{
  "best_global_step": 15850,
  "best_metric": 0.5063754320144653,
  "best_model_checkpoint": "output/LightOnOCR-ft-catmus/checkpoint-6500",
  "epoch": 2.0,
  "eval_steps": 50,
  "global_step": 18184,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0054994912970550225,
      "grad_norm": 1.7269556522369385,
      "learning_rate": 5.9871244635193135e-05,
      "loss": 3.2000225830078124,
      "step": 50
    },
    {
      "epoch": 0.0054994912970550225,
      "eval_loss": 2.544747829437256,
      "eval_runtime": 1.22,
      "eval_samples_per_second": 81.966,
      "eval_steps_per_second": 13.934,
      "step": 50
    },
    {
      "epoch": 0.010998982594110045,
      "grad_norm": 2.1817049980163574,
      "learning_rate": 5.970617365467151e-05,
      "loss": 2.204842987060547,
      "step": 100
    },
    {
      "epoch": 0.010998982594110045,
      "eval_loss": 1.9304633140563965,
      "eval_runtime": 1.2142,
      "eval_samples_per_second": 82.358,
      "eval_steps_per_second": 14.001,
      "step": 100
    },
    {
      "epoch": 0.01649847389116507,
      "grad_norm": 2.861886739730835,
      "learning_rate": 5.954110267414989e-05,
      "loss": 1.7260311889648436,
      "step": 150
    },
    {
      "epoch": 0.01649847389116507,
      "eval_loss": 1.7684886455535889,
      "eval_runtime": 1.2169,
      "eval_samples_per_second": 82.178,
      "eval_steps_per_second": 13.97,
      "step": 150
    },
    {
      "epoch": 0.02199796518822009,
      "grad_norm": 2.9910781383514404,
      "learning_rate": 5.937603169362826e-05,
      "loss": 1.5795289611816405,
      "step": 200
    },
    {
      "epoch": 0.02199796518822009,
      "eval_loss": 1.5510659217834473,
      "eval_runtime": 1.2158,
      "eval_samples_per_second": 82.249,
      "eval_steps_per_second": 13.982,
      "step": 200
    },
    {
      "epoch": 0.027497456485275112,
      "grad_norm": 3.234337329864502,
      "learning_rate": 5.921096071310663e-05,
      "loss": 1.4427146911621094,
      "step": 250
    },
    {
      "epoch": 0.027497456485275112,
      "eval_loss": 1.4127395153045654,
      "eval_runtime": 1.2374,
      "eval_samples_per_second": 80.816,
      "eval_steps_per_second": 13.739,
      "step": 250
    },
    {
      "epoch": 0.03299694778233014,
      "grad_norm": 3.6628358364105225,
      "learning_rate": 5.904588973258501e-05,
      "loss": 1.3803778076171875,
      "step": 300
    },
    {
      "epoch": 0.03299694778233014,
      "eval_loss": 1.3498808145523071,
      "eval_runtime": 1.2372,
      "eval_samples_per_second": 80.827,
      "eval_steps_per_second": 13.741,
      "step": 300
    },
    {
      "epoch": 0.03849643907938516,
      "grad_norm": 3.2028181552886963,
      "learning_rate": 5.8880818752063386e-05,
      "loss": 1.2370665740966797,
      "step": 350
    },
    {
      "epoch": 0.03849643907938516,
      "eval_loss": 1.3298417329788208,
      "eval_runtime": 1.2864,
      "eval_samples_per_second": 77.736,
      "eval_steps_per_second": 13.215,
      "step": 350
    },
    {
      "epoch": 0.04399593037644018,
      "grad_norm": 3.344433307647705,
      "learning_rate": 5.8715747771541766e-05,
      "loss": 1.1885470581054687,
      "step": 400
    },
    {
      "epoch": 0.04399593037644018,
      "eval_loss": 1.296607494354248,
      "eval_runtime": 1.2337,
      "eval_samples_per_second": 81.058,
      "eval_steps_per_second": 13.78,
      "step": 400
    },
    {
      "epoch": 0.0494954216734952,
      "grad_norm": 3.601663827896118,
      "learning_rate": 5.855067679102014e-05,
      "loss": 1.149856185913086,
      "step": 450
    },
    {
      "epoch": 0.0494954216734952,
      "eval_loss": 1.264522910118103,
      "eval_runtime": 1.2178,
      "eval_samples_per_second": 82.114,
      "eval_steps_per_second": 13.959,
      "step": 450
    },
    {
      "epoch": 0.054994912970550223,
      "grad_norm": 4.889139175415039,
      "learning_rate": 5.838560581049852e-05,
      "loss": 1.0299188232421874,
      "step": 500
    },
    {
      "epoch": 0.054994912970550223,
      "eval_loss": 1.2139334678649902,
      "eval_runtime": 1.2138,
      "eval_samples_per_second": 82.388,
      "eval_steps_per_second": 14.006,
      "step": 500
    },
    {
      "epoch": 0.060494404267605245,
      "grad_norm": 4.471691608428955,
      "learning_rate": 5.822053482997689e-05,
      "loss": 1.063873519897461,
      "step": 550
    },
    {
      "epoch": 0.060494404267605245,
      "eval_loss": 1.1947441101074219,
      "eval_runtime": 1.2397,
      "eval_samples_per_second": 80.663,
      "eval_steps_per_second": 13.713,
      "step": 550
    },
    {
      "epoch": 0.06599389556466027,
      "grad_norm": 5.005523204803467,
      "learning_rate": 5.805546384945527e-05,
      "loss": 1.0306187438964844,
      "step": 600
    },
    {
      "epoch": 0.06599389556466027,
      "eval_loss": 1.1054185628890991,
      "eval_runtime": 1.2867,
      "eval_samples_per_second": 77.72,
      "eval_steps_per_second": 13.212,
      "step": 600
    },
    {
      "epoch": 0.07149338686171529,
      "grad_norm": 5.433160781860352,
      "learning_rate": 5.7890392868933643e-05,
      "loss": 0.9948115539550781,
      "step": 650
    },
    {
      "epoch": 0.07149338686171529,
      "eval_loss": 1.118335247039795,
      "eval_runtime": 1.2905,
      "eval_samples_per_second": 77.488,
      "eval_steps_per_second": 13.173,
      "step": 650
    },
    {
      "epoch": 0.07699287815877032,
      "grad_norm": 4.089204788208008,
      "learning_rate": 5.7725321888412016e-05,
      "loss": 0.9623870086669922,
      "step": 700
    },
    {
      "epoch": 0.07699287815877032,
      "eval_loss": 1.1011381149291992,
      "eval_runtime": 1.2137,
      "eval_samples_per_second": 82.396,
      "eval_steps_per_second": 14.007,
      "step": 700
    },
    {
      "epoch": 0.08249236945582533,
      "grad_norm": 4.5177459716796875,
      "learning_rate": 5.7560250907890396e-05,
      "loss": 0.9822674560546875,
      "step": 750
    },
    {
      "epoch": 0.08249236945582533,
      "eval_loss": 1.0355230569839478,
      "eval_runtime": 1.2185,
      "eval_samples_per_second": 82.066,
      "eval_steps_per_second": 13.951,
      "step": 750
    },
    {
      "epoch": 0.08799186075288036,
      "grad_norm": 5.314192295074463,
      "learning_rate": 5.7395179927368776e-05,
      "loss": 0.9478108978271484,
      "step": 800
    },
    {
      "epoch": 0.08799186075288036,
      "eval_loss": 1.026939868927002,
      "eval_runtime": 1.2207,
      "eval_samples_per_second": 81.923,
      "eval_steps_per_second": 13.927,
      "step": 800
    },
    {
      "epoch": 0.09349135204993538,
      "grad_norm": 4.419743061065674,
      "learning_rate": 5.723010894684714e-05,
      "loss": 0.9230728149414062,
      "step": 850
    },
    {
      "epoch": 0.09349135204993538,
      "eval_loss": 1.0253421068191528,
      "eval_runtime": 1.2215,
      "eval_samples_per_second": 81.867,
      "eval_steps_per_second": 13.917,
      "step": 850
    },
    {
      "epoch": 0.0989908433469904,
      "grad_norm": 4.689808368682861,
      "learning_rate": 5.706503796632552e-05,
      "loss": 0.9336647033691406,
      "step": 900
    },
    {
      "epoch": 0.0989908433469904,
      "eval_loss": 0.9888076782226562,
      "eval_runtime": 1.2198,
      "eval_samples_per_second": 81.981,
      "eval_steps_per_second": 13.937,
      "step": 900
    },
    {
      "epoch": 0.10449033464404543,
      "grad_norm": 4.178891181945801,
      "learning_rate": 5.68999669858039e-05,
      "loss": 0.8509888458251953,
      "step": 950
    },
    {
      "epoch": 0.10449033464404543,
      "eval_loss": 0.9283347129821777,
      "eval_runtime": 1.2217,
      "eval_samples_per_second": 81.854,
      "eval_steps_per_second": 13.915,
      "step": 950
    },
    {
      "epoch": 0.10998982594110045,
      "grad_norm": 4.549170017242432,
      "learning_rate": 5.6734896005282274e-05,
      "loss": 0.8530999755859375,
      "step": 1000
    },
    {
      "epoch": 0.10998982594110045,
      "eval_loss": 0.9180505871772766,
      "eval_runtime": 1.2178,
      "eval_samples_per_second": 82.114,
      "eval_steps_per_second": 13.959,
      "step": 1000
    },
    {
      "epoch": 0.11548931723815548,
      "grad_norm": 5.8048095703125,
      "learning_rate": 5.656982502476065e-05,
      "loss": 0.8161511993408204,
      "step": 1050
    },
    {
      "epoch": 0.11548931723815548,
      "eval_loss": 0.9668211936950684,
      "eval_runtime": 1.2152,
      "eval_samples_per_second": 82.292,
      "eval_steps_per_second": 13.99,
      "step": 1050
    },
    {
      "epoch": 0.12098880853521049,
      "grad_norm": 4.776002883911133,
      "learning_rate": 5.6404754044239026e-05,
      "loss": 0.8362539672851562,
      "step": 1100
    },
    {
      "epoch": 0.12098880853521049,
      "eval_loss": 0.9686654806137085,
      "eval_runtime": 1.21,
      "eval_samples_per_second": 82.647,
      "eval_steps_per_second": 14.05,
      "step": 1100
    },
    {
      "epoch": 0.1264882998322655,
      "grad_norm": 4.652673721313477,
      "learning_rate": 5.62396830637174e-05,
      "loss": 0.8160650634765625,
      "step": 1150
    },
    {
      "epoch": 0.1264882998322655,
      "eval_loss": 0.9779856204986572,
      "eval_runtime": 1.2121,
      "eval_samples_per_second": 82.5,
      "eval_steps_per_second": 14.025,
      "step": 1150
    },
    {
      "epoch": 0.13198779112932055,
      "grad_norm": 4.988180160522461,
      "learning_rate": 5.607461208319577e-05,
      "loss": 0.8510865020751953,
      "step": 1200
    },
    {
      "epoch": 0.13198779112932055,
      "eval_loss": 0.9197137951850891,
      "eval_runtime": 1.2363,
      "eval_samples_per_second": 80.884,
      "eval_steps_per_second": 13.75,
      "step": 1200
    },
    {
      "epoch": 0.13748728242637556,
      "grad_norm": 5.33247709274292,
      "learning_rate": 5.590954110267415e-05,
      "loss": 0.8393131256103515,
      "step": 1250
    },
    {
      "epoch": 0.13748728242637556,
      "eval_loss": 0.9012404084205627,
      "eval_runtime": 1.2371,
      "eval_samples_per_second": 80.834,
      "eval_steps_per_second": 13.742,
      "step": 1250
    },
    {
      "epoch": 0.14298677372343058,
      "grad_norm": 4.81198787689209,
      "learning_rate": 5.5744470122152525e-05,
      "loss": 0.7720973205566406,
      "step": 1300
    },
    {
      "epoch": 0.14298677372343058,
      "eval_loss": 0.8723539710044861,
      "eval_runtime": 1.2195,
      "eval_samples_per_second": 81.999,
      "eval_steps_per_second": 13.94,
      "step": 1300
    },
    {
      "epoch": 0.1484862650204856,
      "grad_norm": 4.492185115814209,
      "learning_rate": 5.5579399141630904e-05,
      "loss": 0.8052091217041015,
      "step": 1350
    },
    {
      "epoch": 0.1484862650204856,
      "eval_loss": 0.8542118668556213,
      "eval_runtime": 1.2288,
      "eval_samples_per_second": 81.379,
      "eval_steps_per_second": 13.834,
      "step": 1350
    },
    {
      "epoch": 0.15398575631754063,
      "grad_norm": 3.353337287902832,
      "learning_rate": 5.541432816110928e-05,
      "loss": 0.7565326690673828,
      "step": 1400
    },
    {
      "epoch": 0.15398575631754063,
      "eval_loss": 0.8505687117576599,
      "eval_runtime": 1.2947,
      "eval_samples_per_second": 77.24,
      "eval_steps_per_second": 13.131,
      "step": 1400
    },
    {
      "epoch": 0.15948524761459565,
      "grad_norm": 4.658541202545166,
      "learning_rate": 5.524925718058765e-05,
      "loss": 0.7905632781982422,
      "step": 1450
    },
    {
      "epoch": 0.15948524761459565,
      "eval_loss": 0.8416154980659485,
      "eval_runtime": 1.3011,
      "eval_samples_per_second": 76.857,
      "eval_steps_per_second": 13.066,
      "step": 1450
    },
    {
      "epoch": 0.16498473891165066,
      "grad_norm": 4.894554615020752,
      "learning_rate": 5.508418620006603e-05,
      "loss": 0.7522599029541016,
      "step": 1500
    },
    {
      "epoch": 0.16498473891165066,
      "eval_loss": 0.8781094551086426,
      "eval_runtime": 1.3077,
      "eval_samples_per_second": 76.472,
      "eval_steps_per_second": 13.0,
      "step": 1500
    },
    {
      "epoch": 0.1704842302087057,
      "grad_norm": 5.099001407623291,
      "learning_rate": 5.491911521954441e-05,
      "loss": 0.7591278076171875,
      "step": 1550
    },
    {
      "epoch": 0.1704842302087057,
      "eval_loss": 0.8455641269683838,
      "eval_runtime": 1.3309,
      "eval_samples_per_second": 75.138,
      "eval_steps_per_second": 12.773,
      "step": 1550
    },
    {
      "epoch": 0.17598372150576072,
      "grad_norm": 4.108503818511963,
      "learning_rate": 5.4754044239022776e-05,
      "loss": 0.7117195129394531,
      "step": 1600
    },
    {
      "epoch": 0.17598372150576072,
      "eval_loss": 0.8469740152359009,
      "eval_runtime": 1.3312,
      "eval_samples_per_second": 75.123,
      "eval_steps_per_second": 12.771,
      "step": 1600
    },
    {
      "epoch": 0.18148321280281574,
      "grad_norm": 4.5479536056518555,
      "learning_rate": 5.4588973258501155e-05,
      "loss": 0.7624311828613282,
      "step": 1650
    },
    {
      "epoch": 0.18148321280281574,
      "eval_loss": 0.8670312762260437,
      "eval_runtime": 1.3395,
      "eval_samples_per_second": 74.652,
      "eval_steps_per_second": 12.691,
      "step": 1650
    },
    {
