187862561356544e-05, "loss": 6.365954208374023, "step": 1020 }, { "epoch": 2.0683073832245102, "grad_norm": 30.346057891845703, "learning_rate": 4.407630522088354e-05, "loss": 6.770087432861328, "step": 1030 }, { "epoch": 2.0883977900552484, "grad_norm": 26.053958892822266, "learning_rate": 4.3964747880410536e-05, "loss": 5.629564666748047, "step": 1040 }, { "epoch": 2.108488196885987, "grad_norm": 35.44384765625, "learning_rate": 4.385319053993753e-05, "loss": 7.135092926025391, "step": 1050 }, { "epoch": 2.128578603716725, "grad_norm": 74.50113677978516, "learning_rate": 4.374163319946453e-05, "loss": 6.596900177001953, "step": 1060 }, { "epoch": 2.1486690105474637, "grad_norm": 25.986236572265625, "learning_rate": 4.363007585899153e-05, "loss": 6.268881988525391, "step": 1070 }, { "epoch": 2.168759417378202, "grad_norm": 28.2646541595459, "learning_rate": 4.351851851851852e-05, "loss": 6.352067184448242, "step": 1080 }, { "epoch": 2.18884982420894, "grad_norm": 26.6820068359375, "learning_rate": 4.340696117804552e-05, "loss": 5.82037582397461, "step": 1090 }, { "epoch": 2.2089402310396786, "grad_norm": 41.59135055541992, "learning_rate": 4.329540383757251e-05, "loss": 5.902550888061524, "step": 1100 }, { "epoch": 2.2290306378704168, "grad_norm": 20.264556884765625, "learning_rate": 4.318384649709951e-05, "loss": 6.314144134521484, "step": 1110 }, { "epoch": 2.2491210447011554, "grad_norm": 18.953853607177734, "learning_rate": 4.307228915662651e-05, "loss": 5.690468978881836, "step": 1120 }, { "epoch": 2.2692114515318935, "grad_norm": 43.699649810791016, "learning_rate": 4.29607318161535e-05, "loss": 5.427518081665039, "step": 1130 }, { "epoch": 2.2893018583626317, "grad_norm": 21.426782608032227, "learning_rate": 4.28491744756805e-05, "loss": 5.6670886993408205, "step": 1140 }, { "epoch": 2.3093922651933703, "grad_norm": 31.70428466796875, "learning_rate": 4.2737617135207494e-05, "loss": 6.703258514404297, "step": 1150 }, { "epoch": 2.3294826720241084, "grad_norm": 27.911863327026367, "learning_rate": 4.262605979473449e-05, "loss": 5.849753189086914, "step": 1160 }, { "epoch": 2.3495730788548466, "grad_norm": 57.702880859375, "learning_rate": 4.251450245426149e-05, "loss": 5.396737289428711, "step": 1170 }, { "epoch": 2.369663485685585, "grad_norm": 42.24098587036133, "learning_rate": 4.240294511378849e-05, "loss": 6.970297241210938, "step": 1180 }, { "epoch": 2.3897538925163233, "grad_norm": 34.87739181518555, "learning_rate": 4.229138777331549e-05, "loss": 6.024194717407227, "step": 1190 }, { "epoch": 2.409844299347062, "grad_norm": 34.56913375854492, "learning_rate": 4.2179830432842484e-05, "loss": 7.1401222229003904, "step": 1200 }, { "epoch": 2.4299347061778, "grad_norm": 31.022424697875977, "learning_rate": 4.206827309236948e-05, "loss": 5.916114044189453, "step": 1210 }, { "epoch": 2.4500251130085386, "grad_norm": 32.2326774597168, "learning_rate": 4.1956715751896475e-05, "loss": 5.544026565551758, "step": 1220 }, { "epoch": 2.470115519839277, "grad_norm": 67.76956176757812, "learning_rate": 4.1845158411423475e-05, "loss": 6.099757385253906, "step": 1230 }, { "epoch": 2.490205926670015, "grad_norm": 24.727947235107422, "learning_rate": 4.1733601070950474e-05, "loss": 5.961135482788086, "step": 1240 }, { "epoch": 2.5102963335007535, "grad_norm": 45.534976959228516, "learning_rate": 4.1622043730477466e-05, "loss": 5.8507640838623045, "step": 1250 }, { "epoch": 2.5303867403314917, "grad_norm": 36.52798080444336, "learning_rate": 4.1510486390004466e-05, "loss": 6.213993835449219, "step": 1260 }, { "epoch": 2.55047714716223, "grad_norm": 29.7322998046875, "learning_rate": 4.139892904953146e-05, "loss": 6.422627258300781, "step": 1270 }, { "epoch": 2.5705675539929684, "grad_norm": 87.98380279541016, "learning_rate": 4.128737170905846e-05, "loss": 5.8346599578857425, "step": 1280 }, { "epoch": 2.5906579608237066, "grad_norm": 46.31199264526367, "learning_rate": 4.117581436858545e-05, "loss": 6.729044342041016, "step": 1290 }, { "epoch": 2.6107483676544447, "grad_norm": 22.86014175415039, "learning_rate": 4.106425702811245e-05, "loss": 6.123567199707031, "step": 1300 }, { "epoch": 2.6308387744851833, "grad_norm": 45.6070556640625, "learning_rate": 4.095269968763945e-05, "loss": 5.360657119750977, "step": 1310 }, { "epoch": 2.650929181315922, "grad_norm": 39.19569396972656, "learning_rate": 4.084114234716645e-05, "loss": 6.517160034179687, "step": 1320 }, { "epoch": 2.67101958814666, "grad_norm": 36.43268585205078, "learning_rate": 4.072958500669345e-05, "loss": 6.326155471801758, "step": 1330 }, { "epoch": 2.6911099949773982, "grad_norm": 23.42853355407715, "learning_rate": 4.061802766622044e-05, "loss": 5.638162231445312, "step": 1340 }, { "epoch": 2.711200401808137, "grad_norm": 22.37718391418457, "learning_rate": 4.050647032574744e-05, "loss": 5.6496532440185545, "step": 1350 }, { "epoch": 2.731290808638875, "grad_norm": 64.77632904052734, "learning_rate": 4.039491298527444e-05, "loss": 6.058899688720703, "step": 1360 }, { "epoch": 2.751381215469613, "grad_norm": 22.800050735473633, "learning_rate": 4.028335564480143e-05, "loss": 5.7602485656738285, "step": 1370 }, { "epoch": 2.7714716223003517, "grad_norm": 28.1535587310791, "learning_rate": 4.017179830432843e-05, "loss": 5.900847625732422, "step": 1380 }, { "epoch": 2.79156202913109, "grad_norm": 27.592967987060547, "learning_rate": 4.006024096385542e-05, "loss": 5.556166458129883, "step": 1390 }, { "epoch": 2.811652435961828, "grad_norm": 13.690511703491211, "learning_rate": 3.994868362338242e-05, "loss": 5.470177078247071, "step": 1400 }, { "epoch": 2.8317428427925666, "grad_norm": 27.636857986450195, "learning_rate": 3.9837126282909414e-05, "loss": 5.946683120727539, "step": 1410 }, { "epoch": 2.8518332496233048, "grad_norm": 22.8720760345459, "learning_rate": 3.972556894243641e-05, "loss": 6.123848724365234, "step": 1420 }, { "epoch": 2.8719236564540433, "grad_norm": 31.31513023376465, "learning_rate": 3.961401160196341e-05, "loss": 5.350670623779297, "step": 1430 }, { "epoch": 2.8920140632847815, "grad_norm": 25.95108985900879, "learning_rate": 3.9502454261490405e-05, "loss": 5.712937545776367, "step": 1440 }, { "epoch": 2.91210447011552, "grad_norm": 55.22339630126953, "learning_rate": 3.9390896921017404e-05, "loss": 5.576626205444336, "step": 1450 }, { "epoch": 2.9321948769462582, "grad_norm": 22.332138061523438, "learning_rate": 3.92793395805444e-05, "loss": 5.735363388061524, "step": 1460 }, { "epoch": 2.9522852837769964, "grad_norm": 30.75307273864746, "learning_rate": 3.9167782240071396e-05, "loss": 6.044792556762696, "step": 1470 }, { "epoch": 2.972375690607735, "grad_norm": 37.25911331176758, "learning_rate": 3.9056224899598395e-05, "loss": 5.390208053588867, "step": 1480 }, { "epoch": 2.992466097438473, "grad_norm": 19.11253547668457, "learning_rate": 3.8944667559125395e-05, "loss": 6.361589431762695, "step": 1490 }, { "epoch": 3.0, "eval_accuracy": 0.8275602409638554, "eval_f1": 0.8274702273547456, "eval_loss": 0.39785367250442505, "eval_runtime": 261.3856, "eval_samples_per_second": 15.242, "eval_steps_per_second": 7.621, "step": 1494 }, { "epoch": 3.012054244098443, "grad_norm": 29.47568702697754, "learning_rate": 3.8833110218652394e-05, "loss": 5.428952407836914, "step": 1500 }, { "epoch": 3.0321446509291814, "grad_norm": 24.7688045501709, "learning_rate": 3.8721552878179386e-05, "loss": 5.720760345458984, "step": 1510 }, { "epoch": 3.0522350577599195, "grad_norm": 