      "epoch": 0.18698270409987075,
      "grad_norm": 4.809026718139648,
      "learning_rate": 5.4423902277979535e-05,
      "loss": 0.7137515258789062,
      "step": 1700
    },
    {
      "epoch": 0.18698270409987075,
      "eval_loss": 0.8062080144882202,
      "eval_runtime": 1.3269,
      "eval_samples_per_second": 75.364,
      "eval_steps_per_second": 12.812,
      "step": 1700
    },
    {
      "epoch": 0.1924821953969258,
      "grad_norm": 5.400925636291504,
      "learning_rate": 5.4258831297457914e-05,
      "loss": 0.6972386932373047,
      "step": 1750
    },
    {
      "epoch": 0.1924821953969258,
      "eval_loss": 0.8285601735115051,
      "eval_runtime": 1.3236,
      "eval_samples_per_second": 75.551,
      "eval_steps_per_second": 12.844,
      "step": 1750
    },
    {
      "epoch": 0.1979816866939808,
      "grad_norm": 6.0628461837768555,
      "learning_rate": 5.409376031693628e-05,
      "loss": 0.7547286987304688,
      "step": 1800
    },
    {
      "epoch": 0.1979816866939808,
      "eval_loss": 0.8063403964042664,
      "eval_runtime": 1.3254,
      "eval_samples_per_second": 75.448,
      "eval_steps_per_second": 12.826,
      "step": 1800
    },
    {
      "epoch": 0.20348117799103582,
      "grad_norm": 5.176665306091309,
      "learning_rate": 5.392868933641466e-05,
      "loss": 0.7166018676757813,
      "step": 1850
    },
    {
      "epoch": 0.20348117799103582,
      "eval_loss": 0.7977473735809326,
      "eval_runtime": 1.3331,
      "eval_samples_per_second": 75.013,
      "eval_steps_per_second": 12.752,
      "step": 1850
    },
    {
      "epoch": 0.20898066928809086,
      "grad_norm": 5.566205024719238,
      "learning_rate": 5.376361835589304e-05,
      "loss": 0.7202009582519531,
      "step": 1900
    },
    {
      "epoch": 0.20898066928809086,
      "eval_loss": 0.7941867709159851,
      "eval_runtime": 1.2966,
      "eval_samples_per_second": 77.126,
      "eval_steps_per_second": 13.112,
      "step": 1900
    },
    {
      "epoch": 0.21448016058514588,
      "grad_norm": 6.071581840515137,
      "learning_rate": 5.359854737537141e-05,
      "loss": 0.718297119140625,
      "step": 1950
    },
    {
      "epoch": 0.21448016058514588,
      "eval_loss": 0.8194384574890137,
      "eval_runtime": 1.2884,
      "eval_samples_per_second": 77.613,
      "eval_steps_per_second": 13.194,
      "step": 1950
    },
    {
      "epoch": 0.2199796518822009,
      "grad_norm": 5.566873073577881,
      "learning_rate": 5.3433476394849786e-05,
      "loss": 0.7216673278808594,
      "step": 2000
    },
    {
      "epoch": 0.2199796518822009,
      "eval_loss": 0.7815269231796265,
      "eval_runtime": 1.2875,
      "eval_samples_per_second": 77.668,
      "eval_steps_per_second": 13.204,
      "step": 2000
    },
    {
      "epoch": 0.2254791431792559,
      "grad_norm": 5.567185878753662,
      "learning_rate": 5.3268405414328165e-05,
      "loss": 0.7164375305175781,
      "step": 2050
    },
    {
      "epoch": 0.2254791431792559,
      "eval_loss": 0.8178561925888062,
      "eval_runtime": 1.2891,
      "eval_samples_per_second": 77.574,
      "eval_steps_per_second": 13.188,
      "step": 2050
    },
    {
      "epoch": 0.23097863447631095,
      "grad_norm": 4.171028137207031,
      "learning_rate": 5.310333443380654e-05,
      "loss": 0.6996173095703125,
      "step": 2100
    },
    {
      "epoch": 0.23097863447631095,
      "eval_loss": 0.791594922542572,
      "eval_runtime": 1.287,
      "eval_samples_per_second": 77.698,
      "eval_steps_per_second": 13.209,
      "step": 2100
    },
    {
      "epoch": 0.23647812577336597,
      "grad_norm": 4.468926906585693,
      "learning_rate": 5.293826345328491e-05,
      "loss": 0.685142822265625,
      "step": 2150
    },
    {
      "epoch": 0.23647812577336597,
      "eval_loss": 0.8206081986427307,
      "eval_runtime": 1.2124,
      "eval_samples_per_second": 82.479,
      "eval_steps_per_second": 14.021,
      "step": 2150
    },
    {
      "epoch": 0.24197761707042098,
      "grad_norm": 3.9659266471862793,
      "learning_rate": 5.277319247276329e-05,
      "loss": 0.701788330078125,
      "step": 2200
    },
    {
      "epoch": 0.24197761707042098,
      "eval_loss": 0.7930644750595093,
      "eval_runtime": 1.2014,
      "eval_samples_per_second": 83.24,
      "eval_steps_per_second": 14.151,
      "step": 2200
    },
    {
      "epoch": 0.247477108367476,
      "grad_norm": 4.476805686950684,
      "learning_rate": 5.2608121492241664e-05,
      "loss": 0.710376968383789,
      "step": 2250
    },
    {
      "epoch": 0.247477108367476,
      "eval_loss": 0.7881377339363098,
      "eval_runtime": 1.1999,
      "eval_samples_per_second": 83.337,
      "eval_steps_per_second": 14.167,
      "step": 2250
    },
    {
      "epoch": 0.252976599664531,
      "grad_norm": 3.8596489429473877,
      "learning_rate": 5.244305051172004e-05,
      "loss": 0.7032179260253906,
      "step": 2300
    },
    {
      "epoch": 0.252976599664531,
      "eval_loss": 0.7591221332550049,
      "eval_runtime": 1.2149,
      "eval_samples_per_second": 82.31,
      "eval_steps_per_second": 13.993,
      "step": 2300
    },
    {
      "epoch": 0.2584760909615861,
      "grad_norm": 4.368955135345459,
      "learning_rate": 5.2277979531198416e-05,
      "loss": 0.6489437103271485,
      "step": 2350
    },
    {
      "epoch": 0.2584760909615861,
      "eval_loss": 0.8142778873443604,
      "eval_runtime": 1.2006,
      "eval_samples_per_second": 83.294,
      "eval_steps_per_second": 14.16,
      "step": 2350
    },
    {
      "epoch": 0.2639755822586411,
      "grad_norm": 4.408853530883789,
      "learning_rate": 5.211290855067679e-05,
      "loss": 0.6344734954833985,
      "step": 2400
    },
    {
      "epoch": 0.2639755822586411,
      "eval_loss": 0.789002001285553,
      "eval_runtime": 1.2016,
      "eval_samples_per_second": 83.219,
      "eval_steps_per_second": 14.147,
      "step": 2400
    },
    {
      "epoch": 0.2694750735556961,
      "grad_norm": 4.636422157287598,
      "learning_rate": 5.194783757015517e-05,
      "loss": 0.6603395080566407,
      "step": 2450
    },
    {
      "epoch": 0.2694750735556961,
      "eval_loss": 0.739583432674408,
      "eval_runtime": 1.2017,
      "eval_samples_per_second": 83.216,
      "eval_steps_per_second": 14.147,
      "step": 2450
    },
    {
      "epoch": 0.2749745648527511,
      "grad_norm": 4.370145797729492,
      "learning_rate": 5.178276658963355e-05,
      "loss": 0.6568155670166016,
      "step": 2500
    },
    {
      "epoch": 0.2749745648527511,
      "eval_loss": 0.8292286396026611,
      "eval_runtime": 1.1996,
      "eval_samples_per_second": 83.364,
      "eval_steps_per_second": 14.172,
      "step": 2500
    },
    {
      "epoch": 0.28047405614980614,
      "grad_norm": 4.47123384475708,
      "learning_rate": 5.1617695609111914e-05,
      "loss": 0.6639788055419922,
      "step": 2550
    },
    {
      "epoch": 0.28047405614980614,
      "eval_loss": 0.820250391960144,
      "eval_runtime": 1.2058,
      "eval_samples_per_second": 82.933,
      "eval_steps_per_second": 14.099,
      "step": 2550
    },
    {
      "epoch": 0.28597354744686115,
      "grad_norm": 4.769968509674072,
      "learning_rate": 5.1452624628590294e-05,
      "loss": 0.6434815979003906,
      "step": 2600
    },
    {
      "epoch": 0.28597354744686115,
      "eval_loss": 0.8330257534980774,
      "eval_runtime": 1.2003,
      "eval_samples_per_second": 83.313,
      "eval_steps_per_second": 14.163,
      "step": 2600
    },
    {
      "epoch": 0.29147303874391617,
      "grad_norm": 4.403727054595947,
      "learning_rate": 5.1287553648068674e-05,
      "loss": 0.6872652435302734,
      "step": 2650
    },
    {
      "epoch": 0.29147303874391617,
      "eval_loss": 0.7691981792449951,
      "eval_runtime": 1.1997,
      "eval_samples_per_second": 83.351,
      "eval_steps_per_second": 14.17,
      "step": 2650
    },
    {
      "epoch": 0.2969725300409712,
      "grad_norm": 3.7627687454223633,
      "learning_rate": 5.1122482667547047e-05,
      "loss": 0.625857925415039,
      "step": 2700
    },
    {
      "epoch": 0.2969725300409712,
      "eval_loss": 0.7727508544921875,
      "eval_runtime": 1.2264,
      "eval_samples_per_second": 81.538,
      "eval_steps_per_second": 13.861,
      "step": 2700
    },
    {
      "epoch": 0.30247202133802625,
      "grad_norm": 5.441561222076416,
      "learning_rate": 5.095741168702542e-05,
      "loss": 0.6458732604980468,
      "step": 2750
    },
    {
      "epoch": 0.30247202133802625,
      "eval_loss": 0.7701953053474426,
      "eval_runtime": 1.222,
      "eval_samples_per_second": 81.833,
      "eval_steps_per_second": 13.912,
      "step": 2750
    },
    {
      "epoch": 0.30797151263508127,
      "grad_norm": 4.965064525604248,
      "learning_rate": 5.07923407065038e-05,
      "loss": 0.6677908325195312,
      "step": 2800
    },
    {
      "epoch": 0.30797151263508127,
      "eval_loss": 0.7164813280105591,
      "eval_runtime": 1.2202,
      "eval_samples_per_second": 81.956,
      "eval_steps_per_second": 13.933,
      "step": 2800
    },
    {
      "epoch": 0.3134710039321363,
      "grad_norm": 3.931856870651245,
      "learning_rate": 5.062726972598217e-05,
      "loss": 0.5885476684570312,
      "step": 2850
    },
    {
      "epoch": 0.3134710039321363,
      "eval_loss": 0.7336059808731079,
      "eval_runtime": 1.2203,
      "eval_samples_per_second": 81.948,
      "eval_steps_per_second": 13.931,
      "step": 2850
    },
    {
      "epoch": 0.3189704952291913,
      "grad_norm": 4.760177135467529,
      "learning_rate": 5.046219874546055e-05,
      "loss": 0.6489822387695312,
      "step": 2900
    },
    {
      "epoch": 0.3189704952291913,
      "eval_loss": 0.7551103830337524,
      "eval_runtime": 1.2183,
      "eval_samples_per_second": 82.079,
      "eval_steps_per_second": 13.953,
      "step": 2900
    },
    {
      "epoch": 0.3244699865262463,
      "grad_norm": 4.375728130340576,
      "learning_rate": 5.0297127764938924e-05,
      "loss": 0.6457704162597656,
      "step": 2950
    },
    {
      "epoch": 0.3244699865262463,
      "eval_loss": 0.7187867164611816,
      "eval_runtime": 1.2036,
      "eval_samples_per_second": 83.084,
      "eval_steps_per_second": 14.124,
      "step": 2950
    },
    {
      "epoch": 0.3299694778233013,
      "grad_norm": 4.091928005218506,
      "learning_rate": 5.0132056784417304e-05,
      "loss": 0.6391205596923828,
      "step": 3000
    },
    {
      "epoch": 0.3299694778233013,
      "eval_loss": 0.7715049982070923,
      "eval_runtime": 1.2016,
      "eval_samples_per_second": 83.22,
      "eval_steps_per_second": 14.147,
      "step": 3000
    },
    {
      "epoch": 0.33546896912035634,
      "grad_norm": 4.569828510284424,
      "learning_rate": 4.996698580389568e-05,
      "loss": 0.6714089965820312,
      "step": 3050
    },
    {
      "epoch": 0.33546896912035634,
      "eval_loss": 0.7370268106460571,
      "eval_runtime": 1.2171,
      "eval_samples_per_second": 82.162,
      "eval_steps_per_second": 13.967,
      "step": 3050
    },
    {
      "epoch": 0.3409684604174114,
      "grad_norm": 5.741940975189209,
      "learning_rate": 4.980191482337405e-05,
      "loss": 0.6890049743652343,
      "step": 3100
    },
    {
      "epoch": 0.3409684604174114,
      "eval_loss": 0.7069912552833557,
      "eval_runtime": 1.1974,
      "eval_samples_per_second": 83.514,
      "eval_steps_per_second": 14.197,
      "step": 3100
    },
    {
      "epoch": 0.3464679517144664,
      "grad_norm": 4.857932090759277,
      "learning_rate": 4.963684384285243e-05,
      "loss": 0.5919662475585937,
      "step": 3150
    },
    {
      "epoch": 0.3464679517144664,
      "eval_loss": 0.7350116968154907,
      "eval_runtime": 1.1974,
      "eval_samples_per_second": 83.515,
      "eval_steps_per_second": 14.198,
      "step": 3150
    },
    {
      "epoch": 0.35196744301152144,
      "grad_norm": 4.636399745941162,
      "learning_rate": 4.94717728623308e-05,
      "loss": 0.6361312866210938,
      "step": 3200
    },
    {
      "epoch": 0.35196744301152144,
      "eval_loss": 0.7743600606918335,
      "eval_runtime": 1.271,
      "eval_samples_per_second": 78.677,
      "eval_steps_per_second": 13.375,
      "step": 3200
    },
    {
      "epoch": 0.35746693430857646,
      "grad_norm": 5.155900955200195,
      "learning_rate": 4.930670188180918e-05,
      "loss": 0.602264518737793,
      "step": 3250
    },
    {
      "epoch": 0.35746693430857646,
      "eval_loss": 0.7555291652679443,
      "eval_runtime": 1.2803,
      "eval_samples_per_second": 78.105,
      "eval_steps_per_second": 13.278,
      "step": 3250
    },
    {
      "epoch": 0.36296642560563147,
      "grad_norm": 3.4023196697235107,
      "learning_rate": 4.9141630901287555e-05,
      "loss": 0.5788230133056641,
      "step": 3300
    },
    {
      "epoch": 0.36296642560563147,
      "eval_loss": 0.7717245221138,
      "eval_runtime": 1.3149,
      "eval_samples_per_second": 76.053,
      "eval_steps_per_second": 12.929,
      "step": 3300
    },
    {
      "epoch": 0.3684659169026865,
      "grad_norm": 4.329448223114014,
      "learning_rate": 4.897655992076593e-05,
      "loss": 0.6438528442382813,
      "step": 3350
    },
    {
      "epoch": 0.3684659169026865,
      "eval_loss": 0.6952827572822571,
      "eval_runtime": 1.2957,
      "eval_samples_per_second": 77.176,
      "eval_steps_per_second": 13.12,
      "step": 3350
    },
    {
      "epoch": 0.3739654081997415,
      "grad_norm": 3.610276222229004,
      "learning_rate": 4.881148894024431e-05,
      "loss": 0.6141637802124024,
      "step": 3400
    },
    {
      "epoch": 0.3739654081997415,
      "eval_loss": 0.6926187872886658,
      "eval_runtime": 1.3466,
      "eval_samples_per_second": 74.259,
      "eval_steps_per_second": 12.624,
      "step": 3400
    },
    {
      "epoch": 0.37946489949679657,
      "grad_norm": 6.178794860839844,
      "learning_rate": 4.864641795972269e-05,
      "loss": 0.6356156158447266,
      "step": 3450
    },
    {
      "epoch": 0.37946489949679657,
      "eval_loss": 0.7247772216796875,
      "eval_runtime": 1.3462,
      "eval_samples_per_second": 74.281,
      "eval_steps_per_second": 12.628,
      "step": 3450
    },
    {
      "epoch": 0.3849643907938516,
      "grad_norm": 4.9943695068359375,
      "learning_rate": 4.848134697920105e-05,
      "loss": 0.6148456192016601,
      "step": 3500
    },
    {
      "epoch": 0.3849643907938516,
      "eval_loss": 0.7180845141410828,
      "eval_runtime": 1.3322,
      "eval_samples_per_second": 75.061,
      "eval_steps_per_second": 12.76,
      "step": 3500
    },
    {
      "epoch": 0.3904638820909066,
      "grad_norm": 3.8332393169403076,
      "learning_rate": 4.831627599867943e-05,
      "loss": 0.625141716003418,
      "step": 3550
    },
    {
      "epoch": 0.3904638820909066,
      "eval_loss": 0.6876647472381592,
      "eval_runtime": 1.3382,
      "eval_samples_per_second": 74.73,
      "eval_steps_per_second": 12.704,
      "step": 3550
    },
    {
      "epoch": 0.3959633733879616,
      "grad_norm": 4.58771276473999,
      "learning_rate": 4.815120501815781e-05,
      "loss": 0.6502104187011719,
      "step": 3600
    },
    {
      "epoch": 0.3959633733879616,
      "eval_loss": 0.690920352935791,
      "eval_runtime": 1.343,
      "eval_samples_per_second": 74.46,
      "eval_steps_per_second": 12.658,
      "step": 3600
    },
    {
      "epoch": 0.40146286468501663,
      "grad_norm": 4.435539722442627,
      "learning_rate": 4.7986134037636185e-05,
      "loss": 0.6129857635498047,
      "step": 3650
    },
    {
      "epoch": 0.40146286468501663,
      "eval_loss": 0.6758005023002625,
      "eval_runtime": 1.34,
      "eval_samples_per_second": 74.628,
      "eval_steps_per_second": 12.687,
      "step": 3650
    },
    {
      "epoch": 0.40696235598207164,
      "grad_norm": 4.618966102600098,
      "learning_rate": 4.782106305711456e-05,
      "loss": 0.6234348678588867,
      "step": 3700
    },
    {
      "epoch": 0.40696235598207164,
      "eval_loss": 0.7179376482963562,
      "eval_runtime": 1.3332,
      "eval_samples_per_second": 75.01,
      "eval_steps_per_second": 12.752,
      "step": 3700
    },
    {
      "epoch": 0.41246184727912666,
      "grad_norm": 4.0562052726745605,
      "learning_rate": 4.765599207659294e-05,
      "loss": 0.6168152999877929,
      "step": 3750
    },
    {
      "epoch": 0.41246184727912666,
      "eval_loss": 0.7127401828765869,
      "eval_runtime": 1.3374,
      "eval_samples_per_second": 74.769,
      "eval_steps_per_second": 12.711,
      "step": 3750
    },
    {
      "epoch": 0.41796133857618173,
      "grad_norm": 5.699039459228516,
      "learning_rate": 4.749092109607131e-05,
      "loss": 0.5789441680908203,
      "step": 3800
    },
    {
      "epoch": 0.41796133857618173,
      "eval_loss": 0.6780041456222534,
      "eval_runtime": 1.3483,
      "eval_samples_per_second": 74.167,
      "eval_steps_per_second": 12.608,
      "step": 3800
    },
    {
      "epoch": 0.42346082987323674,
      "grad_norm": 3.523623466491699,
      "learning_rate": 4.7325850115549684e-05,
      "loss": 0.5945124053955078,
      "step": 3850
    },
    {
      "epoch": 0.42346082987323674,
      "eval_loss": 0.695915699005127,
      "eval_runtime": 1.345,
      "eval_samples_per_second": 74.351,
      "eval_steps_per_second": 12.64,
      "step": 3850
    },
    {
      "epoch": 0.42896032117029176,
      "grad_norm": 4.008049488067627,
      "learning_rate": 4.716077913502806e-05,
      "loss": 0.5782461929321289,
      "step": 3900
    },
    {
      "epoch": 0.42896032117029176,
      "eval_loss": 0.6521520018577576,
      "eval_runtime": 1.342,
      "eval_samples_per_second": 74.517,
      "eval_steps_per_second": 12.668,
      "step": 3900
    },
    {
      "epoch": 0.4344598124673468,
      "grad_norm": 4.809508323669434,
      "learning_rate": 4.6995708154506436e-05,
      "loss": 0.5954169464111329,
      "step": 3950
    },
    {
      "epoch": 0.4344598124673468,
      "eval_loss": 0.6668588519096375,
      "eval_runtime": 1.347,
      "eval_samples_per_second": 74.241,
      "eval_steps_per_second": 12.621,
      "step": 3950
    },
    {
      "epoch": 0.4399593037644018,
      "grad_norm": 4.741697788238525,
      "learning_rate": 4.6830637173984816e-05,
      "loss": 0.5780908584594726,
      "step": 4000
    },
    {
      "epoch": 0.4399593037644018,
      "eval_loss": 0.6712077260017395,
      "eval_runtime": 1.3399,
      "eval_samples_per_second": 74.63,
      "eval_steps_per_second": 12.687,
      "step": 4000
    },
    {
      "epoch": 0.4454587950614568,
      "grad_norm": 5.006357192993164,
      "learning_rate": 4.666556619346319e-05,
      "loss": 0.5816222763061524,
      "step": 4050
    },
    {
      "epoch": 0.4454587950614568,
      "eval_loss": 0.659636378288269,
      "eval_runtime": 1.3383,
      "eval_samples_per_second": 74.724,
      "eval_steps_per_second": 12.703,
      "step": 4050
    },
    {
      "epoch": 0.4509582863585118,
      "grad_norm": 4.562034606933594,
      "learning_rate": 4.650049521294156e-05,
      "loss": 0.6115531539916992,
      "step": 4100
    },
    {
      "epoch": 0.4509582863585118,
      "eval_loss": 0.7120453715324402,
      "eval_runtime": 1.3432,
      "eval_samples_per_second": 74.446,
      "eval_steps_per_second": 12.656,
      "step": 4100
    },
    {
      "epoch": 0.4564577776555669,
      "grad_norm": 4.5262837409973145,
      "learning_rate": 4.633542423241994e-05,
      "loss": 0.5980755233764649,
      "step": 4150
    },
    {
      "epoch": 0.4564577776555669,
      "eval_loss": 0.6733386516571045,
      "eval_runtime": 1.3413,
      "eval_samples_per_second": 74.555,
      "eval_steps_per_second": 12.674,
      "step": 4150
    },
    {
      "epoch": 0.4619572689526219,
      "grad_norm": 3.8390605449676514,
      "learning_rate": 4.617035325189832e-05,
      "loss": 0.5741873931884766,
      "step": 4200
    },
    {
      "epoch": 0.4619572689526219,
      "eval_loss": 0.6623669266700745,
      "eval_runtime": 1.341,
      "eval_samples_per_second": 74.57,
      "eval_steps_per_second": 12.677,
      "step": 4200
    },
    {
      "epoch": 0.4674567602496769,
      "grad_norm": 4.214045524597168,
      "learning_rate": 4.6005282271376694e-05,
      "loss": 0.5255369186401367,
      "step": 4250
    },
    {
      "epoch": 0.4674567602496769,
      "eval_loss": 0.6530551910400391,
      "eval_runtime": 1.3425,
      "eval_samples_per_second": 74.487,
      "eval_steps_per_second": 12.663,
      "step": 4250
    },
    {
      "epoch": 0.47295625154673193,
      "grad_norm": 4.7830729484558105,
      "learning_rate": 4.5840211290855067e-05,
      "loss": 0.5830232620239257,
      "step": 4300
    },
    {
      "epoch": 0.47295625154673193,
      "eval_loss": 0.6643821001052856,
      "eval_runtime": 1.344,
      "eval_samples_per_second": 74.407,
      "eval_steps_per_second": 12.649,
      "step": 4300
    },
    {
      "epoch": 0.47845574284378695,
      "grad_norm": 4.745019435882568,
      "learning_rate": 4.5675140310333446e-05,
      "loss": 0.5781446075439454,
      "step": 4350
    },
    {
      "epoch": 0.47845574284378695,
      "eval_loss": 0.6928694844245911,
      "eval_runtime": 1.5854,
      "eval_samples_per_second": 63.074,
      "eval_steps_per_second": 10.723,
      "step": 4350
    },
    {
      "epoch": 0.48395523414084196,
      "grad_norm": 4.537078380584717,
      "learning_rate": 4.5510069329811826e-05,
      "loss": 0.531302490234375,
      "step": 4400
    },
    {
      "epoch": 0.48395523414084196,
      "eval_loss": 0.6292517185211182,
      "eval_runtime": 1.3445,
      "eval_samples_per_second": 74.375,
      "eval_steps_per_second": 12.644,
      "step": 4400
    },
    {
      "epoch": 0.489454725437897,
      "grad_norm": 4.4869384765625,
      "learning_rate": 4.534499834929019e-05,
      "loss": 0.5715638732910157,
      "step": 4450
    },
    {
      "epoch": 0.489454725437897,
      "eval_loss": 0.6663034558296204,
      "eval_runtime": 1.2938,
      "eval_samples_per_second": 77.291,
      "eval_steps_per_second": 13.14,
      "step": 4450
    },
    {
      "epoch": 0.494954216734952,
      "grad_norm": 4.644640922546387,
      "learning_rate": 4.517992736876857e-05,
      "loss": 0.6143413162231446,
      "step": 4500
    },
    {
      "epoch": 0.494954216734952,
      "eval_loss": 0.6727674007415771,
      "eval_runtime": 1.2823,
      "eval_samples_per_second": 77.986,
      "eval_steps_per_second": 13.258,
      "step": 4500
    },
    {
      "epoch": 0.5004537080320071,
      "grad_norm": 4.451071262359619,
      "learning_rate": 4.501485638824695e-05,
      "loss": 0.6003995132446289,
      "step": 4550
    },
    {
      "epoch": 0.5004537080320071,
      "eval_loss": 0.7084936499595642,
      "eval_runtime": 1.292,
      "eval_samples_per_second": 77.4,
      "eval_steps_per_second": 13.158,
      "step": 4550
    },
    {
      "epoch": 0.505953199329062,
      "grad_norm": 3.566272020339966,
      "learning_rate": 4.4849785407725324e-05,
      "loss": 0.5423797607421875,
      "step": 4600
    },
    {
      "epoch": 0.505953199329062,
      "eval_loss": 0.6627475023269653,
      "eval_runtime": 1.2898,
      "eval_samples_per_second": 77.531,
      "eval_steps_per_second": 13.18,
      "step": 4600
    },
    {
      "epoch": 0.5114526906261171,
      "grad_norm": 4.810975074768066,
      "learning_rate": 4.46847144272037e-05,
      "loss": 0.6348634719848633,
      "step": 4650
    },
    {
      "epoch": 0.5114526906261171,
      "eval_loss": 0.5990252494812012,
      "eval_runtime": 1.2836,
      "eval_samples_per_second": 77.908,
      "eval_steps_per_second": 13.244,
      "step": 4650
    },
    {
      "epoch": 0.5169521819231722,
      "grad_norm": 4.475234031677246,
      "learning_rate": 4.451964344668208e-05,
      "loss": 0.5570141220092774,
      "step": 4700
    },
    {
      "epoch": 0.5169521819231722,
      "eval_loss": 0.6244956254959106,
      "eval_runtime": 1.2837,
      "eval_samples_per_second": 77.898,
      "eval_steps_per_second": 13.243,
      "step": 4700
    },
    {
      "epoch": 0.5224516732202271,
      "grad_norm": 4.3085103034973145,
      "learning_rate": 4.435457246616045e-05,
      "loss": 0.55887451171875,
      "step": 4750
    },
    {
      "epoch": 0.5224516732202271,
      "eval_loss": 0.6636219620704651,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 78.068,
      "eval_steps_per_second": 13.272,
      "step": 4750
    },
    {
      "epoch": 0.5279511645172822,
      "grad_norm": 3.598691940307617,
      "learning_rate": 4.418950148563882e-05,
      "loss": 0.5753656005859376,
      "step": 4800
    },
    {
      "epoch": 0.5279511645172822,
      "eval_loss": 0.6499161720275879,
      "eval_runtime": 1.2822,
      "eval_samples_per_second": 77.991,
      "eval_steps_per_second": 13.258,
      "step": 4800
    },
    {
      "epoch": 0.5334506558143371,
      "grad_norm": 4.494378089904785,
      "learning_rate": 4.40244305051172e-05,
      "loss": 0.5845529174804688,
      "step": 4850
    },
    {
      "epoch": 0.5334506558143371,
      "eval_loss": 0.629128634929657,
      "eval_runtime": 1.5134,
      "eval_samples_per_second": 66.078,
      "eval_steps_per_second": 11.233,
      "step": 4850
    },
    {
      "epoch": 0.5389501471113922,
      "grad_norm": 4.149122714996338,
      "learning_rate": 4.3859359524595575e-05,
      "loss": 0.527508659362793,
      "step": 4900
    },
    {
      "epoch": 0.5389501471113922,
      "eval_loss": 0.6683360934257507,
      "eval_runtime": 1.2806,
      "eval_samples_per_second": 78.088,
      "eval_steps_per_second": 13.275,
      "step": 4900
    },
    {
      "epoch": 0.5444496384084472,
      "grad_norm": 4.04086971282959,
      "learning_rate": 4.3694288544073955e-05,
      "loss": 0.602709732055664,
      "step": 4950
    },
    {
      "epoch": 0.5444496384084472,
      "eval_loss": 0.646293044090271,
      "eval_runtime": 1.2828,
      "eval_samples_per_second": 77.952,
      "eval_steps_per_second": 13.252,
      "step": 4950
    },
    {
      "epoch": 0.5499491297055022,
      "grad_norm": 4.0907440185546875,
      "learning_rate": 4.352921756355233e-05,
      "loss": 0.5631252670288086,
      "step": 5000
    },
    {
      "epoch": 0.5499491297055022,
      "eval_loss": 0.6324547529220581,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 78.07,
      "eval_steps_per_second": 13.272,
      "step": 5000
    },
    {
      "epoch": 0.5554486210025573,
      "grad_norm": 4.2775654792785645,
      "learning_rate": 4.33641465830307e-05,