16.392057418823242, "learning_rate": 3.8609995537706386e-05, "loss": 5.032233047485351, "step": 1520 }, { "epoch": 3.072325464590658, "grad_norm": 86.99443817138672, "learning_rate": 3.849843819723338e-05, "loss": 5.509403228759766, "step": 1530 }, { "epoch": 3.0924158714213963, "grad_norm": 23.566726684570312, "learning_rate": 3.838688085676038e-05, "loss": 5.087054061889648, "step": 1540 }, { "epoch": 3.1125062782521344, "grad_norm": 77.42285919189453, "learning_rate": 3.8275323516287377e-05, "loss": 5.9715118408203125, "step": 1550 }, { "epoch": 3.132596685082873, "grad_norm": 12.615682601928711, "learning_rate": 3.816376617581437e-05, "loss": 5.37689437866211, "step": 1560 }, { "epoch": 3.152687091913611, "grad_norm": 12.577225685119629, "learning_rate": 3.805220883534137e-05, "loss": 5.694247436523438, "step": 1570 }, { "epoch": 3.1727774987443498, "grad_norm": 55.27588653564453, "learning_rate": 3.794065149486836e-05, "loss": 6.124555206298828, "step": 1580 }, { "epoch": 3.192867905575088, "grad_norm": 13.139041900634766, "learning_rate": 3.782909415439536e-05, "loss": 6.096420669555664, "step": 1590 }, { "epoch": 3.212958312405826, "grad_norm": 18.4031982421875, "learning_rate": 3.771753681392236e-05, "loss": 5.371559906005859, "step": 1600 }, { "epoch": 3.2330487192365647, "grad_norm": 25.290729522705078, "learning_rate": 3.760597947344935e-05, "loss": 5.954509735107422, "step": 1610 }, { "epoch": 3.253139126067303, "grad_norm": 57.6512451171875, "learning_rate": 3.749442213297635e-05, "loss": 5.709614181518555, "step": 1620 }, { "epoch": 3.273229532898041, "grad_norm": 70.0116958618164, "learning_rate": 3.738286479250335e-05, "loss": 5.772966003417968, "step": 1630 }, { "epoch": 3.2933199397287796, "grad_norm": 81.4374008178711, "learning_rate": 3.727130745203035e-05, "loss": 5.014947509765625, "step": 1640 }, { "epoch": 3.3134103465595177, "grad_norm": 27.316287994384766, "learning_rate": 3.715975011155734e-05, "loss": 5.662544631958008, "step": 1650 }, { "epoch": 3.3335007533902563, "grad_norm": 36.81215286254883, "learning_rate": 3.704819277108434e-05, "loss": 5.530815505981446, "step": 1660 }, { "epoch": 3.3535911602209945, "grad_norm": 23.90372085571289, "learning_rate": 3.693663543061134e-05, "loss": 5.7403514862060545, "step": 1670 }, { "epoch": 3.3736815670517326, "grad_norm": 27.02726173400879, "learning_rate": 3.682507809013833e-05, "loss": 5.826567840576172, "step": 1680 }, { "epoch": 3.393771973882471, "grad_norm": 48.38102722167969, "learning_rate": 3.671352074966533e-05, "loss": 5.291037750244141, "step": 1690 }, { "epoch": 3.4138623807132094, "grad_norm": 30.439931869506836, "learning_rate": 3.6601963409192325e-05, "loss": 5.683506774902344, "step": 1700 }, { "epoch": 3.433952787543948, "grad_norm": 17.58039665222168, "learning_rate": 3.6490406068719324e-05, "loss": 5.402456283569336, "step": 1710 }, { "epoch": 3.454043194374686, "grad_norm": 50.540428161621094, "learning_rate": 3.6378848728246323e-05, "loss": 5.341756057739258, "step": 1720 }, { "epoch": 3.4741336012054242, "grad_norm": 35.1678352355957, "learning_rate": 3.6267291387773316e-05, "loss": 5.54007568359375, "step": 1730 }, { "epoch": 3.494224008036163, "grad_norm": 52.99409484863281, "learning_rate": 3.6155734047300315e-05, "loss": 5.751492309570312, "step": 1740 }, { "epoch": 3.514314414866901, "grad_norm": 43.16945266723633, "learning_rate": 3.604417670682731e-05, "loss": 7.202930450439453, "step": 1750 }, { "epoch": 3.534404821697639, "grad_norm": 33.9586296081543, "learning_rate": 3.593261936635431e-05, "loss": 5.380310821533203, "step": 1760 }, { "epoch": 3.5544952285283777, "grad_norm": 22.890636444091797, "learning_rate": 3.58210620258813e-05, "loss": 4.9199378967285154, "step": 1770 }, { "epoch": 3.574585635359116, "grad_norm": 40.72444534301758, "learning_rate": 3.57095046854083e-05, "loss": 5.063058853149414, "step": 1780 }, { "epoch": 3.5946760421898545, "grad_norm": 16.248395919799805, "learning_rate": 3.55979473449353e-05, "loss": 5.807795715332031, "step": 1790 }, { "epoch": 3.6147664490205926, "grad_norm": 57.422149658203125, "learning_rate": 3.54863900044623e-05, "loss": 5.828661727905273, "step": 1800 }, { "epoch": 3.6348568558513312, "grad_norm": 61.2015495300293, "learning_rate": 3.5374832663989296e-05, "loss": 6.271392822265625, "step": 1810 }, { "epoch": 3.6549472626820694, "grad_norm": 35.906982421875, "learning_rate": 3.526327532351629e-05, "loss": 5.414740753173828, "step": 1820 }, { "epoch": 3.6750376695128075, "grad_norm": 54.37947463989258, "learning_rate": 3.515171798304329e-05, "loss": 5.270346832275391, "step": 1830 }, { "epoch": 3.695128076343546, "grad_norm": 28.034360885620117, "learning_rate": 3.504016064257029e-05, "loss": 5.407860183715821, "step": 1840 }, { "epoch": 3.7152184831742843, "grad_norm": 71.68135833740234, "learning_rate": 3.492860330209728e-05, "loss": 5.702225112915039, "step": 1850 }, { "epoch": 3.7353088900050224, "grad_norm": 22.46561050415039, "learning_rate": 3.481704596162428e-05, "loss": 5.201891708374023, "step": 1860 }, { "epoch": 3.755399296835761, "grad_norm": 24.60894203186035, "learning_rate": 3.470548862115127e-05, "loss": 5.850607299804688, "step": 1870 }, { "epoch": 3.775489703666499, "grad_norm": 28.00958251953125, "learning_rate": 3.459393128067827e-05, "loss": 5.123921203613281, "step": 1880 }, { "epoch": 3.7955801104972373, "grad_norm": 31.907236099243164, "learning_rate": 3.4482373940205263e-05, "loss": 5.6304481506347654, "step": 1890 }, { "epoch": 3.815670517327976, "grad_norm": 17.76685905456543, "learning_rate": 3.437081659973226e-05, "loss": 5.2005657196044925, "step": 1900 }, { "epoch": 3.835760924158714, "grad_norm": 21.260128021240234, "learning_rate": 3.425925925925926e-05, "loss": 5.258316421508789, "step": 1910 }, { "epoch": 3.8558513309894527, "grad_norm": 19.49888801574707, "learning_rate": 3.4147701918786255e-05, "loss": 4.879679489135742, "step": 1920 }, { "epoch": 3.875941737820191, "grad_norm": 65.16366577148438, "learning_rate": 3.4036144578313254e-05, "loss": 6.453560638427734, "step": 1930 }, { "epoch": 3.8960321446509294, "grad_norm": 37.992557525634766, "learning_rate": 3.3924587237840246e-05, "loss": 5.946857452392578, "step": 1940 }, { "epoch": 3.9161225514816675, "grad_norm": 29.18259048461914, "learning_rate": 3.3813029897367246e-05, "loss": 5.703883361816406, "step": 1950 }, { "epoch": 3.9362129583124057, "grad_norm": 50.241573333740234, "learning_rate": 3.3701472556894245e-05, "loss": 5.593105316162109, "step": 1960 }, { "epoch": 3.9563033651431443, "grad_norm": 16.286664962768555, "learning_rate": 3.3589915216421244e-05, "loss": 5.243052673339844, "step": 1970 }, { "epoch": 3.9763937719738824, "grad_norm": 33.029258728027344, "learning_rate": 3.347835787594824e-05, "loss": 5.550778198242187, "step": 1980 }, { "epoch": 3.9964841788046206, "grad_norm": 34.720306396484375, "learning_rate": 3.3366800535475236e-05, "loss": 4.825481796264649, "step": 1990 }, { "epoch": 4.0, "eval_accuracy": 0.8313253012048193, "eval_f1": 0.8308991466535153, "eval_loss": 0.381637305021286, "eval_runtime": 271.7971, "eval_samples_per_second": 14.658, "eval_steps_per_second": 7.329, "step": 1992 }, { "epoch": 4.016072325464591, "grad_norm": 74.65340423583984, "learning_rate": 3.3255243195002235e-05, "loss": 5.714904403686523, "step": 2000 }, { "epoch": 4.036162732295329, "grad_norm": 21.287803649902344, "learning_rate": 3.314368585452923e-05, "loss": 5.464476776123047, "step": 2010 }, { "epoch": 4.056253139126067, "grad_norm": 18.8568115234375, "learning_rate": 3.303212851405623e-05, "loss": 5.644306182861328, "step": 2020 }, { "epoch": 4.076343545956806, "grad_norm": 30.95215606689453, "learning_rate": 3.2920571173583226e-05, "loss": 5.692291259765625, "step": 2030 }, { "epoch": 4.096433952787544, "grad_norm": 15.916340827941895, "learning_rate": 3.280901383311022e-05, "loss": 5.483885192871094, "step": 2040 }, { "epoch": 4.116524359618282, "grad_norm": 47.925392150878906, "learning_rate": 3.269745649263722e-05, "loss": 5.201124954223633, "step": 2050 }, { "epoch": 4.1366147664490205, "grad_norm": 10.943302154541016, "learning_rate": 3.258589915216421e-05, "loss": 5.38978385925293, "step": 2060 }, { "epoch": 4.156705173279759, "grad_norm": 18.42093276977539, "learning_rate": 3.247434181169121e-05, "loss": 5.158708572387695, "step": 2070 }, { "epoch": 4.176795580110497, "grad_norm": 24.33405303955078, "learning_rate": 3.236278447121821e-05, "loss": 5.419537353515625, "step": 2080 }, { "epoch": 4.196885986941235, "grad_norm": 66.79510498046875, "learning_rate": 3.22512271307452e-05, "loss": 5.358119964599609, "step": 2090 }, { "epoch": 4.216976393771974, "grad_norm": 31.320959091186523, "learning_rate": 3.21396697902722e-05, "loss": 5.4256237030029295, "step": 2100 }, { "epoch": 4.237066800602713, "grad_norm": 27.916889190673828, "learning_rate": 3.20281124497992e-05, "loss": 5.278132629394531, "step": 2110 }, { "epoch": 4.25715720743345, "grad_norm": 56.40442657470703, "learning_rate": 3.19165551093262e-05, "loss": 5.812885284423828, "step": 2120 }, { "epoch": 4.277247614264189, "grad_norm": 35.5269775390625, "learning_rate": 3.180499776885319e-05, "loss": 5.212789154052734, "step": 2130 }, { "epoch": 4.2973380210949275, "grad_norm": 76.2720718383789, "learning_rate": 3.169344042838019e-05, "loss": 5.163627624511719, "step": 2140 }, { "epoch": 4.317428427925665, "grad_norm": 15.253010749816895, "learning_rate": 3.158188308790719e-05, "loss": 5.492343521118164, "step": 2150 }, { "epoch": 4.337518834756404, "grad_norm": 27.946918487548828, "learning_rate": 3.147032574743418e-05, "loss": 5.1853797912597654, "step": 2160 }, { "epoch": 4.357609241587142, "grad_norm": 52.33238983154297, "learning_rate": 3.135876840696118e-05, "loss": 5.158102416992188, "step": 2170 }, { "epoch": 4.37769964841788, "grad_norm": 25.031095504760742, "learning_rate": 3.1247211066488174e-05, "loss": 5.204159927368164, "step": 2180 }, { "epoch": 4.397790055248619, "grad_norm": 17.851661682128906, "learning_rate": 3.1135653726015174e-05, "loss": 5.704181671142578, "step": 2190 }, { "epoch": 4.417880462079357, "grad_norm": 46.313568115234375, "learning_rate": 3.102409638554217e-05, "loss": 5.241341018676758, "step": 2200 }, { "epoch": 4.437970868910096, "grad_norm": 32.30226516723633, "learning_rate": 3.0912539045069165e-05, "loss": 5.10718879699707, "step": 2210 }, { "epoch": 4.4580612757408336, "grad_norm": 15.941781044006348, "learning_rate": 3.0800981704596165e-05, "loss": 5.454336929321289, "step": 2220 }, { "epoch": 4.478151682571572, "grad_norm": 50.22789001464844, "learning_rate": 3.068942436412316e-05, "loss": 5.622463607788086, "step": 2230 }, { "epoch": 4.498242089402311, "grad_norm": 24.384248733520508, "learning_rate": 3.0577867023650156e-05, "loss": 5.408155059814453, "step": 2240 }, { "epoch": 4.5183324962330484, "grad_norm": 16.212059020996094, "learning_rate": 3.0466309683177152e-05, "loss": 5.022688674926758, "step": 2250 }, { "epoch": 4.538422903063787, "grad_norm": 18.441513061523438, "learning_rate": 3.035475234270415e-05, "loss": 5.356740188598633, "step": 2260 }, { "epoch": 4.558513309894526, "grad_norm": 16.790136337280273, "learning_rate": 3.024319500223115e-05, "loss": 5.5142967224121096, "step": 2270 }, { "epoch": 4.578603716725263, "grad_norm": 14.181636810302734, "learning_rate": 3.0131637661758143e-05, "loss": 4.767865753173828, "step": 2280 }, { "epoch": 4.598694123556002, "grad_norm": 17.37836265563965, "learning_rate": 3.0020080321285143e-05, "loss": 5.370041275024414, "step": 2290 }, { "epoch": 4.6187845303867405, "grad_norm": 49.22777557373047, "learning_rate": 2.990852298081214e-05, "loss": 4.569227600097657, "step": 2300 }, { "epoch": 4.638874937217478, "grad_norm": 25.545143127441406, "learning_rate": 2.9796965640339138e-05, "loss": 5.380747985839844, "step": 2310 }, { "epoch": 4.658965344048217, "grad_norm": 43.53788757324219, "learning_rate": 2.9685408299866134e-05, "loss": 4.9394775390625, "step": 2320 }, { "epoch": 4.679055750878955, "grad_norm": 49.636932373046875, "learning_rate": 2.957385095939313e-05, "loss": 5.990687561035156, "step": 2330 }, { "epoch": 4.699146157709693, "grad_norm": 38.258567810058594, "learning_rate": 2.946229361892013e-05, "loss": 5.420593643188477, "step": 2340 }, { "epoch": 4.719236564540432, "grad_norm": 27.52723503112793, "learning_rate": 2.935073627844712e-05, "loss": 5.536288452148438, "step": 2350 }, { "epoch": 4.73932697137117, "grad_norm": 60.57950210571289, "learning_rate": 2.923917893797412e-05, "loss": 4.603693008422852, "step": 2360 }, { "epoch": 4.759417378201909, "grad_norm": 22.113107681274414, "learning_rate": 2.9127621597501113e-05, "loss": 4.981324768066406, "step": 2370 }, { "epoch": 4.779507785032647, "grad_norm": 30.821203231811523, "learning_rate": 2.9016064257028112e-05, "loss": 4.554284286499024, "step": 2380 }, { "epoch": 4.799598191863385, "grad_norm": 26.094152450561523, "learning_rate": 2.890450691655511e-05, "loss": 5.04138298034668, "step": 2390 }, { "epoch": 4.819688598694124, "grad_norm": 17.493146896362305, "learning_rate": 2.8792949576082107e-05, "loss": 5.155031967163086, "step": 2400 }, { "epoch": 4.8397790055248615, "grad_norm": 15.644641876220703, "learning_rate": 2.8681392235609107e-05, "loss": 5.377874755859375, "step": 2410 }, { "epoch": 4.8598694123556, "grad_norm": 38.115047454833984, "learning_rate": 2.85698348951361e-05, "loss": 4.66938362121582, "step": 2420 }, { "epoch": 4.879959819186339, "grad_norm": 53.47895812988281, "learning_rate": 2.84582775546631e-05, "loss": 5.689941787719727, "step": 2430 }, { "epoch": 4.900050226017077, "grad_norm": 36.03934860229492, "learning_rate": 2.8346720214190098e-05, "loss": 5.6914318084716795, "step": 2440 }, { "epoch": 4.920140632847815, "grad_norm": 53.556766510009766, "learning_rate": 2.823516287371709e-05, "loss": 4.916519546508789, "step": 2450 }, { "epoch": 4.940231039678554, "grad_norm": 57.19694519042969, "learning_rate": 2.812360553324409e-05, "loss": 5.351926803588867, "step": 2460 }, { "epoch": 4.960321446509292, "grad_norm": 18.76446533203125, "learning_rate": 2.8012048192771085e-05, "loss": 4.898180770874023, "step": 2470 }, { "epoch": 4.98041185334003, "grad_norm": 24.70296859741211, "learning_rate": 2.7900490852298085e-05, "loss": 5.895172882080078, "step": 2480 }, { "epoch": 5.0, "grad_norm": 35.55866622924805, "learning_rate": 2.7788933511825077e-05, "loss": 5.8037456512451175, "step": 2490 }, { "epoch": 5.0, "eval_accuracy": 0.8411144578313253, "eval_f1": 0.8409578932624466, "eval_loss": 0.3684503734111786, "eval_runtime": 292.0862, "eval_samples_per_second": 13.64, "eval_steps_per_second": 6.82, "step": 2490 }, { "epoch": 5.020090406830739, "grad_norm": 28.72409439086914, "learning_rate": 2.7677376171352076e-05, "loss": 5.221046829223633, "step": 2500 }, { "epoch": 5.040180813661476, "grad_norm": 18.975839614868164, "learning_rate": 2.7565818830879076e-05, "loss": 4.8713134765625, "step": 