      "loss": 0.5570418930053711,
      "step": 5050
    },
    {
      "epoch": 0.5554486210025573,
      "eval_loss": 0.6621595621109009,
      "eval_runtime": 1.2825,
      "eval_samples_per_second": 77.971,
      "eval_steps_per_second": 13.255,
      "step": 5050
    },
    {
      "epoch": 0.5609481122996123,
      "grad_norm": 4.414310932159424,
      "learning_rate": 4.319907560250908e-05,
      "loss": 0.5383467483520508,
      "step": 5100
    },
    {
      "epoch": 0.5609481122996123,
      "eval_loss": 0.6726260185241699,
      "eval_runtime": 1.2823,
      "eval_samples_per_second": 77.983,
      "eval_steps_per_second": 13.257,
      "step": 5100
    },
    {
      "epoch": 0.5664476035966673,
      "grad_norm": 3.679974317550659,
      "learning_rate": 4.303400462198746e-05,
      "loss": 0.5569720840454102,
      "step": 5150
    },
    {
      "epoch": 0.5664476035966673,
      "eval_loss": 0.6547858715057373,
      "eval_runtime": 1.289,
      "eval_samples_per_second": 77.579,
      "eval_steps_per_second": 13.188,
      "step": 5150
    },
    {
      "epoch": 0.5719470948937223,
      "grad_norm": 5.782617568969727,
      "learning_rate": 4.2868933641465826e-05,
      "loss": 0.5539520263671875,
      "step": 5200
    },
    {
      "epoch": 0.5719470948937223,
      "eval_loss": 0.6701158881187439,
      "eval_runtime": 1.2849,
      "eval_samples_per_second": 77.825,
      "eval_steps_per_second": 13.23,
      "step": 5200
    },
    {
      "epoch": 0.5774465861907774,
      "grad_norm": 4.194858074188232,
      "learning_rate": 4.2703862660944205e-05,
      "loss": 0.5348934173583985,
      "step": 5250
    },
    {
      "epoch": 0.5774465861907774,
      "eval_loss": 0.6580336093902588,
      "eval_runtime": 1.2831,
      "eval_samples_per_second": 77.938,
      "eval_steps_per_second": 13.249,
      "step": 5250
    },
    {
      "epoch": 0.5829460774878323,
      "grad_norm": 4.302168369293213,
      "learning_rate": 4.2538791680422585e-05,
      "loss": 0.5106255340576172,
      "step": 5300
    },
    {
      "epoch": 0.5829460774878323,
      "eval_loss": 0.6552238464355469,
      "eval_runtime": 1.2852,
      "eval_samples_per_second": 77.81,
      "eval_steps_per_second": 13.228,
      "step": 5300
    },
    {
      "epoch": 0.5884455687848874,
      "grad_norm": 4.042543411254883,
      "learning_rate": 4.237372069990096e-05,
      "loss": 0.5317581558227539,
      "step": 5350
    },
    {
      "epoch": 0.5884455687848874,
      "eval_loss": 0.6482524275779724,
      "eval_runtime": 1.5001,
      "eval_samples_per_second": 66.661,
      "eval_steps_per_second": 11.332,
      "step": 5350
    },
    {
      "epoch": 0.5939450600819424,
      "grad_norm": 4.4569830894470215,
      "learning_rate": 4.220864971937933e-05,
      "loss": 0.5747990036010742,
      "step": 5400
    },
    {
      "epoch": 0.5939450600819424,
      "eval_loss": 0.6177729368209839,
      "eval_runtime": 1.2798,
      "eval_samples_per_second": 78.134,
      "eval_steps_per_second": 13.283,
      "step": 5400
    },
    {
      "epoch": 0.5994445513789974,
      "grad_norm": 4.751041889190674,
      "learning_rate": 4.204357873885771e-05,
      "loss": 0.5374135971069336,
      "step": 5450
    },
    {
      "epoch": 0.5994445513789974,
      "eval_loss": 0.6517400145530701,
      "eval_runtime": 1.28,
      "eval_samples_per_second": 78.128,
      "eval_steps_per_second": 13.282,
      "step": 5450
    },
    {
      "epoch": 0.6049440426760525,
      "grad_norm": 7.24479341506958,
      "learning_rate": 4.187850775833609e-05,
      "loss": 0.5593222045898437,
      "step": 5500
    },
    {
      "epoch": 0.6049440426760525,
      "eval_loss": 0.6892206072807312,
      "eval_runtime": 1.2818,
      "eval_samples_per_second": 78.014,
      "eval_steps_per_second": 13.262,
      "step": 5500
    },
    {
      "epoch": 0.6104435339731075,
      "grad_norm": 4.312963008880615,
      "learning_rate": 4.171343677781446e-05,
      "loss": 0.5525634002685547,
      "step": 5550
    },
    {
      "epoch": 0.6104435339731075,
      "eval_loss": 0.6747671365737915,
      "eval_runtime": 1.2815,
      "eval_samples_per_second": 78.036,
      "eval_steps_per_second": 13.266,
      "step": 5550
    },
    {
      "epoch": 0.6159430252701625,
      "grad_norm": 4.606757164001465,
      "learning_rate": 4.1548365797292836e-05,
      "loss": 0.5449155807495117,
      "step": 5600
    },
    {
      "epoch": 0.6159430252701625,
      "eval_loss": 0.6547083854675293,
      "eval_runtime": 1.2835,
      "eval_samples_per_second": 77.914,
      "eval_steps_per_second": 13.245,
      "step": 5600
    },
    {
      "epoch": 0.6214425165672175,
      "grad_norm": 5.024621486663818,
      "learning_rate": 4.1383294816771216e-05,
      "loss": 0.6019486618041993,
      "step": 5650
    },
    {
      "epoch": 0.6214425165672175,
      "eval_loss": 0.6467494964599609,
      "eval_runtime": 1.2839,
      "eval_samples_per_second": 77.889,
      "eval_steps_per_second": 13.241,
      "step": 5650
    },
    {
      "epoch": 0.6269420078642726,
      "grad_norm": 4.251932144165039,
      "learning_rate": 4.121822383624959e-05,
      "loss": 0.5073886489868165,
      "step": 5700
    },
    {
      "epoch": 0.6269420078642726,
      "eval_loss": 0.6638882160186768,
      "eval_runtime": 1.2832,
      "eval_samples_per_second": 77.932,
      "eval_steps_per_second": 13.249,
      "step": 5700
    },
    {
      "epoch": 0.6324414991613275,
      "grad_norm": 3.3922533988952637,
      "learning_rate": 4.105315285572796e-05,
      "loss": 0.531150894165039,
      "step": 5750
    },
    {
      "epoch": 0.6324414991613275,
      "eval_loss": 0.6248385310173035,
      "eval_runtime": 1.2919,
      "eval_samples_per_second": 77.406,
      "eval_steps_per_second": 13.159,
      "step": 5750
    },
    {
      "epoch": 0.6379409904583826,
      "grad_norm": 4.290137767791748,
      "learning_rate": 4.088808187520634e-05,
      "loss": 0.5194898986816406,
      "step": 5800
    },
    {
      "epoch": 0.6379409904583826,
      "eval_loss": 0.6306109428405762,
      "eval_runtime": 1.2834,
      "eval_samples_per_second": 77.918,
      "eval_steps_per_second": 13.246,
      "step": 5800
    },
    {
      "epoch": 0.6434404817554377,
      "grad_norm": 4.854128837585449,
      "learning_rate": 4.0723010894684714e-05,
      "loss": 0.5465607833862305,
      "step": 5850
    },
    {
      "epoch": 0.6434404817554377,
      "eval_loss": 0.6254453063011169,
      "eval_runtime": 1.5113,
      "eval_samples_per_second": 66.169,
      "eval_steps_per_second": 11.249,
      "step": 5850
    },
    {
      "epoch": 0.6489399730524926,
      "grad_norm": 4.647885799407959,
      "learning_rate": 4.0557939914163093e-05,
      "loss": 0.5407907104492188,
      "step": 5900
    },
    {
      "epoch": 0.6489399730524926,
      "eval_loss": 0.6638280749320984,
      "eval_runtime": 1.2958,
      "eval_samples_per_second": 77.17,
      "eval_steps_per_second": 13.119,
      "step": 5900
    },
    {
      "epoch": 0.6544394643495477,
      "grad_norm": 4.279372215270996,
      "learning_rate": 4.0392868933641466e-05,
      "loss": 0.5451357269287109,
      "step": 5950
    },
    {
      "epoch": 0.6544394643495477,
      "eval_loss": 0.6228541731834412,
      "eval_runtime": 1.3241,
      "eval_samples_per_second": 75.524,
      "eval_steps_per_second": 12.839,
      "step": 5950
    },
    {
      "epoch": 0.6599389556466027,
      "grad_norm": 4.0558247566223145,
      "learning_rate": 4.022779795311984e-05,
      "loss": 0.5368893814086914,
      "step": 6000
    },
    {
      "epoch": 0.6599389556466027,
      "eval_loss": 0.6732752323150635,
      "eval_runtime": 1.3368,
      "eval_samples_per_second": 74.807,
      "eval_steps_per_second": 12.717,
      "step": 6000
    },
    {
      "epoch": 0.6654384469436577,
      "grad_norm": 3.353104591369629,
      "learning_rate": 4.006272697259822e-05,
      "loss": 0.5184137344360351,
      "step": 6050
    },
    {
      "epoch": 0.6654384469436577,
      "eval_loss": 0.6266540884971619,
      "eval_runtime": 1.3374,
      "eval_samples_per_second": 74.773,
      "eval_steps_per_second": 12.711,
      "step": 6050
    },
    {
      "epoch": 0.6709379382407127,
      "grad_norm": 3.8511996269226074,
      "learning_rate": 3.98976559920766e-05,
      "loss": 0.5407165145874023,
      "step": 6100
    },
    {
      "epoch": 0.6709379382407127,
      "eval_loss": 0.6703444123268127,
      "eval_runtime": 1.3374,
      "eval_samples_per_second": 74.77,
      "eval_steps_per_second": 12.711,
      "step": 6100
    },
    {
      "epoch": 0.6764374295377678,
      "grad_norm": 3.9859249591827393,
      "learning_rate": 3.9732585011554965e-05,
      "loss": 0.4901425552368164,
      "step": 6150
    },
    {
      "epoch": 0.6764374295377678,
      "eval_loss": 0.6332722902297974,
      "eval_runtime": 1.341,
      "eval_samples_per_second": 74.569,
      "eval_steps_per_second": 12.677,
      "step": 6150
    },
    {
      "epoch": 0.6819369208348228,
      "grad_norm": 3.666247844696045,
      "learning_rate": 3.9567514031033344e-05,
      "loss": 0.5188226318359375,
      "step": 6200
    },
    {
      "epoch": 0.6819369208348228,
      "eval_loss": 0.5851776599884033,
      "eval_runtime": 1.3337,
      "eval_samples_per_second": 74.982,
      "eval_steps_per_second": 12.747,
      "step": 6200
    },
    {
      "epoch": 0.6874364121318778,
      "grad_norm": 4.355357646942139,
      "learning_rate": 3.9402443050511724e-05,
      "loss": 0.523404426574707,
      "step": 6250
    },
    {
      "epoch": 0.6874364121318778,
      "eval_loss": 0.5948991179466248,
      "eval_runtime": 1.3477,
      "eval_samples_per_second": 74.199,
      "eval_steps_per_second": 12.614,
      "step": 6250
    },
    {
      "epoch": 0.6929359034289329,
      "grad_norm": 4.099778652191162,
      "learning_rate": 3.92373720699901e-05,
      "loss": 0.5017270278930664,
      "step": 6300
    },
    {
      "epoch": 0.6929359034289329,
      "eval_loss": 0.6322646737098694,
      "eval_runtime": 1.3296,
      "eval_samples_per_second": 75.208,
      "eval_steps_per_second": 12.785,
      "step": 6300
    },
    {
      "epoch": 0.6984353947259878,
      "grad_norm": 5.135687351226807,
      "learning_rate": 3.907230108946847e-05,
      "loss": 0.5303592300415039,
      "step": 6350
    },
    {
      "epoch": 0.6984353947259878,
      "eval_loss": 0.6268444657325745,
      "eval_runtime": 1.5763,
      "eval_samples_per_second": 63.442,
      "eval_steps_per_second": 10.785,
      "step": 6350
    },
    {
      "epoch": 0.7039348860230429,
      "grad_norm": 4.834221839904785,
      "learning_rate": 3.890723010894685e-05,
      "loss": 0.5274005889892578,
      "step": 6400
    },
    {
      "epoch": 0.7039348860230429,
      "eval_loss": 0.5901980996131897,
      "eval_runtime": 1.3333,
      "eval_samples_per_second": 75.003,
      "eval_steps_per_second": 12.75,
      "step": 6400
    },
    {
      "epoch": 0.7094343773200978,
      "grad_norm": 5.028069496154785,
      "learning_rate": 3.874215912842522e-05,
      "loss": 0.5233419799804687,
      "step": 6450
    },
    {
      "epoch": 0.7094343773200978,
      "eval_loss": 0.6389637589454651,
      "eval_runtime": 1.2872,
      "eval_samples_per_second": 77.685,
      "eval_steps_per_second": 13.206,
      "step": 6450
    },
    {
      "epoch": 0.7149338686171529,
      "grad_norm": 4.620915412902832,
      "learning_rate": 3.85770881479036e-05,
      "loss": 0.5316643905639649,
      "step": 6500
    },
    {
      "epoch": 0.7149338686171529,
      "eval_loss": 0.5779242515563965,
      "eval_runtime": 1.2776,
      "eval_samples_per_second": 78.271,
      "eval_steps_per_second": 13.306,
      "step": 6500
    },
    {
      "epoch": 0.720433359914208,
      "grad_norm": 3.9142255783081055,
      "learning_rate": 3.8412017167381975e-05,
      "loss": 0.4801639175415039,
      "step": 6550
    },
    {
      "epoch": 0.720433359914208,
      "eval_loss": 0.5951541662216187,
      "eval_runtime": 1.2302,
      "eval_samples_per_second": 81.288,
      "eval_steps_per_second": 13.819,
      "step": 6550
    },
    {
      "epoch": 0.7259328512112629,
      "grad_norm": 4.454485893249512,
      "learning_rate": 3.824694618686035e-05,
      "loss": 0.5149478912353516,
      "step": 6600
    },
    {
      "epoch": 0.7259328512112629,
      "eval_loss": 0.5860444903373718,
      "eval_runtime": 1.235,
      "eval_samples_per_second": 80.974,
      "eval_steps_per_second": 13.766,
      "step": 6600
    },
    {
      "epoch": 0.731432342508318,
      "grad_norm": 4.176424026489258,
      "learning_rate": 3.808187520633873e-05,
      "loss": 0.543246192932129,
      "step": 6650
    },
    {
      "epoch": 0.731432342508318,
      "eval_loss": 0.5805695056915283,
      "eval_runtime": 1.2369,
      "eval_samples_per_second": 80.844,
      "eval_steps_per_second": 13.744,
      "step": 6650
    },
    {
      "epoch": 0.736931833805373,
      "grad_norm": 3.361717462539673,
      "learning_rate": 3.79168042258171e-05,
      "loss": 0.5410548400878906,
      "step": 6700
    },
    {
      "epoch": 0.736931833805373,
      "eval_loss": 0.5974660515785217,
      "eval_runtime": 1.2286,
      "eval_samples_per_second": 81.396,
      "eval_steps_per_second": 13.837,
      "step": 6700