2510 }, { "epoch": 5.060271220492215, "grad_norm": 15.418108940124512, "learning_rate": 2.7454261490406068e-05, "loss": 6.1083221435546875, "step": 2520 }, { "epoch": 5.0803616273229535, "grad_norm": 28.050870895385742, "learning_rate": 2.7342704149933067e-05, "loss": 5.821896743774414, "step": 2530 }, { "epoch": 5.100452034153691, "grad_norm": 17.038471221923828, "learning_rate": 2.7231146809460063e-05, "loss": 4.623192596435547, "step": 2540 }, { "epoch": 5.12054244098443, "grad_norm": 23.476816177368164, "learning_rate": 2.7119589468987063e-05, "loss": 5.190683364868164, "step": 2550 }, { "epoch": 5.140632847815168, "grad_norm": 37.98016357421875, "learning_rate": 2.7008032128514062e-05, "loss": 5.112508010864258, "step": 2560 }, { "epoch": 5.160723254645907, "grad_norm": 24.850126266479492, "learning_rate": 2.6896474788041054e-05, "loss": 4.7745849609375, "step": 2570 }, { "epoch": 5.180813661476645, "grad_norm": 47.20379638671875, "learning_rate": 2.6784917447568054e-05, "loss": 5.232223129272461, "step": 2580 }, { "epoch": 5.200904068307383, "grad_norm": 23.13062858581543, "learning_rate": 2.6673360107095046e-05, "loss": 5.186569595336914, "step": 2590 }, { "epoch": 5.220994475138122, "grad_norm": 27.696128845214844, "learning_rate": 2.6561802766622045e-05, "loss": 5.067018127441406, "step": 2600 }, { "epoch": 5.24108488196886, "grad_norm": 13.323182106018066, "learning_rate": 2.645024542614904e-05, "loss": 4.888212966918945, "step": 2610 }, { "epoch": 5.261175288799598, "grad_norm": 25.06966209411621, "learning_rate": 2.6338688085676037e-05, "loss": 4.49219856262207, "step": 2620 }, { "epoch": 5.281265695630337, "grad_norm": 17.505725860595703, "learning_rate": 2.6227130745203036e-05, "loss": 5.749640655517578, "step": 2630 }, { "epoch": 5.3013561024610745, "grad_norm": 15.64422607421875, "learning_rate": 2.6115573404730032e-05, "loss": 4.5112770080566404, "step": 2640 }, { "epoch": 5.321446509291813, "grad_norm": 73.4803695678711, "learning_rate": 2.600401606425703e-05, "loss": 6.108562469482422, "step": 2650 }, { "epoch": 5.341536916122552, "grad_norm": 20.907390594482422, "learning_rate": 2.5892458723784024e-05, "loss": 4.795833587646484, "step": 2660 }, { "epoch": 5.361627322953289, "grad_norm": 38.76797866821289, "learning_rate": 2.5780901383311023e-05, "loss": 5.315673446655273, "step": 2670 }, { "epoch": 5.381717729784028, "grad_norm": 43.318016052246094, "learning_rate": 2.5669344042838023e-05, "loss": 4.8762256622314455, "step": 2680 }, { "epoch": 5.4018081366147666, "grad_norm": 30.775569915771484, "learning_rate": 2.5557786702365015e-05, "loss": 6.07193603515625, "step": 2690 }, { "epoch": 5.421898543445505, "grad_norm": 40.072669982910156, "learning_rate": 2.5446229361892014e-05, "loss": 5.428866958618164, "step": 2700 }, { "epoch": 5.441988950276243, "grad_norm": 53.4805793762207, "learning_rate": 2.533467202141901e-05, "loss": 4.893692398071289, "step": 2710 }, { "epoch": 5.4620793571069814, "grad_norm": 19.371530532836914, "learning_rate": 2.522311468094601e-05, "loss": 4.8185382843017575, "step": 2720 }, { "epoch": 5.48216976393772, "grad_norm": 44.22858428955078, "learning_rate": 2.5111557340473002e-05, "loss": 5.695796966552734, "step": 2730 }, { "epoch": 5.502260170768458, "grad_norm": 31.715206146240234, "learning_rate": 2.5e-05, "loss": 4.415434646606445, "step": 2740 }, { "epoch": 5.522350577599196, "grad_norm": 42.429161071777344, "learning_rate": 2.4888442659526997e-05, "loss": 4.981886672973633, "step": 2750 }, { "epoch": 5.542440984429935, "grad_norm": 27.741533279418945, "learning_rate": 2.4776885319053993e-05, "loss": 5.128759765625, "step": 2760 }, { "epoch": 5.562531391260673, "grad_norm": 15.454511642456055, "learning_rate": 2.466532797858099e-05, "loss": 5.218790054321289, "step": 2770 }, { "epoch": 5.582621798091411, "grad_norm": 30.33209800720215, "learning_rate": 2.4553770638107988e-05, "loss": 4.657939910888672, "step": 2780 }, { "epoch": 5.60271220492215, "grad_norm": 20.21453094482422, "learning_rate": 2.4442213297634987e-05, "loss": 5.108760833740234, "step": 2790 }, { "epoch": 5.622802611752888, "grad_norm": 25.322263717651367, "learning_rate": 2.4330655957161983e-05, "loss": 5.250006866455078, "step": 2800 }, { "epoch": 5.642893018583626, "grad_norm": 53.17401123046875, "learning_rate": 2.421909861668898e-05, "loss": 5.401283645629883, "step": 2810 }, { "epoch": 5.662983425414365, "grad_norm": 35.35806655883789, "learning_rate": 2.4107541276215975e-05, "loss": 5.498031997680664, "step": 2820 }, { "epoch": 5.683073832245103, "grad_norm": 22.878442764282227, "learning_rate": 2.399598393574297e-05, "loss": 5.459403228759766, "step": 2830 }, { "epoch": 5.703164239075841, "grad_norm": 20.102827072143555, "learning_rate": 2.388442659526997e-05, "loss": 6.1413829803466795, "step": 2840 }, { "epoch": 5.72325464590658, "grad_norm": 20.25745391845703, "learning_rate": 2.3772869254796966e-05, "loss": 4.882641983032227, "step": 2850 }, { "epoch": 5.743345052737318, "grad_norm": 35.74831008911133, "learning_rate": 2.3661311914323965e-05, "loss": 5.014767074584961, "step": 2860 }, { "epoch": 5.763435459568056, "grad_norm": 23.318525314331055, "learning_rate": 2.354975457385096e-05, "loss": 5.152687835693359, "step": 2870 }, { "epoch": 5.7835258663987945, "grad_norm": 21.513328552246094, "learning_rate": 2.3438197233377957e-05, "loss": 4.725801849365235, "step": 2880 }, { "epoch": 5.803616273229533, "grad_norm": 56.45954895019531, "learning_rate": 2.3326639892904953e-05, "loss": 5.157341384887696, "step": 2890 }, { "epoch": 5.823706680060271, "grad_norm": 65.35350799560547, "learning_rate": 2.3215082552431952e-05, "loss": 5.307432174682617, "step": 2900 }, { "epoch": 5.843797086891009, "grad_norm": 28.175186157226562, "learning_rate": 2.3103525211958948e-05, "loss": 4.665093612670899, "step": 2910 }, { "epoch": 5.863887493721748, "grad_norm": 48.39313888549805, "learning_rate": 2.2991967871485944e-05, "loss": 5.316522598266602, "step": 2920 }, { "epoch": 5.883977900552486, "grad_norm": 33.451805114746094, "learning_rate": 2.288041053101294e-05, "loss": 4.894639205932617, "step": 2930 }, { "epoch": 5.904068307383224, "grad_norm": 25.893495559692383, "learning_rate": 2.276885319053994e-05, "loss": 4.870404815673828, "step": 2940 }, { "epoch": 5.924158714213963, "grad_norm": 29.453739166259766, "learning_rate": 2.2657295850066935e-05, "loss": 4.7879188537597654, "step": 2950 }, { "epoch": 5.9442491210447015, "grad_norm": 18.500818252563477, "learning_rate": 2.2545738509593934e-05, "loss": 4.371553039550781, "step": 2960 }, { "epoch": 5.964339527875439, "grad_norm": 69.91905212402344, "learning_rate": 2.243418116912093e-05, "loss": 5.153863906860352, "step": 2970 }, { "epoch": 5.984429934706178, "grad_norm": 42.159034729003906, "learning_rate": 2.2322623828647926e-05, "loss": 5.773333740234375, "step": 2980 }, { "epoch": 6.0, "eval_accuracy": 0.8423694779116466, "eval_f1": 0.842002521945778, "eval_loss": 0.3624602258205414, "eval_runtime": 268.2496, "eval_samples_per_second": 14.852, "eval_steps_per_second": 7.426, "step": 2988 }, { "epoch": 6.004018081366148, "grad_norm": 35.53681945800781, "learning_rate": 2.2211066488174922e-05, "loss": 4.662354278564453, "step": 2990 }, { "epoch": 6.024108488196886, "grad_norm": 24.490995407104492, "learning_rate": 2.2099509147701918e-05, "loss": 5.122311401367187, "step": 3000 }, { "epoch": 6.044198895027624, "grad_norm": 27.2031192779541, "learning_rate": 