    },
    {
      "epoch": 0.742431325102428,
      "grad_norm": 5.069472312927246,
      "learning_rate": 3.775173324529548e-05,
      "loss": 0.5026102447509766,
      "step": 6750
    },
    {
      "epoch": 0.742431325102428,
      "eval_loss": 0.5945417284965515,
      "eval_runtime": 1.2116,
      "eval_samples_per_second": 82.533,
      "eval_steps_per_second": 14.031,
      "step": 6750
    },
    {
      "epoch": 0.747930816399483,
      "grad_norm": 4.298215389251709,
      "learning_rate": 3.758666226477385e-05,
      "loss": 0.5604416275024414,
      "step": 6800
    },
    {
      "epoch": 0.747930816399483,
      "eval_loss": 0.5883623361587524,
      "eval_runtime": 1.2141,
      "eval_samples_per_second": 82.363,
      "eval_steps_per_second": 14.002,
      "step": 6800
    },
    {
      "epoch": 0.7534303076965381,
      "grad_norm": 3.469435930252075,
      "learning_rate": 3.742159128425223e-05,
      "loss": 0.5037693023681641,
      "step": 6850
    },
    {
      "epoch": 0.7534303076965381,
      "eval_loss": 0.5655568838119507,
      "eval_runtime": 1.3814,
      "eval_samples_per_second": 72.389,
      "eval_steps_per_second": 12.306,
      "step": 6850
    },
    {
      "epoch": 0.7589297989935931,
      "grad_norm": 4.014948844909668,
      "learning_rate": 3.7256520303730605e-05,
      "loss": 0.5645696258544922,
      "step": 6900
    },
    {
      "epoch": 0.7589297989935931,
      "eval_loss": 0.6064311265945435,
      "eval_runtime": 1.2076,
      "eval_samples_per_second": 82.809,
      "eval_steps_per_second": 14.078,
      "step": 6900
    },
    {
      "epoch": 0.7644292902906481,
      "grad_norm": 3.9340033531188965,
      "learning_rate": 3.709144932320898e-05,
      "loss": 0.5047724914550781,
      "step": 6950
    },
    {
      "epoch": 0.7644292902906481,
      "eval_loss": 0.5839043259620667,
      "eval_runtime": 1.221,
      "eval_samples_per_second": 81.901,
      "eval_steps_per_second": 13.923,
      "step": 6950
    },
    {
      "epoch": 0.7699287815877032,
      "grad_norm": 3.939054250717163,
      "learning_rate": 3.692637834268736e-05,
      "loss": 0.5168508529663086,
      "step": 7000
    },
    {
      "epoch": 0.7699287815877032,
      "eval_loss": 0.5967159867286682,
      "eval_runtime": 1.2228,
      "eval_samples_per_second": 81.776,
      "eval_steps_per_second": 13.902,
      "step": 7000
    },
    {
      "epoch": 0.7754282728847581,
      "grad_norm": 4.098312854766846,
      "learning_rate": 3.676130736216574e-05,
      "loss": 0.49574569702148436,
      "step": 7050
    },
    {
      "epoch": 0.7754282728847581,
      "eval_loss": 0.6113559603691101,
      "eval_runtime": 1.2197,
      "eval_samples_per_second": 81.991,
      "eval_steps_per_second": 13.938,
      "step": 7050
    },
    {
      "epoch": 0.7809277641818132,
      "grad_norm": 5.130489826202393,
      "learning_rate": 3.6596236381644103e-05,
      "loss": 0.5368572235107422,
      "step": 7100
    },
    {
      "epoch": 0.7809277641818132,
      "eval_loss": 0.5671849250793457,
      "eval_runtime": 1.2087,
      "eval_samples_per_second": 82.733,
      "eval_steps_per_second": 14.065,
      "step": 7100
    },
    {
      "epoch": 0.7864272554788682,
      "grad_norm": 3.2629666328430176,
      "learning_rate": 3.643116540112248e-05,
      "loss": 0.5247505569458008,
      "step": 7150
    },
    {
      "epoch": 0.7864272554788682,
      "eval_loss": 0.5848333835601807,
      "eval_runtime": 1.2165,
      "eval_samples_per_second": 82.205,
      "eval_steps_per_second": 13.975,
      "step": 7150
    },
    {
      "epoch": 0.7919267467759232,
      "grad_norm": 3.4071853160858154,
      "learning_rate": 3.626609442060086e-05,
      "loss": 0.5215546417236329,
      "step": 7200
    },
    {
      "epoch": 0.7919267467759232,
      "eval_loss": 0.5874826312065125,
      "eval_runtime": 1.2062,
      "eval_samples_per_second": 82.907,
      "eval_steps_per_second": 14.094,
      "step": 7200
    },
    {
      "epoch": 0.7974262380729783,
      "grad_norm": 4.264019966125488,
      "learning_rate": 3.6101023440079236e-05,
      "loss": 0.48300968170166014,
      "step": 7250
    },
    {
      "epoch": 0.7974262380729783,
      "eval_loss": 0.6169635057449341,
      "eval_runtime": 1.2014,
      "eval_samples_per_second": 83.24,
      "eval_steps_per_second": 14.151,
      "step": 7250
    },
    {
      "epoch": 0.8029257293700333,
      "grad_norm": 3.845081090927124,
      "learning_rate": 3.593595245955761e-05,
      "loss": 0.5431819152832031,
      "step": 7300
    },
    {
      "epoch": 0.8029257293700333,
      "eval_loss": 0.5864665508270264,
      "eval_runtime": 1.1999,
      "eval_samples_per_second": 83.339,
      "eval_steps_per_second": 14.168,
      "step": 7300
    },
    {
      "epoch": 0.8084252206670883,
      "grad_norm": 4.696225166320801,
      "learning_rate": 3.577088147903599e-05,
      "loss": 0.5017805480957032,
      "step": 7350
    },
    {
      "epoch": 0.8084252206670883,
      "eval_loss": 0.5771105289459229,
      "eval_runtime": 1.3868,
      "eval_samples_per_second": 72.106,
      "eval_steps_per_second": 12.258,
      "step": 7350
    },
    {
      "epoch": 0.8139247119641433,
      "grad_norm": 3.846862316131592,
      "learning_rate": 3.560581049851436e-05,
      "loss": 0.4925709915161133,
      "step": 7400
    },
    {
      "epoch": 0.8139247119641433,
      "eval_loss": 0.5872745513916016,
      "eval_runtime": 1.2193,
      "eval_samples_per_second": 82.016,
      "eval_steps_per_second": 13.943,
      "step": 7400
    },
    {
      "epoch": 0.8194242032611984,
      "grad_norm": 5.725467681884766,
      "learning_rate": 3.544073951799274e-05,
      "loss": 0.5305783081054688,
      "step": 7450
    },
    {
      "epoch": 0.8194242032611984,
      "eval_loss": 0.5858078002929688,
      "eval_runtime": 1.209,
      "eval_samples_per_second": 82.716,
      "eval_steps_per_second": 14.062,
      "step": 7450
    },
    {
      "epoch": 0.8249236945582533,
      "grad_norm": 5.1305766105651855,
      "learning_rate": 3.5275668537471114e-05,
      "loss": 0.49862171173095704,
      "step": 7500
    },
    {
      "epoch": 0.8249236945582533,
      "eval_loss": 0.5829967260360718,
      "eval_runtime": 1.2108,
      "eval_samples_per_second": 82.588,
      "eval_steps_per_second": 14.04,
      "step": 7500
    },
    {
      "epoch": 0.8304231858553084,
      "grad_norm": 3.6588644981384277,
      "learning_rate": 3.5110597556949486e-05,
      "loss": 0.47825916290283205,
      "step": 7550
    },
    {
      "epoch": 0.8304231858553084,
      "eval_loss": 0.6038760542869568,
      "eval_runtime": 1.2158,
      "eval_samples_per_second": 82.251,
      "eval_steps_per_second": 13.983,
      "step": 7550
    },
    {
      "epoch": 0.8359226771523635,
      "grad_norm": 4.205902576446533,
      "learning_rate": 3.4945526576427866e-05,
      "loss": 0.49293697357177735,
      "step": 7600
    },
    {
      "epoch": 0.8359226771523635,
      "eval_loss": 0.5801113843917847,
      "eval_runtime": 1.2352,
      "eval_samples_per_second": 80.957,
      "eval_steps_per_second": 13.763,
      "step": 7600
    },
    {
      "epoch": 0.8414221684494184,
      "grad_norm": 3.2005882263183594,
      "learning_rate": 3.478045559590624e-05,
      "loss": 0.4907111740112305,
      "step": 7650
    },
    {
      "epoch": 0.8414221684494184,
      "eval_loss": 0.5856965184211731,
      "eval_runtime": 1.2264,
      "eval_samples_per_second": 81.54,
      "eval_steps_per_second": 13.862,
      "step": 7650
    },
    {
      "epoch": 0.8469216597464735,
      "grad_norm": 5.1610636711120605,
      "learning_rate": 3.461538461538461e-05,
      "loss": 0.5118446731567383,
      "step": 7700
    },
    {
      "epoch": 0.8469216597464735,
      "eval_loss": 0.5943632125854492,
      "eval_runtime": 1.2029,
      "eval_samples_per_second": 83.135,
      "eval_steps_per_second": 14.133,
      "step": 7700
    },
    {
      "epoch": 0.8524211510435284,
      "grad_norm": 3.638803482055664,
      "learning_rate": 3.445031363486299e-05,
      "loss": 0.5173551559448242,
      "step": 7750
    },
    {
      "epoch": 0.8524211510435284,
      "eval_loss": 0.5883214473724365,
      "eval_runtime": 1.2146,
      "eval_samples_per_second": 82.334,
      "eval_steps_per_second": 13.997,
      "step": 7750
    },
    {
      "epoch": 0.8579206423405835,
      "grad_norm": 4.749381065368652,
      "learning_rate": 3.428524265434137e-05,
      "loss": 0.5153055953979492,
      "step": 7800
    },
    {
      "epoch": 0.8579206423405835,
      "eval_loss": 0.5808895230293274,
      "eval_runtime": 1.2469,
      "eval_samples_per_second": 80.201,
      "eval_steps_per_second": 13.634,
      "step": 7800
    },
    {
      "epoch": 0.8634201336376385,
      "grad_norm": 4.376150608062744,
      "learning_rate": 3.4120171673819744e-05,
      "loss": 0.5378147506713867,
      "step": 7850
    },
    {
      "epoch": 0.8634201336376385,
      "eval_loss": 0.5930312871932983,
      "eval_runtime": 1.3832,
      "eval_samples_per_second": 72.299,
      "eval_steps_per_second": 12.291,
      "step": 7850
    },
    {
      "epoch": 0.8689196249346935,
      "grad_norm": 4.232579708099365,
      "learning_rate": 3.395510069329812e-05,
      "loss": 0.505134048461914,
      "step": 7900
    },
    {
      "epoch": 0.8689196249346935,
      "eval_loss": 0.6020961999893188,
      "eval_runtime": 1.2142,
      "eval_samples_per_second": 82.356,
      "eval_steps_per_second": 14.0,
      "step": 7900
    },
    {
      "epoch": 0.8744191162317486,
      "grad_norm": 5.355160713195801,
      "learning_rate": 3.3790029712776497e-05,
      "loss": 0.5102433776855468,
      "step": 7950
    },
    {
      "epoch": 0.8744191162317486,
      "eval_loss": 0.5917235016822815,
      "eval_runtime": 1.206,
      "eval_samples_per_second": 82.917,
      "eval_steps_per_second": 14.096,
      "step": 7950
    },
    {
      "epoch": 0.8799186075288036,
      "grad_norm": 3.3613343238830566,
      "learning_rate": 3.3624958732254876e-05,
      "loss": 0.4822299194335937,
      "step": 8000
    },
    {
      "epoch": 0.8799186075288036,
      "eval_loss": 0.5934929251670837,
      "eval_runtime": 1.2112,
      "eval_samples_per_second": 82.566,
      "eval_steps_per_second": 14.036,
      "step": 8000
    },
    {
      "epoch": 0.8854180988258586,
      "grad_norm": 4.434471130371094,
      "learning_rate": 3.345988775173324e-05,
      "loss": 0.49528308868408205,
      "step": 8050
    },
    {
      "epoch": 0.8854180988258586,
      "eval_loss": 0.5964680314064026,
      "eval_runtime": 1.2137,
      "eval_samples_per_second": 82.39,
      "eval_steps_per_second": 14.006,
      "step": 8050
    },
    {
      "epoch": 0.8909175901229136,
      "grad_norm": 4.2046403884887695,
      "learning_rate": 3.329481677121162e-05,
      "loss": 0.48887725830078127,
      "step": 8100
    },
    {
      "epoch": 0.8909175901229136,
      "eval_loss": 0.5806313753128052,
      "eval_runtime": 1.2203,
      "eval_samples_per_second": 81.947,
      "eval_steps_per_second": 13.931,
      "step": 8100
    },
    {
      "epoch": 0.8964170814199687,
      "grad_norm": 4.626391410827637,
      "learning_rate": 3.312974579069e-05,
      "loss": 0.5233592987060547,
      "step": 8150
    },
    {
      "epoch": 0.8964170814199687,
      "eval_loss": 0.6079022884368896,
      "eval_runtime": 1.216,
      "eval_samples_per_second": 82.236,
      "eval_steps_per_second": 13.98,
      "step": 8150
    },
    {
      "epoch": 0.9019165727170236,
      "grad_norm": 4.376235008239746,
      "learning_rate": 3.2964674810168374e-05,
      "loss": 0.4639776611328125,
      "step": 8200
    },
    {
      "epoch": 0.9019165727170236,
      "eval_loss": 0.6205313205718994,
      "eval_runtime": 1.2055,
      "eval_samples_per_second": 82.955,
      "eval_steps_per_second": 14.102,
      "step": 8200
    },
    {
      "epoch": 0.9074160640140787,
      "grad_norm": 3.8218092918395996,
      "learning_rate": 3.279960382964675e-05,
      "loss": 0.44373504638671873,
      "step": 8250
    },
    {
      "epoch": 0.9074160640140787,
      "eval_loss": 0.5643773078918457,
      "eval_runtime": 1.2145,
      "eval_samples_per_second": 82.339,
      "eval_steps_per_second": 13.998,
      "step": 8250
    },
    {
      "epoch": 0.9129155553111338,
      "grad_norm": 3.81736159324646,
      "learning_rate": 3.263453284912513e-05,
      "loss": 0.48470027923583986,
      "step": 8300
    },
    {
      "epoch": 0.9129155553111338,
      "eval_loss": 0.5744062066078186,
      "eval_runtime": 1.2167,
      "eval_samples_per_second": 82.188,
      "eval_steps_per_second": 13.972,
      "step": 8300
    },
    {
      "epoch": 0.9184150466081887,
      "grad_norm": 5.86279296875,
      "learning_rate": 3.24694618686035e-05,
      "loss": 0.4852021408081055,
      "step": 8350
    },
    {
      "epoch": 0.9184150466081887,
      "eval_loss": 0.5889118313789368,
      "eval_runtime": 1.423,
      "eval_samples_per_second": 70.273,
      "eval_steps_per_second": 11.946,
      "step": 8350
    },
    {
      "epoch": 0.9239145379052438,
      "grad_norm": 3.33119535446167,
      "learning_rate": 3.230439088808188e-05,
      "loss": 0.47623142242431643,
      "step": 8400
    },
    {
      "epoch": 0.9239145379052438,
      "eval_loss": 0.6064158082008362,
      "eval_runtime": 1.204,
      "eval_samples_per_second": 83.056,
      "eval_steps_per_second": 14.119,
      "step": 8400
    },
    {
      "epoch": 0.9294140292022988,
      "grad_norm": 2.885103940963745,
      "learning_rate": 3.213931990756025e-05,
      "loss": 0.49996829986572267,
      "step": 8450
    },
    {
      "epoch": 0.9294140292022988,
      "eval_loss": 0.5843780040740967,
      "eval_runtime": 1.2023,
      "eval_samples_per_second": 83.174,
      "eval_steps_per_second": 14.14,
      "step": 8450
    },
    {
      "epoch": 0.9349135204993538,
      "grad_norm": 4.857532978057861,
      "learning_rate": 3.1974248927038625e-05,
      "loss": 0.47324295043945314,
      "step": 8500
    },
    {
      "epoch": 0.9349135204993538,
      "eval_loss": 0.6105228662490845,
      "eval_runtime": 1.2083,
      "eval_samples_per_second": 82.759,
      "eval_steps_per_second": 14.069,
      "step": 8500
    },
    {
      "epoch": 0.9404130117964088,
      "grad_norm": 3.946885108947754,
      "learning_rate": 3.1809177946517005e-05,
      "loss": 0.49978759765625,
      "step": 8550
    },
    {
      "epoch": 0.9404130117964088,
      "eval_loss": 0.5941745638847351,
      "eval_runtime": 1.2125,
      "eval_samples_per_second": 82.477,
      "eval_steps_per_second": 14.021,
      "step": 8550
    },
    {
      "epoch": 0.9459125030934639,
      "grad_norm": 4.021317005157471,
      "learning_rate": 3.164410696599538e-05,
      "loss": 0.528785514831543,
      "step": 8600
    },
    {
      "epoch": 0.9459125030934639,
      "eval_loss": 0.6242286562919617,
      "eval_runtime": 1.2102,
      "eval_samples_per_second": 82.628,
      "eval_steps_per_second": 14.047,
      "step": 8600
    },
    {
      "epoch": 0.9514119943905188,
      "grad_norm": 3.708808183670044,
      "learning_rate": 3.147903598547375e-05,
      "loss": 0.46576389312744143,
      "step": 8650
    },
    {
      "epoch": 0.9514119943905188,
      "eval_loss": 0.611571192741394,
      "eval_runtime": 1.204,
      "eval_samples_per_second": 83.055,
      "eval_steps_per_second": 14.119,
      "step": 8650
    },
    {
      "epoch": 0.9569114856875739,
      "grad_norm": 3.2899420261383057,
      "learning_rate": 3.131396500495213e-05,
      "loss": 0.46845787048339843,
      "step": 8700
    },
    {
      "epoch": 0.9569114856875739,
      "eval_loss": 0.6180684566497803,
      "eval_runtime": 1.212,
      "eval_samples_per_second": 82.506,
      "eval_steps_per_second": 14.026,
      "step": 8700
    },
    {
      "epoch": 0.962410976984629,
      "grad_norm": 5.375493049621582,
      "learning_rate": 3.114889402443051e-05,
      "loss": 0.4573846435546875,
      "step": 8750
    },
    {
      "epoch": 0.962410976984629,
      "eval_loss": 0.6240963935852051,
      "eval_runtime": 1.2083,
      "eval_samples_per_second": 82.759,
      "eval_steps_per_second": 14.069,
      "step": 8750
    },
    {
      "epoch": 0.9679104682816839,
      "grad_norm": 3.9251935482025146,
      "learning_rate": 3.0983823043908876e-05,
      "loss": 0.4789009094238281,
      "step": 8800
    },
    {
      "epoch": 0.9679104682816839,
      "eval_loss": 0.6151527762413025,
      "eval_runtime": 1.245,
      "eval_samples_per_second": 80.322,
      "eval_steps_per_second": 13.655,
      "step": 8800
    },
    {
      "epoch": 0.973409959578739,
      "grad_norm": 4.760181903839111,
      "learning_rate": 3.0818752063387256e-05,
      "loss": 0.4835487365722656,
      "step": 8850
    },
    {
      "epoch": 0.973409959578739,
      "eval_loss": 0.6076204776763916,
      "eval_runtime": 1.3823,
      "eval_samples_per_second": 72.341,
      "eval_steps_per_second": 12.298,
      "step": 8850
    },
    {
      "epoch": 0.978909450875794,
      "grad_norm": 4.721770763397217,
      "learning_rate": 3.0653681082865635e-05,
      "loss": 0.4760139083862305,
      "step": 8900
    },
    {
      "epoch": 0.978909450875794,
      "eval_loss": 0.6116940975189209,
      "eval_runtime": 1.2074,
      "eval_samples_per_second": 82.823,
      "eval_steps_per_second": 14.08,
      "step": 8900
    },
    {
      "epoch": 0.984408942172849,
      "grad_norm": 2.7520203590393066,
      "learning_rate": 3.0488610102344005e-05,
      "loss": 0.46280517578125,
      "step": 8950
    },
    {
      "epoch": 0.984408942172849,
      "eval_loss": 0.594266951084137,
      "eval_runtime": 1.2134,
      "eval_samples_per_second": 82.416,
      "eval_steps_per_second": 14.011,
      "step": 8950
    },
    {
      "epoch": 0.989908433469904,
      "grad_norm": 3.4478979110717773,
      "learning_rate": 3.0323539121822385e-05,
      "loss": 0.48518154144287107,
      "step": 9000
    },
    {
      "epoch": 0.989908433469904,
      "eval_loss": 0.6080638766288757,
      "eval_runtime": 1.2202,
      "eval_samples_per_second": 81.953,
      "eval_steps_per_second": 13.932,
      "step": 9000
    },
    {
      "epoch": 0.995407924766959,
      "grad_norm": 3.8885610103607178,
      "learning_rate": 3.015846814130076e-05,
      "loss": 0.4918204116821289,
      "step": 9050
    },
    {
      "epoch": 0.995407924766959,
      "eval_loss": 0.6131730079650879,
      "eval_runtime": 1.236,
      "eval_samples_per_second": 80.906,
      "eval_steps_per_second": 13.754,
      "step": 9050
    },
    {
      "epoch": 1.0008799186075288,
      "grad_norm": 3.4417338371276855,
      "learning_rate": 2.9993397160779137e-05,
      "loss": 0.4655106353759766,
      "step": 9100
    },
    {
      "epoch": 1.0008799186075288,
      "eval_loss": 0.6303781270980835,
      "eval_runtime": 1.2182,
      "eval_samples_per_second": 82.087,
      "eval_steps_per_second": 13.955,
      "step": 9100
    },
    {
      "epoch": 1.0063794099045837,
      "grad_norm": 4.042264461517334,
      "learning_rate": 2.982832618025751e-05,
      "loss": 0.4372904968261719,
      "step": 9150
    },
    {
      "epoch": 1.0063794099045837,
      "eval_loss": 0.6115362048149109,
      "eval_runtime": 1.2191,
      "eval_samples_per_second": 82.028,
      "eval_steps_per_second": 13.945,
      "step": 9150
    },
    {
      "epoch": 1.011878901201639,
      "grad_norm": 4.3367018699646,
      "learning_rate": 2.966325519973589e-05,
      "loss": 0.4454679489135742,
      "step": 9200
    },
    {
      "epoch": 1.011878901201639,
      "eval_loss": 0.598572850227356,
      "eval_runtime": 1.2205,
      "eval_samples_per_second": 81.932,
      "eval_steps_per_second": 13.928,
      "step": 9200
    },
    {
      "epoch": 1.0173783924986939,
      "grad_norm": 5.504449844360352,
      "learning_rate": 2.9498184219214262e-05,
      "loss": 0.4694999694824219,
      "step": 9250
    },
    {
      "epoch": 1.0173783924986939,
      "eval_loss": 0.5946099162101746,
      "eval_runtime": 1.2073,
      "eval_samples_per_second": 82.832,
      "eval_steps_per_second": 14.081,
      "step": 9250
    },
    {
      "epoch": 1.0228778837957488,
      "grad_norm": 5.267527103424072,
      "learning_rate": 2.933311323869264e-05,
      "loss": 0.44829036712646486,
      "step": 9300
    },
    {
      "epoch": 1.0228778837957488,
      "eval_loss": 0.596511960029602,
      "eval_runtime": 1.2164,
      "eval_samples_per_second": 82.213,
      "eval_steps_per_second": 13.976,
      "step": 9300
    },
    {
      "epoch": 1.028377375092804,
      "grad_norm": 2.8371832370758057,
      "learning_rate": 2.9168042258171015e-05,
      "loss": 0.4043942642211914,
      "step": 9350
    },
    {
      "epoch": 1.028377375092804,
      "eval_loss": 0.600749671459198,
      "eval_runtime": 1.2377,
      "eval_samples_per_second": 80.796,
      "eval_steps_per_second": 13.735,
      "step": 9350
    },
    {
      "epoch": 1.033876866389859,
      "grad_norm": 3.1648924350738525,
      "learning_rate": 2.9002971277649388e-05,
      "loss": 0.47807037353515625,
      "step": 9400
    },
    {
      "epoch": 1.033876866389859,
      "eval_loss": 0.6105673909187317,
      "eval_runtime": 1.2193,
      "eval_samples_per_second": 82.012,
      "eval_steps_per_second": 13.942,
      "step": 9400
    },
    {
      "epoch": 1.039376357686914,
      "grad_norm": 4.341183662414551,
      "learning_rate": 2.8837900297127767e-05,
      "loss": 0.4305224609375,
      "step": 9450
    },
    {
      "epoch": 1.039376357686914,
      "eval_loss": 0.5932527184486389,
      "eval_runtime": 1.2151,
      "eval_samples_per_second": 82.297,
      "eval_steps_per_second": 13.991,
      "step": 9450
    },
    {
      "epoch": 1.044875848983969,
      "grad_norm": 3.4657225608825684,
      "learning_rate": 2.867282931660614e-05,
      "loss": 0.3872489929199219,
      "step": 9500
    },
    {
      "epoch": 1.044875848983969,
      "eval_loss": 0.6022618412971497,
      "eval_runtime": 1.203,
      "eval_samples_per_second": 83.129,
      "eval_steps_per_second": 14.132,
      "step": 9500
    },
    {
      "epoch": 1.050375340281024,
      "grad_norm": 3.8219797611236572,
      "learning_rate": 2.8507758336084517e-05,
      "loss": 0.44281375885009766,
      "step": 9550
    },
    {
      "epoch": 1.050375340281024,
      "eval_loss": 0.5904479026794434,
      "eval_runtime": 1.1999,
      "eval_samples_per_second": 83.343,
      "eval_steps_per_second": 14.168,
      "step": 9550
    },
    {
      "epoch": 1.055874831578079,
      "grad_norm": 3.437319755554199,
      "learning_rate": 2.8342687355562893e-05,
      "loss": 0.453095703125,
      "step": 9600
    },
    {
      "epoch": 1.055874831578079,
      "eval_loss": 0.5905536413192749,
      "eval_runtime": 1.2019,
      "eval_samples_per_second": 83.203,
      "eval_steps_per_second": 14.144,
      "step": 9600
    },
    {
      "epoch": 1.061374322875134,
      "grad_norm": 5.347193241119385,
      "learning_rate": 2.817761637504127e-05,
      "loss": 0.4297781753540039,
      "step": 9650
    },
    {
      "epoch": 1.061374322875134,
      "eval_loss": 0.5929006338119507,
      "eval_runtime": 1.2006,
      "eval_samples_per_second": 83.292,
      "eval_steps_per_second": 14.16,
      "step": 9650
    },
    {
      "epoch": 1.066873814172189,
      "grad_norm": 3.720005750656128,
      "learning_rate": 2.8012545394519642e-05,
      "loss": 0.42318790435791015,
      "step": 9700
    },
    {
      "epoch": 1.066873814172189,
      "eval_loss": 0.5905603766441345,
      "eval_runtime": 1.2021,
      "eval_samples_per_second": 83.187,
      "eval_steps_per_second": 14.142,
      "step": 9700
    },
    {
      "epoch": 1.0723733054692441,
      "grad_norm": 4.219228267669678,
      "learning_rate": 2.784747441399802e-05,
      "loss": 0.4420646286010742,
      "step": 9750
    },
    {
      "epoch": 1.0723733054692441,
      "eval_loss": 0.5723536014556885,
      "eval_runtime": 1.2102,
      "eval_samples_per_second": 82.63,
      "eval_steps_per_second": 14.047,
      "step": 9750
    },
    {
      "epoch": 1.077872796766299,
      "grad_norm": 5.102869987487793,
      "learning_rate": 2.7682403433476395e-05,
      "loss": 0.44880119323730466,
      "step": 9800
    },
    {
      "epoch": 1.077872796766299,
      "eval_loss": 0.5921871662139893,
      "eval_runtime": 1.2009,
      "eval_samples_per_second": 83.271,
      "eval_steps_per_second": 14.156,
      "step": 9800
    },
    {
      "epoch": 1.083372288063354,
      "grad_norm": 4.417986869812012,
      "learning_rate": 2.751733245295477e-05,
      "loss": 0.43164543151855467,
      "step": 9850
    },
    {
      "epoch": 1.083372288063354,
      "eval_loss": 0.5745819211006165,
      "eval_runtime": 1.199,
      "eval_samples_per_second": 83.404,
      "eval_steps_per_second": 14.179,
      "step": 9850
    },
    {
      "epoch": 1.0888717793604092,
      "grad_norm": 4.315613746643066,
      "learning_rate": 2.7352261472433147e-05,
      "loss": 0.4114876937866211,
      "step": 9900
    },
    {
      "epoch": 1.0888717793604092,
      "eval_loss": 0.6222988367080688,
      "eval_runtime": 1.2039,
      "eval_samples_per_second": 83.064,
      "eval_steps_per_second": 14.121,
      "step": 9900
    },
    {
      "epoch": 1.0943712706574642,
      "grad_norm": 3.8662261962890625,
      "learning_rate": 2.7187190491911523e-05,
      "loss": 0.4395499420166016,
      "step": 9950
    },
    {
      "epoch": 1.0943712706574642,
      "eval_loss": 0.598095178604126,
      "eval_runtime": 1.2065,
      "eval_samples_per_second": 82.886,
      "eval_steps_per_second": 14.091,
      "step": 9950
    },
    {
      "epoch": 1.0998707619545192,
      "grad_norm": 4.77580451965332,
      "learning_rate": 2.70221195113899e-05,
      "loss": 0.4401175308227539,
      "step": 10000
    },
    {
      "epoch": 1.0998707619545192,
      "eval_loss": 0.6062231659889221,
      "eval_runtime": 1.1984,
      "eval_samples_per_second": 83.447,
      "eval_steps_per_second": 14.186,
      "step": 10000
    },
    {
      "epoch": 1.1053702532515741,
      "grad_norm": 5.308359146118164,
      "learning_rate": 2.6857048530868276e-05,
      "loss": 0.38489757537841796,
      "step": 10050
    },
    {
      "epoch": 1.1053702532515741,
      "eval_loss": 0.574999988079071,
      "eval_runtime": 1.1984,
      "eval_samples_per_second": 83.444,
      "eval_steps_per_second": 14.186,
      "step": 10050
    },
    {
      "epoch": 1.1108697445486293,
      "grad_norm": 3.92620587348938,
      "learning_rate": 2.669197755034665e-05,