2.1987951807228917e-05, "loss": 4.6893970489501955, "step": 3010 }, { "epoch": 6.064289301858363, "grad_norm": 57.05522155761719, "learning_rate": 2.1876394466755913e-05, "loss": 5.1965492248535154, "step": 3020 }, { "epoch": 6.084379708689101, "grad_norm": 23.291120529174805, "learning_rate": 2.1764837126282912e-05, "loss": 5.080121231079102, "step": 3030 }, { "epoch": 6.104470115519839, "grad_norm": 45.572669982910156, "learning_rate": 2.1653279785809908e-05, "loss": 5.157864379882812, "step": 3040 }, { "epoch": 6.124560522350578, "grad_norm": 71.93682098388672, "learning_rate": 2.1541722445336904e-05, "loss": 4.763975143432617, "step": 3050 }, { "epoch": 6.144650929181316, "grad_norm": 27.576343536376953, "learning_rate": 2.14301651048639e-05, "loss": 4.805879592895508, "step": 3060 }, { "epoch": 6.164741336012054, "grad_norm": 25.874540328979492, "learning_rate": 2.1318607764390896e-05, "loss": 5.126565551757812, "step": 3070 }, { "epoch": 6.184831742842793, "grad_norm": 20.238725662231445, "learning_rate": 2.1207050423917895e-05, "loss": 4.988492584228515, "step": 3080 }, { "epoch": 6.204922149673531, "grad_norm": 16.861356735229492, "learning_rate": 2.109549308344489e-05, "loss": 4.830979919433593, "step": 3090 }, { "epoch": 6.225012556504269, "grad_norm": 75.32235717773438, "learning_rate": 2.098393574297189e-05, "loss": 4.752168273925781, "step": 3100 }, { "epoch": 6.2451029633350075, "grad_norm": 24.361948013305664, "learning_rate": 2.0872378402498886e-05, "loss": 5.145538330078125, "step": 3110 }, { "epoch": 6.265193370165746, "grad_norm": 36.55158233642578, "learning_rate": 2.0760821062025882e-05, "loss": 4.896182632446289, "step": 3120 }, { "epoch": 6.285283776996484, "grad_norm": 52.193538665771484, "learning_rate": 2.0649263721552878e-05, "loss": 5.444088363647461, "step": 3130 }, { "epoch": 6.305374183827222, "grad_norm": 42.52162170410156, "learning_rate": 2.0537706381079877e-05, "loss": 5.043056869506836, "step": 3140 }, { "epoch": 6.325464590657961, "grad_norm": 63.23277282714844, "learning_rate": 2.0426149040606873e-05, "loss": 5.012929916381836, "step": 3150 }, { "epoch": 6.3455549974886996, "grad_norm": 24.21165657043457, "learning_rate": 2.031459170013387e-05, "loss": 5.35864143371582, "step": 3160 }, { "epoch": 6.365645404319437, "grad_norm": 34.47937774658203, "learning_rate": 2.0203034359660865e-05, "loss": 5.117205810546875, "step": 3170 }, { "epoch": 6.385735811150176, "grad_norm": 30.00104522705078, "learning_rate": 2.0091477019187864e-05, "loss": 5.130288696289062, "step": 3180 }, { "epoch": 6.4058262179809144, "grad_norm": 16.255022048950195, "learning_rate": 1.997991967871486e-05, "loss": 4.516607284545898, "step": 3190 }, { "epoch": 6.425916624811652, "grad_norm": 15.049686431884766, "learning_rate": 1.986836233824186e-05, "loss": 5.757273101806641, "step": 3200 }, { "epoch": 6.446007031642391, "grad_norm": 34.83894729614258, "learning_rate": 1.9756804997768855e-05, "loss": 4.890773010253906, "step": 3210 }, { "epoch": 6.466097438473129, "grad_norm": 25.50164222717285, "learning_rate": 1.964524765729585e-05, "loss": 4.795869445800781, "step": 3220 }, { "epoch": 6.486187845303867, "grad_norm": 18.05068588256836, "learning_rate": 1.9533690316822847e-05, "loss": 4.6408027648925785, "step": 3230 }, { "epoch": 6.506278252134606, "grad_norm": 16.90067481994629, "learning_rate": 1.9422132976349843e-05, "loss": 4.570175552368164, "step": 3240 }, { "epoch": 6.526368658965344, "grad_norm": 29.6487979888916, "learning_rate": 1.9310575635876842e-05, "loss": 4.774335861206055, "step": 3250 }, { "epoch": 6.546459065796082, "grad_norm": 21.24527931213379, "learning_rate": 1.919901829540384e-05, "loss": 4.519001388549805, "step": 3260 }, { "epoch": 6.5665494726268205, "grad_norm": 20.351415634155273, "learning_rate": 1.9087460954930837e-05, "loss": 4.842393493652343, "step": 3270 }, { "epoch": 6.586639879457559, "grad_norm": 35.6263542175293, "learning_rate": 1.8975903614457833e-05, "loss": 5.707883834838867, "step": 3280 }, { "epoch": 6.606730286288298, "grad_norm": 16.515222549438477, "learning_rate": 1.886434627398483e-05, "loss": 5.153984451293946, "step": 3290 }, { "epoch": 6.626820693119035, "grad_norm": 34.04801559448242, "learning_rate": 1.8752788933511825e-05, "loss": 5.007660675048828, "step": 3300 }, { "epoch": 6.646911099949774, "grad_norm": 33.79451370239258, "learning_rate": 1.864123159303882e-05, "loss": 5.102581405639649, "step": 3310 }, { "epoch": 6.667001506780513, "grad_norm": 92.29517364501953, "learning_rate": 1.852967425256582e-05, "loss": 4.617330169677734, "step": 3320 }, { "epoch": 6.68709191361125, "grad_norm": 12.401615142822266, "learning_rate": 1.8418116912092816e-05, "loss": 4.904205322265625, "step": 3330 }, { "epoch": 6.707182320441989, "grad_norm": 26.304513931274414, "learning_rate": 1.8306559571619815e-05, "loss": 5.454282760620117, "step": 3340 }, { "epoch": 6.7272727272727275, "grad_norm": 27.230979919433594, "learning_rate": 1.819500223114681e-05, "loss": 5.710644149780274, "step": 3350 }, { "epoch": 6.747363134103465, "grad_norm": 46.883522033691406, "learning_rate": 1.8083444890673807e-05, "loss": 5.027747344970703, "step": 3360 }, { "epoch": 6.767453540934204, "grad_norm": 47.2624626159668, "learning_rate": 1.7971887550200802e-05, "loss": 4.515190505981446, "step": 3370 }, { "epoch": 6.787543947764942, "grad_norm": 9.284256935119629, "learning_rate": 1.7860330209727802e-05, "loss": 4.776156616210938, "step": 3380 }, { "epoch": 6.807634354595681, "grad_norm": 24.37062644958496, "learning_rate": 1.7748772869254798e-05, "loss": 5.167645263671875, "step": 3390 }, { "epoch": 6.827724761426419, "grad_norm": 41.971954345703125, "learning_rate": 1.7637215528781794e-05, "loss": 5.264893341064453, "step": 3400 }, { "epoch": 6.847815168257157, "grad_norm": 45.36711502075195, "learning_rate": 1.7525658188308793e-05, "loss": 5.778470230102539, "step": 3410 }, { "epoch": 6.867905575087896, "grad_norm": 36.880287170410156, "learning_rate": 1.741410084783579e-05, "loss": 5.683300399780274, "step": 3420 }, { "epoch": 6.887995981918634, "grad_norm": 43.906246185302734, "learning_rate": 1.7302543507362785e-05, "loss": 5.370430374145508, "step": 3430 }, { "epoch": 6.908086388749372, "grad_norm": 23.548818588256836, "learning_rate": 1.7190986166889784e-05, "loss": 4.880501556396484, "step": 3440 }, { "epoch": 6.928176795580111, "grad_norm": 31.558584213256836, "learning_rate": 1.707942882641678e-05, "loss": 4.303641891479492, "step": 3450 }, { "epoch": 6.9482672024108485, "grad_norm": 52.002445220947266, "learning_rate": 1.6967871485943776e-05, "loss": 4.768168258666992, "step": 3460 }, { "epoch": 6.968357609241587, "grad_norm": 28.17192840576172, "learning_rate": 1.685631414547077e-05, "loss": 5.042802047729492, "step": 3470 }, { "epoch": 6.988448016072326, "grad_norm": 19.393342971801758, "learning_rate": 1.6744756804997767e-05, "loss": 4.945818328857422, "step": 3480 }, { "epoch": 7.0, "eval_accuracy": 0.8436244979919679, "eval_f1": 0.8433492483480091, "eval_loss": 0.35702601075172424, "eval_runtime": 262.2333, "eval_samples_per_second": 15.193, "eval_steps_per_second": 7.596, "step": 3486 }, { "epoch": 7.008036162732295, "grad_norm": 14.138530731201172, "learning_rate": 1.6633199464524767e-05, "loss": 4.3596343994140625, "step": 3490 }, { "epoch": 7.0281265695630335, "grad_norm": 22.500049591064453, "learning_rate": 1.6521642124051766e-05, "loss": 5.607269287109375, "step": 3500 }, { "epoch": 7.048216976393772, "grad_norm": 59.02973175048828, "learning_rate": 1.6410084783578762e-05, "loss": 4.270198822021484, "step": 3510 }, { "epoch": 7.068307383224511, "grad_norm": 24.499643325805664, "learning_rate": 1.6298527443105758e-05, "loss": 4.8923088073730465, "step": 3520 }, { "epoch": 7.088397790055248, "grad_norm": 13.680716514587402, "learning_rate": 1.6186970102632753e-05, "loss": 5.587213134765625, "step": 3530 }, { "epoch": 7.108488196885987, "grad_norm": 60.47969436645508, "learning_rate": 1.607541276215975e-05, "loss": 5.904486846923828, "step": 3540 }, { "epoch": 7.128578603716726, "grad_norm": 50.3714714050293, "learning_rate": 1.5963855421686745e-05, "loss": 5.157215118408203, "step": 3550 }, { "epoch": 7.148669010547463, "grad_norm": 19.577560424804688, "learning_rate": 1.5852298081213744e-05, "loss": 4.865789794921875, "step": 3560 }, { "epoch": 7.168759417378202, "grad_norm": 22.570194244384766, "learning_rate": 1.574074074074074e-05, "loss": 4.57782096862793, "step": 3570 }, { "epoch": 7.1888498242089405, "grad_norm": 33.76600646972656, "learning_rate": 1.562918340026774e-05, "loss": 5.149881362915039, "step": 3580 }, { "epoch": 7.208940231039678, "grad_norm": 23.610483169555664, "learning_rate": 1.5517626059794736e-05, "loss": 4.826559066772461, "step": 3590 }, { "epoch": 7.229030637870417, "grad_norm": 37.79949188232422, "learning_rate": 1.540606871932173e-05, "loss": 5.518171691894532, "step": 3600 }, { "epoch": 7.249121044701155, "grad_norm": 44.173587799072266, "learning_rate": 1.5294511378848727e-05, "loss": 4.428212738037109, "step": 3610 }, { "epoch": 7.269211451531893, "grad_norm": 12.11299991607666, "learning_rate": 1.5182954038375727e-05, "loss": 4.974694442749024, "step": 3620 }, { "epoch": 7.289301858362632, "grad_norm": 28.53829002380371, "learning_rate": 1.5071396697902722e-05, "loss": 4.633474349975586, "step": 3630 }, { "epoch": 7.30939226519337, "grad_norm": 61.57353973388672, "learning_rate": 1.495983935742972e-05, "loss": 5.062638854980468, "step": 3640 }, { "epoch": 7.329482672024109, "grad_norm": 40.34135437011719, "learning_rate": 1.4848282016956716e-05, "loss": 4.733907699584961, "step": 3650 }, { "epoch": 7.349573078854847, "grad_norm": 60.098907470703125, "learning_rate": 1.4736724676483712e-05, "loss": 4.926570129394531, "step": 3660 }, { "epoch": 7.369663485685585, "grad_norm": 28.38014030456543, "learning_rate": 1.462516733601071e-05, "loss": 4.4268341064453125, "step": 3670 }, { "epoch": 7.389753892516324, "grad_norm": 44.57749938964844, "learning_rate": 1.4513609995537709e-05, "loss": 4.547550201416016, "step": 3680 }, { "epoch": 7.4098442993470615, "grad_norm": 38.65041732788086, "learning_rate": 1.4402052655064704e-05, "loss": 5.56726303100586, "step": 3690 }, { "epoch": 7.4299347061778, "grad_norm": 16.378496170043945, "learning_rate": 1.42904953145917e-05, "loss": 5.123839950561523, "step": 3700 }, { "epoch": 7.450025113008539, "grad_norm": 48.2341423034668, "learning_rate": 1.4178937974118698e-05, "loss": 5.816294097900391, "step": 3710 }, { "epoch": 7.470115519839276, "grad_norm": 45.043521881103516, "learning_rate": 1.4067380633645694e-05, "loss": 5.263410186767578, "step": 3720 }, { "epoch": 7.490205926670015, "grad_norm": 30.503353118896484, "learning_rate": 1.395582329317269e-05, "loss": 5.0578865051269535, "step": 3730 }, { "epoch": 7.5102963335007535, "grad_norm": 41.905250549316406, "learning_rate": 1.3844265952699689e-05, "loss": 4.4703208923339846, "step": 3740 }, { "epoch": 7.530386740331492, "grad_norm": 34.12063217163086, "learning_rate": 1.3732708612226686e-05, "loss": 5.721608734130859, "step": 3750 }, { "epoch": 7.55047714716223, "grad_norm": 46.85991287231445, "learning_rate": 1.3621151271753682e-05, "loss": 5.07727279663086, "step": 3760 }, { "epoch": 7.570567553992968, "grad_norm": 24.391342163085938, "learning_rate": 1.3509593931280678e-05, "loss": 4.039135360717774, "step": 3770 }, { "epoch": 7.590657960823707, "grad_norm": 39.22905731201172, "learning_rate": 1.3398036590807674e-05, "loss": 5.317110061645508, "step": 3780 }, { "epoch": 7.610748367654445, "grad_norm": 25.743370056152344, "learning_rate": 1.3286479250334672e-05, "loss": 5.379373550415039, "step": 3790 }, { "epoch": 7.630838774485183, "grad_norm": 45.748741149902344, "learning_rate": 1.3174921909861671e-05, "loss": 4.716722106933593, "step": 3800 }, { "epoch": 7.650929181315922, "grad_norm": 22.601913452148438, "learning_rate": 1.3063364569388667e-05, "loss": 5.000032043457031, "step": 3810 }, { "epoch": 7.67101958814666, "grad_norm": 13.845768928527832, "learning_rate": 1.2951807228915663e-05, "loss": 4.806098556518554, "step": 3820 }, { "epoch": 7.691109994977398, "grad_norm": 26.75832748413086, "learning_rate": 1.284024988844266e-05, "loss": 5.216695022583008, "step": 3830 }, { "epoch": 7.711200401808137, "grad_norm": 29.472978591918945, "learning_rate": 1.2728692547969656e-05, "loss": 4.140066909790039, "step": 3840 }, { "epoch": 7.7312908086388745, "grad_norm": 18.088420867919922, "learning_rate": 1.2617135207496652e-05, "loss": 5.431718826293945, "step": 3850 }, { "epoch": 7.751381215469613, "grad_norm": 19.155441284179688, "learning_rate": 1.2505577867023651e-05, "loss": 4.607300567626953, "step": 3860 }, { "epoch": 7.771471622300352, "grad_norm": 27.480331420898438, "learning_rate": 1.2394020526550649e-05, "loss": 4.828065872192383, "step": 3870 }, { "epoch": 7.791562029131089, "grad_norm": 22.26152992248535, "learning_rate": 1.2282463186077645e-05, "loss": 5.170344543457031, "step": 3880 }, { "epoch": 7.811652435961828, "grad_norm": 31.332334518432617, "learning_rate": 1.217090584560464e-05, "loss": 5.4249217987060545, "step": 3890 }, { "epoch": 7.831742842792567, "grad_norm": 36.22314453125, "learning_rate": 1.2059348505131638e-05, "loss": 4.919199752807617, "step": 3900 }, { "epoch": 7.851833249623305, "grad_norm": 47.752017974853516, "learning_rate": 1.1947791164658636e-05, "loss": 5.097568511962891, "step": 3910 }, { "epoch": 7.871923656454043, "grad_norm": 31.654233932495117, "learning_rate": 1.1836233824185632e-05, "loss": 4.419127655029297, "step": 3920 }, { "epoch": 7.8920140632847815, "grad_norm": 19.052715301513672, "learning_rate": 1.172467648371263e-05, "loss": 5.012520217895508, "step": 3930 }, { "epoch": 7.91210447011552, "grad_norm": 50.09199905395508, "learning_rate": 1.1613119143239625e-05, "loss": 3.986498260498047, "step": 3940 }, { "epoch": 7.932194876946258, "grad_norm": 19.460662841796875, "learning_rate": 1.1501561802766623e-05, "loss": 5.136830520629883, "step": 3950 }, { "epoch": 7.952285283776996, "grad_norm": 69.93310546875, "learning_rate": 1.139000446229362e-05, "loss": 4.8323314666748045, "step": 3960 }, { "epoch": 7.972375690607735, "grad_norm": 55.283058166503906, "learning_rate": 1.1278447121820616e-05, "loss": 4.889380645751953, "step": 3970 }, { "epoch": 7.992466097438474, "grad_norm": 18.24380111694336, "learning_rate": 1.1166889781347612e-05, "loss": 4.738026428222656, "step": 3980 }, { "epoch": 8.0, "eval_accuracy": 0.8458835341365462, "eval_f1": 0.8456345616387457, "eval_loss": 0.35393810272216797, "eval_runtime": 310.6093, "eval_samples_per_second": 12.826, "eval_steps_per_second": 6.413, "step": 3984 }, { "epoch": 8.012054244098444, "grad_norm": 23.76414680480957, "learning_rate": 1.1055332440874611e-05, "loss": 5.486224746704101, "step": 3990 }, { "epoch": 8.032144650929181, "grad_norm": 15.661172866821289, "learning_rate": 1.0943775100401607e-05, "loss": 4.3542743682861325, "step": 