      "loss": 0.445535888671875,
      "step": 10100
    },
    {
      "epoch": 1.1108697445486293,
      "eval_loss": 0.5968570113182068,
      "eval_runtime": 1.2009,
      "eval_samples_per_second": 83.268,
      "eval_steps_per_second": 14.156,
      "step": 10100
    },
    {
      "epoch": 1.1163692358456843,
      "grad_norm": 3.6382229328155518,
      "learning_rate": 2.652690656982503e-05,
      "loss": 0.43107017517089846,
      "step": 10150
    },
    {
      "epoch": 1.1163692358456843,
      "eval_loss": 0.6031837463378906,
      "eval_runtime": 1.1994,
      "eval_samples_per_second": 83.378,
      "eval_steps_per_second": 14.174,
      "step": 10150
    },
    {
      "epoch": 1.1218687271427392,
      "grad_norm": 5.4295148849487305,
      "learning_rate": 2.63618355893034e-05,
      "loss": 0.44390846252441407,
      "step": 10200
    },
    {
      "epoch": 1.1218687271427392,
      "eval_loss": 0.5818211436271667,
      "eval_runtime": 1.2017,
      "eval_samples_per_second": 83.212,
      "eval_steps_per_second": 14.146,
      "step": 10200
    },
    {
      "epoch": 1.1273682184397944,
      "grad_norm": 4.309296607971191,
      "learning_rate": 2.6196764608781774e-05,
      "loss": 0.45012378692626953,
      "step": 10250
    },
    {
      "epoch": 1.1273682184397944,
      "eval_loss": 0.5798439979553223,
      "eval_runtime": 1.2245,
      "eval_samples_per_second": 81.667,
      "eval_steps_per_second": 13.883,
      "step": 10250
    },
    {
      "epoch": 1.1328677097368494,
      "grad_norm": 4.410998821258545,
      "learning_rate": 2.6031693628260154e-05,
      "loss": 0.4658625411987305,
      "step": 10300
    },
    {
      "epoch": 1.1328677097368494,
      "eval_loss": 0.5707818865776062,
      "eval_runtime": 1.1991,
      "eval_samples_per_second": 83.396,
      "eval_steps_per_second": 14.177,
      "step": 10300
    },
    {
      "epoch": 1.1383672010339043,
      "grad_norm": 2.5657384395599365,
      "learning_rate": 2.5866622647738527e-05,
      "loss": 0.4424343490600586,
      "step": 10350
    },
    {
      "epoch": 1.1383672010339043,
      "eval_loss": 0.5677274465560913,
      "eval_runtime": 1.1985,
      "eval_samples_per_second": 83.439,
      "eval_steps_per_second": 14.185,
      "step": 10350
    },
    {
      "epoch": 1.1438666923309593,
      "grad_norm": 4.544326305389404,
      "learning_rate": 2.5701551667216903e-05,
      "loss": 0.4189057922363281,
      "step": 10400
    },
    {
      "epoch": 1.1438666923309593,
      "eval_loss": 0.5669907331466675,
      "eval_runtime": 1.2023,
      "eval_samples_per_second": 83.172,
      "eval_steps_per_second": 14.139,
      "step": 10400
    },
    {
      "epoch": 1.1493661836280145,
      "grad_norm": 4.390478134155273,
      "learning_rate": 2.553648068669528e-05,
      "loss": 0.44770816802978514,
      "step": 10450
    },
    {
      "epoch": 1.1493661836280145,
      "eval_loss": 0.5683467388153076,
      "eval_runtime": 1.1991,
      "eval_samples_per_second": 83.395,
      "eval_steps_per_second": 14.177,
      "step": 10450
    },
    {
      "epoch": 1.1548656749250694,
      "grad_norm": 3.9074809551239014,
      "learning_rate": 2.5371409706173655e-05,
      "loss": 0.4494611740112305,
      "step": 10500
    },
    {
      "epoch": 1.1548656749250694,
      "eval_loss": 0.5813124179840088,
      "eval_runtime": 1.1995,
      "eval_samples_per_second": 83.365,
      "eval_steps_per_second": 14.172,
      "step": 10500
    },
    {
      "epoch": 1.1603651662221244,
      "grad_norm": 3.1746835708618164,
      "learning_rate": 2.520633872565203e-05,
      "loss": 0.42440425872802734,
      "step": 10550
    },
    {
      "epoch": 1.1603651662221244,
      "eval_loss": 0.5736593008041382,
      "eval_runtime": 1.2009,
      "eval_samples_per_second": 83.272,
      "eval_steps_per_second": 14.156,
      "step": 10550
    },
    {
      "epoch": 1.1658646575191796,
      "grad_norm": 5.491518497467041,
      "learning_rate": 2.5041267745130408e-05,
      "loss": 0.4350612258911133,
      "step": 10600
    },
    {
      "epoch": 1.1658646575191796,
      "eval_loss": 0.57778000831604,
      "eval_runtime": 1.1993,
      "eval_samples_per_second": 83.38,
      "eval_steps_per_second": 14.175,
      "step": 10600
    },
    {
      "epoch": 1.1713641488162345,
      "grad_norm": 4.8435468673706055,
      "learning_rate": 2.487619676460878e-05,
      "loss": 0.4232054901123047,
      "step": 10650
    },
    {
      "epoch": 1.1713641488162345,
      "eval_loss": 0.5833326578140259,
      "eval_runtime": 1.1979,
      "eval_samples_per_second": 83.477,
      "eval_steps_per_second": 14.191,
      "step": 10650
    },
    {
      "epoch": 1.1768636401132895,
      "grad_norm": 5.074549674987793,
      "learning_rate": 2.471112578408716e-05,
      "loss": 0.45191131591796874,
      "step": 10700
    },
    {
      "epoch": 1.1768636401132895,
      "eval_loss": 0.5973538160324097,
      "eval_runtime": 1.2004,
      "eval_samples_per_second": 83.305,
      "eval_steps_per_second": 14.162,
      "step": 10700
    },
    {
      "epoch": 1.1823631314103444,
      "grad_norm": 3.509275436401367,
      "learning_rate": 2.4546054803565533e-05,
      "loss": 0.4495719528198242,
      "step": 10750
    },
    {
      "epoch": 1.1823631314103444,
      "eval_loss": 0.5876668095588684,
      "eval_runtime": 1.2029,
      "eval_samples_per_second": 83.13,
      "eval_steps_per_second": 14.132,
      "step": 10750
    },
    {
      "epoch": 1.1878626227073996,
      "grad_norm": 3.4657552242279053,
      "learning_rate": 2.438098382304391e-05,
      "loss": 0.4320774459838867,
      "step": 10800
    },
    {
      "epoch": 1.1878626227073996,
      "eval_loss": 0.5911355018615723,
      "eval_runtime": 1.2004,
      "eval_samples_per_second": 83.303,
      "eval_steps_per_second": 14.161,
      "step": 10800
    },
    {
      "epoch": 1.1933621140044546,
      "grad_norm": 3.424093008041382,
      "learning_rate": 2.4215912842522286e-05,
      "loss": 0.41817344665527345,
      "step": 10850
    },
    {
      "epoch": 1.1933621140044546,
      "eval_loss": 0.558462381362915,
      "eval_runtime": 1.2044,
      "eval_samples_per_second": 83.032,
      "eval_steps_per_second": 14.115,
      "step": 10850
    },
    {
      "epoch": 1.1988616053015095,
      "grad_norm": 5.278721332550049,
      "learning_rate": 2.4050841862000662e-05,
      "loss": 0.42692329406738283,
      "step": 10900
    },
    {
      "epoch": 1.1988616053015095,
      "eval_loss": 0.5609988570213318,
      "eval_runtime": 1.2061,
      "eval_samples_per_second": 82.911,
      "eval_steps_per_second": 14.095,
      "step": 10900
    },
    {
      "epoch": 1.2043610965985647,
      "grad_norm": 4.2132248878479,
      "learning_rate": 2.3885770881479035e-05,
      "loss": 0.4087539291381836,
      "step": 10950
    },
    {
      "epoch": 1.2043610965985647,
      "eval_loss": 0.5824187397956848,
      "eval_runtime": 1.2378,
      "eval_samples_per_second": 80.789,
      "eval_steps_per_second": 13.734,
      "step": 10950
    },
    {
      "epoch": 1.2098605878956197,
      "grad_norm": 4.436295509338379,
      "learning_rate": 2.3720699900957415e-05,
      "loss": 0.3884201812744141,
      "step": 11000
    },
    {
      "epoch": 1.2098605878956197,
      "eval_loss": 0.5735225677490234,
      "eval_runtime": 1.2641,
      "eval_samples_per_second": 79.108,
      "eval_steps_per_second": 13.448,
      "step": 11000
    },
    {
      "epoch": 1.2153600791926746,
      "grad_norm": 4.041130542755127,
      "learning_rate": 2.3555628920435788e-05,
      "loss": 0.3993444061279297,
      "step": 11050
    },
    {
      "epoch": 1.2153600791926746,
      "eval_loss": 0.5744249820709229,
      "eval_runtime": 1.2074,
      "eval_samples_per_second": 82.822,
      "eval_steps_per_second": 14.08,
      "step": 11050
    },
    {
      "epoch": 1.2208595704897296,
      "grad_norm": 4.301640510559082,
      "learning_rate": 2.3390557939914164e-05,
      "loss": 0.39464141845703127,
      "step": 11100
    },
    {
      "epoch": 1.2208595704897296,
      "eval_loss": 0.5948730111122131,
      "eval_runtime": 1.2581,
      "eval_samples_per_second": 79.487,
      "eval_steps_per_second": 13.513,
      "step": 11100
    },
    {
      "epoch": 1.2263590617867848,
      "grad_norm": 5.845645427703857,
      "learning_rate": 2.322548695939254e-05,
      "loss": 0.4228610610961914,
      "step": 11150
    },
    {
      "epoch": 1.2263590617867848,
      "eval_loss": 0.5744452476501465,
      "eval_runtime": 1.2349,
      "eval_samples_per_second": 80.975,
      "eval_steps_per_second": 13.766,
      "step": 11150
    },
    {
      "epoch": 1.2318585530838397,
      "grad_norm": 4.14743185043335,
      "learning_rate": 2.3060415978870913e-05,
      "loss": 0.43561710357666017,
      "step": 11200
    },
    {
      "epoch": 1.2318585530838397,
      "eval_loss": 0.5542231798171997,
      "eval_runtime": 1.2462,
      "eval_samples_per_second": 80.242,
      "eval_steps_per_second": 13.641,
      "step": 11200
    },
    {
      "epoch": 1.2373580443808947,
      "grad_norm": 4.9092607498168945,
      "learning_rate": 2.2895344998349293e-05,
      "loss": 0.4485149765014648,
      "step": 11250
    },
    {
      "epoch": 1.2373580443808947,
      "eval_loss": 0.5608264803886414,
      "eval_runtime": 1.2042,
      "eval_samples_per_second": 83.044,
      "eval_steps_per_second": 14.118,
      "step": 11250
    },
    {
      "epoch": 1.2428575356779499,
      "grad_norm": 4.795513153076172,
      "learning_rate": 2.2730274017827665e-05,
      "loss": 0.4002879333496094,
      "step": 11300
    },
    {
      "epoch": 1.2428575356779499,
      "eval_loss": 0.5752193927764893,
      "eval_runtime": 1.2005,
      "eval_samples_per_second": 83.3,
      "eval_steps_per_second": 14.161,
      "step": 11300
    },
    {
      "epoch": 1.2483570269750048,
      "grad_norm": 4.756551742553711,
      "learning_rate": 2.2565203037306042e-05,
      "loss": 0.4129877853393555,
      "step": 11350
    },
    {
      "epoch": 1.2483570269750048,
      "eval_loss": 0.5692643523216248,
      "eval_runtime": 1.202,
      "eval_samples_per_second": 83.198,
      "eval_steps_per_second": 14.144,
      "step": 11350
    },
    {
      "epoch": 1.2538565182720598,
      "grad_norm": 4.6832051277160645,
      "learning_rate": 2.2400132056784418e-05,
      "loss": 0.40815105438232424,
      "step": 11400
    },
    {
      "epoch": 1.2538565182720598,
      "eval_loss": 0.5672106742858887,
      "eval_runtime": 1.2026,
      "eval_samples_per_second": 83.153,
      "eval_steps_per_second": 14.136,
      "step": 11400
    },
    {
      "epoch": 1.2593560095691148,
      "grad_norm": 4.295003414154053,
      "learning_rate": 2.2235061076262794e-05,
      "loss": 0.43860099792480467,
      "step": 11450
    },
    {
      "epoch": 1.2593560095691148,
      "eval_loss": 0.5500693321228027,
      "eval_runtime": 1.1996,
      "eval_samples_per_second": 83.363,
      "eval_steps_per_second": 14.172,
      "step": 11450
    },
    {
      "epoch": 1.26485550086617,
      "grad_norm": 3.2815680503845215,
      "learning_rate": 2.2069990095741167e-05,
      "loss": 0.39200534820556643,
      "step": 11500
    },
    {
      "epoch": 1.26485550086617,
      "eval_loss": 0.5783631801605225,
      "eval_runtime": 1.2001,
      "eval_samples_per_second": 83.324,
      "eval_steps_per_second": 14.165,
      "step": 11500
    },
    {
      "epoch": 1.270354992163225,
      "grad_norm": 5.105454921722412,
      "learning_rate": 2.1904919115219547e-05,
      "loss": 0.447188606262207,
      "step": 11550
    },
    {
      "epoch": 1.270354992163225,
      "eval_loss": 0.5806690454483032,
      "eval_runtime": 1.2018,
      "eval_samples_per_second": 83.21,
      "eval_steps_per_second": 14.146,
      "step": 11550
    },
    {
      "epoch": 1.2758544834602799,
      "grad_norm": 7.1614580154418945,
      "learning_rate": 2.173984813469792e-05,
      "loss": 0.4186487579345703,
      "step": 11600
    },
    {
      "epoch": 1.2758544834602799,
      "eval_loss": 0.5866115689277649,
      "eval_runtime": 1.2043,
      "eval_samples_per_second": 83.036,
      "eval_steps_per_second": 14.116,
      "step": 11600
    },
    {
      "epoch": 1.281353974757335,
      "grad_norm": 3.8269095420837402,
      "learning_rate": 2.1574777154176296e-05,
      "loss": 0.38072307586669923,
      "step": 11650
    },
    {
      "epoch": 1.281353974757335,
      "eval_loss": 0.5898852944374084,
      "eval_runtime": 1.2117,
      "eval_samples_per_second": 82.525,
      "eval_steps_per_second": 14.029,
      "step": 11650
    },
    {
      "epoch": 1.28685346605439,
      "grad_norm": 4.064493179321289,
      "learning_rate": 2.1409706173654672e-05,
      "loss": 0.4382596206665039,
      "step": 11700
    },
    {
      "epoch": 1.28685346605439,
      "eval_loss": 0.5848357677459717,
      "eval_runtime": 1.1999,
      "eval_samples_per_second": 83.34,
      "eval_steps_per_second": 14.168,
      "step": 11700
    },
    {
      "epoch": 1.292352957351445,
      "grad_norm": 5.449599742889404,
      "learning_rate": 2.124463519313305e-05,
      "loss": 0.42343997955322266,
      "step": 11750
    },
    {
      "epoch": 1.292352957351445,
      "eval_loss": 0.5586597323417664,
      "eval_runtime": 1.2023,