4000 }, { "epoch": 8.052235057759919, "grad_norm": 49.623653411865234, "learning_rate": 1.0832217759928603e-05, "loss": 4.300787353515625, "step": 4010 }, { "epoch": 8.072325464590659, "grad_norm": 15.006990432739258, "learning_rate": 1.07206604194556e-05, "loss": 4.680204772949219, "step": 4020 }, { "epoch": 8.092415871421396, "grad_norm": 46.151432037353516, "learning_rate": 1.0609103078982598e-05, "loss": 5.311506271362305, "step": 4030 }, { "epoch": 8.112506278252134, "grad_norm": 20.228389739990234, "learning_rate": 1.0497545738509594e-05, "loss": 5.797823333740235, "step": 4040 }, { "epoch": 8.132596685082873, "grad_norm": 13.789586067199707, "learning_rate": 1.0385988398036592e-05, "loss": 5.060232925415039, "step": 4050 }, { "epoch": 8.152687091913611, "grad_norm": 14.948539733886719, "learning_rate": 1.0274431057563588e-05, "loss": 4.8325458526611325, "step": 4060 }, { "epoch": 8.172777498744349, "grad_norm": 33.25334167480469, "learning_rate": 1.0162873717090585e-05, "loss": 5.2680011749267575, "step": 4070 }, { "epoch": 8.192867905575088, "grad_norm": 17.973224639892578, "learning_rate": 1.0051316376617583e-05, "loss": 4.909983825683594, "step": 4080 }, { "epoch": 8.212958312405826, "grad_norm": 35.23036193847656, "learning_rate": 9.939759036144579e-06, "loss": 5.232453536987305, "step": 4090 }, { "epoch": 8.233048719236564, "grad_norm": 26.402755737304688, "learning_rate": 9.828201695671576e-06, "loss": 5.20031852722168, "step": 4100 }, { "epoch": 8.253139126067303, "grad_norm": 22.437862396240234, "learning_rate": 9.716644355198574e-06, "loss": 5.2191204071044925, "step": 4110 }, { "epoch": 8.273229532898041, "grad_norm": 61.909061431884766, "learning_rate": 9.60508701472557e-06, "loss": 5.198928451538086, "step": 4120 }, { "epoch": 8.293319939728779, "grad_norm": 61.255428314208984, "learning_rate": 9.493529674252565e-06, "loss": 4.426901626586914, "step": 4130 }, { "epoch": 8.313410346559518, "grad_norm": 31.23830795288086, "learning_rate": 9.381972333779563e-06, "loss": 4.7098651885986325, "step": 4140 }, { "epoch": 8.333500753390256, "grad_norm": 26.656343460083008, "learning_rate": 9.27041499330656e-06, "loss": 4.663322067260742, "step": 4150 }, { "epoch": 8.353591160220994, "grad_norm": 20.919090270996094, "learning_rate": 9.158857652833556e-06, "loss": 4.325035476684571, "step": 4160 }, { "epoch": 8.373681567051733, "grad_norm": 39.30440902709961, "learning_rate": 9.047300312360554e-06, "loss": 4.679663467407226, "step": 4170 }, { "epoch": 8.39377197388247, "grad_norm": 17.87153434753418, "learning_rate": 8.93574297188755e-06, "loss": 5.820931625366211, "step": 4180 }, { "epoch": 8.41386238071321, "grad_norm": 19.720964431762695, "learning_rate": 8.824185631414547e-06, "loss": 4.8222816467285154, "step": 4190 }, { "epoch": 8.433952787543948, "grad_norm": 52.371498107910156, "learning_rate": 8.712628290941545e-06, "loss": 4.4416961669921875, "step": 4200 }, { "epoch": 8.454043194374686, "grad_norm": 23.638113021850586, "learning_rate": 8.601070950468541e-06, "loss": 5.278662490844726, "step": 4210 }, { "epoch": 8.474133601205425, "grad_norm": 34.30152130126953, "learning_rate": 8.489513609995538e-06, "loss": 4.774466705322266, "step": 4220 }, { "epoch": 8.494224008036163, "grad_norm": 31.3404483795166, "learning_rate": 8.377956269522536e-06, "loss": 4.360430145263672, "step": 4230 }, { "epoch": 8.5143144148669, "grad_norm": 106.59876251220703, "learning_rate": 8.266398929049532e-06, "loss": 4.840221786499024, "step": 4240 }, { "epoch": 8.53440482169764, "grad_norm": 45.42464065551758, "learning_rate": 8.154841588576528e-06, "loss": 5.20860710144043, "step": 4250 }, { "epoch": 8.554495228528378, "grad_norm": 62.43822479248047, "learning_rate": 8.043284248103525e-06, "loss": 4.646908569335937, "step": 4260 }, { "epoch": 8.574585635359115, "grad_norm": 36.19871520996094, "learning_rate": 7.931726907630523e-06, "loss": 5.283548736572266, "step": 4270 }, { "epoch": 8.594676042189855, "grad_norm": 15.450304985046387, "learning_rate": 7.820169567157519e-06, "loss": 4.814856338500976, "step": 4280 }, { "epoch": 8.614766449020593, "grad_norm": 33.513038635253906, "learning_rate": 7.708612226684516e-06, "loss": 4.491749954223633, "step": 4290 }, { "epoch": 8.63485685585133, "grad_norm": 37.80437088012695, "learning_rate": 7.597054886211513e-06, "loss": 4.529288101196289, "step": 4300 }, { "epoch": 8.65494726268207, "grad_norm": 32.805511474609375, "learning_rate": 7.48549754573851e-06, "loss": 5.167245101928711, "step": 4310 }, { "epoch": 8.675037669512808, "grad_norm": 27.483816146850586, "learning_rate": 7.3739402052655074e-06, "loss": 4.453053283691406, "step": 4320 }, { "epoch": 8.695128076343545, "grad_norm": 21.18474578857422, "learning_rate": 7.262382864792504e-06, "loss": 4.621733474731445, "step": 4330 }, { "epoch": 8.715218483174285, "grad_norm": 30.602943420410156, "learning_rate": 7.1508255243195e-06, "loss": 4.995375442504883, "step": 4340 }, { "epoch": 8.735308890005022, "grad_norm": 69.80766296386719, "learning_rate": 7.039268183846498e-06, "loss": 4.608235168457031, "step": 4350 }, { "epoch": 8.75539929683576, "grad_norm": 17.186925888061523, "learning_rate": 6.927710843373494e-06, "loss": 4.889940643310547, "step": 4360 }, { "epoch": 8.7754897036665, "grad_norm": 39.77102279663086, "learning_rate": 6.816153502900491e-06, "loss": 5.3718009948730465, "step": 4370 }, { "epoch": 8.795580110497237, "grad_norm": 25.449817657470703, "learning_rate": 6.704596162427489e-06, "loss": 5.211667251586914, "step": 4380 }, { "epoch": 8.815670517327977, "grad_norm": 22.01348304748535, "learning_rate": 6.593038821954485e-06, "loss": 4.383057403564453, "step": 4390 }, { "epoch": 8.835760924158715, "grad_norm": 23.297985076904297, "learning_rate": 6.481481481481481e-06, "loss": 4.567440795898437, "step": 4400 }, { "epoch": 8.855851330989452, "grad_norm": 46.80546951293945, "learning_rate": 6.36992414100848e-06, "loss": 4.4877574920654295, "step": 4410 }, { "epoch": 8.875941737820192, "grad_norm": 14.178481101989746, "learning_rate": 6.2583668005354755e-06, "loss": 4.646826553344726, "step": 4420 }, { "epoch": 8.89603214465093, "grad_norm": 26.017709732055664, "learning_rate": 6.146809460062473e-06, "loss": 4.534694671630859, "step": 4430 }, { "epoch": 8.916122551481667, "grad_norm": 25.873004913330078, "learning_rate": 6.035252119589469e-06, "loss": 5.3920646667480465, "step": 4440 }, { "epoch": 8.936212958312407, "grad_norm": 35.372188568115234, "learning_rate": 5.9236947791164665e-06, "loss": 5.096422958374023, "step": 4450 }, { "epoch": 8.956303365143144, "grad_norm": 32.886024475097656, "learning_rate": 5.812137438643463e-06, "loss": 4.863045883178711, "step": 4460 }, { "epoch": 8.976393771973882, "grad_norm": 12.875351905822754, "learning_rate": 5.70058009817046e-06, "loss": 5.423389434814453, "step": 4470 }, { "epoch": 8.996484178804621, "grad_norm": 25.433364868164062, "learning_rate": 5.589022757697457e-06, "loss": 5.10112190246582, "step": 4480 }, { "epoch": 9.0, "eval_accuracy": 0.8463855421686747, "eval_f1": 0.8461247961548366, "eval_loss": 0.3521043062210083, "eval_runtime": 388.4753, "eval_samples_per_second": 10.255, "eval_steps_per_second": 5.128, "step": 4482 }, { "epoch": 9.01607232546459, "grad_norm": 23.561555862426758, "learning_rate": 5.477465417224454e-06, "loss": 4.897409820556641, "step": 4490 }, { "epoch": 9.03616273229533, "grad_norm": 38.759464263916016, "learning_rate": 5.36590807675145e-06, "loss": 4.951680755615234, "step": 4500 }, { "epoch": 9.056253139126067, "grad_norm": 31.88351821899414, "learning_rate": 5.254350736278448e-06, "loss": 5.266290283203125, "step": 4510 }, { "epoch": 9.076343545956806, "grad_norm": 26.392484664916992, "learning_rate": 5.1427933958054445e-06, "loss": 5.610364532470703, "step": 4520 }, { "epoch": 9.096433952787544, "grad_norm": 40.15414810180664, "learning_rate": 5.031236055332441e-06, "loss": 5.086753845214844, "step": 4530 }, { "epoch": 9.116524359618282, "grad_norm": 21.427326202392578, "learning_rate": 4.919678714859438e-06, "loss": 4.946912384033203, "step": 4540 }, { "epoch": 9.136614766449021, "grad_norm": 45.96141052246094, "learning_rate": 4.8081213743864355e-06, "loss": 5.841570281982422, "step": 4550 }, { "epoch": 9.156705173279759, "grad_norm": 20.726591110229492, "learning_rate": 4.696564033913431e-06, "loss": 4.203896713256836, "step": 4560 }, { "epoch": 9.176795580110497, "grad_norm": 26.498027801513672, "learning_rate": 4.585006693440429e-06, "loss": 4.880064010620117, "step": 4570 }, { "epoch": 9.196885986941236, "grad_norm": 37.2780876159668, "learning_rate": 4.473449352967426e-06, "loss": 4.683342361450196, "step": 4580 }, { "epoch": 9.216976393771974, "grad_norm": 32.95926284790039, "learning_rate": 4.361892012494422e-06, "loss": 4.241422271728515, "step": 4590 }, { "epoch": 9.237066800602712, "grad_norm": 38.193660736083984, "learning_rate": 4.250334672021419e-06, "loss": 5.024569702148438, "step": 4600 }, { "epoch": 9.257157207433451, "grad_norm": 41.15227508544922, "learning_rate": 4.138777331548416e-06, "loss": 4.861378479003906, "step": 4610 }, { "epoch": 9.277247614264189, "grad_norm": 50.86275100708008, "learning_rate": 4.0272199910754126e-06, "loss": 4.926229858398438, "step": 4620 }, { "epoch": 9.297338021094927, "grad_norm": 40.13926315307617, "learning_rate": 3.91566265060241e-06, "loss": 4.608467483520508, "step": 4630 }, { "epoch": 9.317428427925666, "grad_norm": 27.938167572021484, "learning_rate": 3.8041053101294064e-06, "loss": 4.918039321899414, "step": 4640 }, { "epoch": 9.337518834756404, "grad_norm": 37.898468017578125, "learning_rate": 3.6925479696564036e-06, "loss": 4.164243698120117, "step": 4650 }, { "epoch": 9.357609241587141, "grad_norm": 30.704143524169922, "learning_rate": 3.5809906291834007e-06, "loss": 4.754757308959961, "step": 4660 }, { "epoch": 9.377699648417881, "grad_norm": 27.234174728393555, "learning_rate": 3.469433288710397e-06, "loss": 4.536068725585937, "step": 4670 }, { "epoch": 9.397790055248619, "grad_norm": 40.83728790283203, "learning_rate": 3.357875948237394e-06, "loss": 4.871234512329101, "step": 4680 }, { "epoch": 9.417880462079356, "grad_norm": 34.322566986083984, "learning_rate": 3.2463186077643913e-06, "loss": 5.678173065185547, "step": 4690 }, { "epoch": 9.437970868910096, "grad_norm": 21.594993591308594, "learning_rate": 3.1347612672913876e-06, "loss": 4.519970321655274, "step": 4700 }, { "epoch": 9.458061275740834, "grad_norm": 19.62320899963379, "learning_rate": 3.0232039268183848e-06, "loss": 4.683649063110352, "step": 4710 }, { "epoch": 9.478151682571571, "grad_norm": 39.327266693115234, "learning_rate": 2.911646586345382e-06, "loss": 4.583841705322266, "step": 4720 }, { "epoch": 9.49824208940231, "grad_norm": 38.761844635009766, "learning_rate": 2.8000892458723787e-06, "loss": 4.372256469726563, "step": 4730 }, { "epoch": 9.518332496233048, "grad_norm": 12.754522323608398, "learning_rate": 2.6885319053993754e-06, "loss": 4.406585311889648, "step": 4740 }, { "epoch": 9.538422903063786, "grad_norm": 44.86601257324219, "learning_rate": 2.5769745649263725e-06, "loss": 5.148698425292968, "step": 4750 }, { "epoch": 9.558513309894526, "grad_norm": 44.27239990234375, "learning_rate": 2.4654172244533692e-06, "loss": 5.037176513671875, "step": 4760 }, { "epoch": 9.578603716725263, "grad_norm": 36.976619720458984, "learning_rate": 2.353859883980366e-06, "loss": 5.089888381958008, "step": 4770 }, { "epoch": 9.598694123556003, "grad_norm": 32.39399719238281, "learning_rate": 2.242302543507363e-06, "loss": 3.977669525146484, "step": 4780 }, { "epoch": 9.61878453038674, "grad_norm": 21.381723403930664, "learning_rate": 2.13074520303436e-06, "loss": 4.274771881103516, "step": 4790 }, { "epoch": 9.638874937217478, "grad_norm": 64.7051773071289, "learning_rate": 2.0191878625613566e-06, "loss": 4.958181381225586, "step": 4800 }, { "epoch": 9.658965344048218, "grad_norm": 33.4415168762207, "learning_rate": 1.9076305220883537e-06, "loss": 5.07172737121582, "step": 4810 }, { "epoch": 9.679055750878955, "grad_norm": 26.71714210510254, "learning_rate": 1.7960731816153504e-06, "loss": 4.795691680908203, "step": 4820 }, { "epoch": 9.699146157709693, "grad_norm": 53.09344482421875, "learning_rate": 1.6845158411423472e-06, "loss": 4.691039657592773, "step": 4830 }, { "epoch": 9.719236564540433, "grad_norm": 27.439380645751953, "learning_rate": 1.5729585006693443e-06, "loss": 5.053922271728515, "step": 4840 }, { "epoch": 9.73932697137117, "grad_norm": 40.02062225341797, "learning_rate": 1.461401160196341e-06, "loss": 6.021943664550781, "step": 4850 }, { "epoch": 9.759417378201908, "grad_norm": 22.583547592163086, "learning_rate": 1.349843819723338e-06, "loss": 4.261155700683593, "step": 4860 }, { "epoch": 9.779507785032648, "grad_norm": 28.114410400390625, "learning_rate": 1.2382864792503347e-06, "loss": 5.520102691650391, "step": 4870 }, { "epoch": 9.799598191863385, "grad_norm": 34.60763931274414, "learning_rate": 1.1267291387773316e-06, "loss": 5.160928726196289, "step": 4880 }, { "epoch": 9.819688598694123, "grad_norm": 99.95295715332031, "learning_rate": 1.0151717983043286e-06, "loss": 5.416384506225586, "step": 4890 }, { "epoch": 9.839779005524862, "grad_norm": 17.75224494934082, "learning_rate": 9.036144578313253e-07, "loss": 4.775234603881836, "step": 4900 }, { "epoch": 9.8598694123556, "grad_norm": 25.65403938293457, "learning_rate": 7.920571173583222e-07, "loss": 4.709438705444336, "step": 4910 }, { "epoch": 9.879959819186338, "grad_norm": 19.766345977783203, "learning_rate": 6.804997768853191e-07, "loss": 4.9360191345214846, "step": 4920 }, { "epoch": 9.900050226017077, "grad_norm": 29.716949462890625, "learning_rate": 5.689424364123159e-07, "loss": 5.012723922729492, "step": 4930 }, { "epoch": 9.920140632847815, "grad_norm": 28.660503387451172, "learning_rate": 4.5738509593931284e-07, "loss": 4.778982543945313, "step": 4940 }, { "epoch": 9.940231039678553, "grad_norm": 44.6384162902832, "learning_rate": 3.4582775546630967e-07, "loss": 4.651815414428711, "step": 4950 }, { "epoch": 9.960321446509292, "grad_norm": 39.0531005859375, "learning_rate": 2.3427041499330658e-07, "loss": 5.169061279296875, "step": 4960 }, { "epoch": 9.98041185334003, "grad_norm": 41.97426223754883, "learning_rate": 1.2271307452030343e-07, "loss": 4.876540756225586, "step": 4970 }, { "epoch": 10.0, "grad_norm": 23.00905990600586, "learning_rate": 1.1155734047300312e-08, "loss": 4.496361923217774, "step": 4980 }, { "epoch": 10.0, "eval_accuracy": 0.8466365461847389, "eval_f1": 0.8463534876410834, "eval_loss": 0.35189494490623474, "eval_runtime": 289.0861, "eval_samples_per_second": 13.781, "eval_steps_per_second": 6.891, "step": 4980 } ], "logging_steps": 10, "max_steps": 4980, "num_input_tokens_seen": 0, "num_train_epochs": 10, "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": 5.427590971342848e+16, "train_batch_size": 2, "trial_name": null, "trial_params": null }