      "eval_samples_per_second": 83.172,
      "eval_steps_per_second": 14.139,
      "step": 11750
    },
    {
      "epoch": 1.2978524486485,
      "grad_norm": 3.673954725265503,
      "learning_rate": 2.107956421261142e-05,
      "loss": 0.41550613403320313,
      "step": 11800
    },
    {
      "epoch": 1.2978524486485,
      "eval_loss": 0.5658605694770813,
      "eval_runtime": 1.1991,
      "eval_samples_per_second": 83.399,
      "eval_steps_per_second": 14.178,
      "step": 11800
    },
    {
      "epoch": 1.303351939945555,
      "grad_norm": 3.6161746978759766,
      "learning_rate": 2.09144932320898e-05,
      "loss": 0.4265287780761719,
      "step": 11850
    },
    {
      "epoch": 1.303351939945555,
      "eval_loss": 0.5512486100196838,
      "eval_runtime": 1.2044,
      "eval_samples_per_second": 83.029,
      "eval_steps_per_second": 14.115,
      "step": 11850
    },
    {
      "epoch": 1.30885143124261,
      "grad_norm": 4.095085620880127,
      "learning_rate": 2.0749422251568174e-05,
      "loss": 0.44609962463378905,
      "step": 11900
    },
    {
      "epoch": 1.30885143124261,
      "eval_loss": 0.5730013847351074,
      "eval_runtime": 1.2017,
      "eval_samples_per_second": 83.215,
      "eval_steps_per_second": 14.147,
      "step": 11900
    },
    {
      "epoch": 1.314350922539665,
      "grad_norm": 4.820618152618408,
      "learning_rate": 2.0584351271046554e-05,
      "loss": 0.4422262191772461,
      "step": 11950
    },
    {
      "epoch": 1.314350922539665,
      "eval_loss": 0.5577285289764404,
      "eval_runtime": 1.1984,
      "eval_samples_per_second": 83.443,
      "eval_steps_per_second": 14.185,
      "step": 11950
    },
    {
      "epoch": 1.3198504138367202,
      "grad_norm": 3.5373456478118896,
      "learning_rate": 2.0419280290524926e-05,
      "loss": 0.42433460235595705,
      "step": 12000
    },
    {
      "epoch": 1.3198504138367202,
      "eval_loss": 0.5625931024551392,
      "eval_runtime": 1.1987,
      "eval_samples_per_second": 83.422,
      "eval_steps_per_second": 14.182,
      "step": 12000
    },
    {
      "epoch": 1.3253499051337752,
      "grad_norm": 4.760179042816162,
      "learning_rate": 2.0254209310003303e-05,
      "loss": 0.3792121887207031,
      "step": 12050
    },
    {
      "epoch": 1.3253499051337752,
      "eval_loss": 0.5574110746383667,
      "eval_runtime": 1.2015,
      "eval_samples_per_second": 83.233,
      "eval_steps_per_second": 14.15,
      "step": 12050
    },
    {
      "epoch": 1.3308493964308301,
      "grad_norm": 5.790397644042969,
      "learning_rate": 2.008913832948168e-05,
      "loss": 0.4382122039794922,
      "step": 12100
    },
    {
      "epoch": 1.3308493964308301,
      "eval_loss": 0.5597708225250244,
      "eval_runtime": 1.2092,
      "eval_samples_per_second": 82.703,
      "eval_steps_per_second": 14.059,
      "step": 12100
    },
    {
      "epoch": 1.336348887727885,
      "grad_norm": 4.420812606811523,
      "learning_rate": 1.9924067348960052e-05,
      "loss": 0.42329288482666017,
      "step": 12150
    },
    {
      "epoch": 1.336348887727885,
      "eval_loss": 0.5556257367134094,
      "eval_runtime": 1.1986,
      "eval_samples_per_second": 83.431,
      "eval_steps_per_second": 14.183,
      "step": 12150
    },
    {
      "epoch": 1.3418483790249403,
      "grad_norm": 4.655048370361328,
      "learning_rate": 1.9758996368438428e-05,
      "loss": 0.4278908920288086,
      "step": 12200
    },
    {
      "epoch": 1.3418483790249403,
      "eval_loss": 0.543867290019989,
      "eval_runtime": 1.1984,
      "eval_samples_per_second": 83.442,
      "eval_steps_per_second": 14.185,
      "step": 12200
    },
    {
      "epoch": 1.3473478703219952,
      "grad_norm": 4.914540767669678,
      "learning_rate": 1.9593925387916804e-05,
      "loss": 0.42110458374023435,
      "step": 12250
    },
    {
      "epoch": 1.3473478703219952,
      "eval_loss": 0.5576221346855164,
      "eval_runtime": 1.2024,
      "eval_samples_per_second": 83.17,
      "eval_steps_per_second": 14.139,
      "step": 12250
    },
    {
      "epoch": 1.3528473616190502,
      "grad_norm": 3.613415002822876,
      "learning_rate": 1.942885440739518e-05,
      "loss": 0.408565788269043,
      "step": 12300
    },
    {
      "epoch": 1.3528473616190502,
      "eval_loss": 0.5335881114006042,
      "eval_runtime": 1.1993,
      "eval_samples_per_second": 83.383,
      "eval_steps_per_second": 14.175,
      "step": 12300
    },
    {
      "epoch": 1.3583468529161054,
      "grad_norm": 4.228052616119385,
      "learning_rate": 1.9263783426873553e-05,
      "loss": 0.40878799438476565,
      "step": 12350
    },
    {
      "epoch": 1.3583468529161054,
      "eval_loss": 0.5544968247413635,
      "eval_runtime": 1.2063,
      "eval_samples_per_second": 82.896,
      "eval_steps_per_second": 14.092,
      "step": 12350
    },
    {
      "epoch": 1.3638463442131603,
      "grad_norm": 3.1512410640716553,
      "learning_rate": 1.9098712446351933e-05,
      "loss": 0.40386688232421875,
      "step": 12400
    },
    {
      "epoch": 1.3638463442131603,
      "eval_loss": 0.5391093492507935,
      "eval_runtime": 1.206,
      "eval_samples_per_second": 82.92,
      "eval_steps_per_second": 14.096,
      "step": 12400
    },
    {
      "epoch": 1.3693458355102153,
      "grad_norm": 4.095332145690918,
      "learning_rate": 1.8933641465830306e-05,
      "loss": 0.4119942092895508,
      "step": 12450
    },
    {
      "epoch": 1.3693458355102153,
      "eval_loss": 0.5375053286552429,
      "eval_runtime": 1.1993,
      "eval_samples_per_second": 83.383,
      "eval_steps_per_second": 14.175,
      "step": 12450
    },
    {
      "epoch": 1.3748453268072702,
      "grad_norm": 4.36025333404541,
      "learning_rate": 1.8768570485308686e-05,
      "loss": 0.42032379150390625,
      "step": 12500
    },
    {
      "epoch": 1.3748453268072702,
      "eval_loss": 0.5409677624702454,
      "eval_runtime": 1.1988,
      "eval_samples_per_second": 83.417,
      "eval_steps_per_second": 14.181,
      "step": 12500
    },
    {
      "epoch": 1.3803448181043254,
      "grad_norm": 3.8784241676330566,
      "learning_rate": 1.860349950478706e-05,
      "loss": 0.3923546600341797,
      "step": 12550
    },
    {
      "epoch": 1.3803448181043254,
      "eval_loss": 0.5505947470664978,
      "eval_runtime": 1.2002,
      "eval_samples_per_second": 83.318,
      "eval_steps_per_second": 14.164,
      "step": 12550
    },
    {
      "epoch": 1.3858443094013804,
      "grad_norm": 4.052207946777344,
      "learning_rate": 1.8438428524265435e-05,
      "loss": 0.38611976623535155,
      "step": 12600
    },
    {
      "epoch": 1.3858443094013804,
      "eval_loss": 0.5389760732650757,
      "eval_runtime": 1.2026,
      "eval_samples_per_second": 83.155,
      "eval_steps_per_second": 14.136,
      "step": 12600
    },
    {
      "epoch": 1.3913438006984353,
      "grad_norm": 5.018970489501953,
      "learning_rate": 1.827335754374381e-05,
      "loss": 0.4026565933227539,
      "step": 12650
    },
    {
      "epoch": 1.3913438006984353,
      "eval_loss": 0.5398291945457458,
      "eval_runtime": 1.2079,
      "eval_samples_per_second": 82.791,
      "eval_steps_per_second": 14.074,
      "step": 12650
    },
    {
      "epoch": 1.3968432919954905,
      "grad_norm": 3.710087537765503,
      "learning_rate": 1.8108286563222187e-05,
      "loss": 0.4165144729614258,
      "step": 12700
    },
    {
      "epoch": 1.3968432919954905,
      "eval_loss": 0.5442482233047485,
      "eval_runtime": 1.2705,
      "eval_samples_per_second": 78.709,
      "eval_steps_per_second": 13.381,
      "step": 12700
    },
    {
      "epoch": 1.4023427832925455,
      "grad_norm": 4.182759761810303,
      "learning_rate": 1.794321558270056e-05,
      "loss": 0.3919545745849609,
      "step": 12750
    },
    {
      "epoch": 1.4023427832925455,
      "eval_loss": 0.5415162444114685,
      "eval_runtime": 1.2788,
      "eval_samples_per_second": 78.199,
      "eval_steps_per_second": 13.294,
      "step": 12750
    },
    {
      "epoch": 1.4078422745896004,
      "grad_norm": 4.3373870849609375,
      "learning_rate": 1.777814460217894e-05,
      "loss": 0.40383522033691405,
      "step": 12800
    },
    {
      "epoch": 1.4078422745896004,
      "eval_loss": 0.5278663635253906,
      "eval_runtime": 1.2779,
      "eval_samples_per_second": 78.256,
      "eval_steps_per_second": 13.304,
      "step": 12800
    },
    {
      "epoch": 1.4133417658866554,
      "grad_norm": 3.619389533996582,
      "learning_rate": 1.7613073621657313e-05,
      "loss": 0.44847320556640624,
      "step": 12850
    },
    {
      "epoch": 1.4133417658866554,
      "eval_loss": 0.5374107360839844,
      "eval_runtime": 1.2797,
      "eval_samples_per_second": 78.145,
      "eval_steps_per_second": 13.285,
      "step": 12850
    },
    {
      "epoch": 1.4188412571837106,
      "grad_norm": 3.119107246398926,
      "learning_rate": 1.744800264113569e-05,
      "loss": 0.39309986114501955,
      "step": 12900
    },
    {
      "epoch": 1.4188412571837106,
      "eval_loss": 0.5523837804794312,
      "eval_runtime": 1.278,
      "eval_samples_per_second": 78.245,
      "eval_steps_per_second": 13.302,
      "step": 12900
    },
    {
      "epoch": 1.4243407484807655,
      "grad_norm": 3.7152740955352783,
      "learning_rate": 1.7282931660614065e-05,
      "loss": 0.42365001678466796,
      "step": 12950
    },
    {
      "epoch": 1.4243407484807655,
      "eval_loss": 0.5404840707778931,
      "eval_runtime": 1.2774,
      "eval_samples_per_second": 78.282,
      "eval_steps_per_second": 13.308,
      "step": 12950
    },
    {
      "epoch": 1.4298402397778205,
      "grad_norm": 4.347856521606445,
      "learning_rate": 1.7117860680092438e-05,
      "loss": 0.39466506958007813,
      "step": 13000
    },
    {
      "epoch": 1.4298402397778205,
      "eval_loss": 0.5432237386703491,
      "eval_runtime": 1.2709,
      "eval_samples_per_second": 78.687,
      "eval_steps_per_second": 13.377,
      "step": 13000
    },
    {
      "epoch": 1.4353397310748757,
      "grad_norm": 4.440253257751465,
      "learning_rate": 1.6952789699570814e-05,
      "loss": 0.4289556121826172,
      "step": 13050
    },
    {
      "epoch": 1.4353397310748757,
      "eval_loss": 0.5323364734649658,
      "eval_runtime": 1.1995,
      "eval_samples_per_second": 83.369,
      "eval_steps_per_second": 14.173,
      "step": 13050
    },
    {
      "epoch": 1.4408392223719306,
      "grad_norm": 4.130159854888916,
      "learning_rate": 1.678771871904919e-05,
      "loss": 0.4275970458984375,
      "step": 13100
    },
    {
      "epoch": 1.4408392223719306,
      "eval_loss": 0.5353785157203674,
      "eval_runtime": 1.2118,
      "eval_samples_per_second": 82.52,
      "eval_steps_per_second": 14.028,
      "step": 13100
    },
    {
      "epoch": 1.4463387136689856,
      "grad_norm": 3.5807628631591797,
      "learning_rate": 1.6622647738527567e-05,
      "loss": 0.414808464050293,
      "step": 13150
    },
    {
      "epoch": 1.4463387136689856,
      "eval_loss": 0.5167968273162842,
      "eval_runtime": 1.2016,
      "eval_samples_per_second": 83.223,
      "eval_steps_per_second": 14.148,
      "step": 13150
    },
    {
      "epoch": 1.4518382049660405,
      "grad_norm": 3.19081449508667,
      "learning_rate": 1.6457576758005943e-05,
      "loss": 0.4333197021484375,
      "step": 13200
    },
    {
      "epoch": 1.4518382049660405,
      "eval_loss": 0.5306875109672546,
      "eval_runtime": 1.2826,
      "eval_samples_per_second": 77.965,
      "eval_steps_per_second": 13.254,
      "step": 13200
    },
    {
      "epoch": 1.4573376962630957,
      "grad_norm": 3.25466251373291,
      "learning_rate": 1.629250577748432e-05,
      "loss": 0.39129966735839844,
      "step": 13250
    },
    {
      "epoch": 1.4573376962630957,
      "eval_loss": 0.5385807752609253,
      "eval_runtime": 1.282,
      "eval_samples_per_second": 78.006,
      "eval_steps_per_second": 13.261,
      "step": 13250
    },
    {
      "epoch": 1.4628371875601507,
      "grad_norm": 3.3677966594696045,
      "learning_rate": 1.6127434796962692e-05,
      "loss": 0.40751338958740235,
      "step": 13300
    },
    {
      "epoch": 1.4628371875601507,
      "eval_loss": 0.516380250453949,
      "eval_runtime": 1.2802,
      "eval_samples_per_second": 78.112,
      "eval_steps_per_second": 13.279,
      "step": 13300
    },
    {
      "epoch": 1.4683366788572056,
      "grad_norm": 3.450413465499878,
      "learning_rate": 1.5962363816441072e-05,
      "loss": 0.40498565673828124,
      "step": 13350
    },
    {
      "epoch": 1.4683366788572056,
      "eval_loss": 0.5298721194267273,
      "eval_runtime": 1.2815,
      "eval_samples_per_second": 78.034,
      "eval_steps_per_second": 13.266,
      "step": 13350
    },
    {
      "epoch": 1.4738361701542608,
      "grad_norm": 3.3262946605682373,
      "learning_rate": 1.5797292835919445e-05,
      "loss": 0.3863627243041992,
      "step": 13400
    },
    {
      "epoch": 1.4738361701542608,
      "eval_loss": 0.516625165939331,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 78.067,
      "eval_steps_per_second": 13.271,
      "step": 13400
    },
    {
      "epoch": 1.4793356614513158,
      "grad_norm": 3.365875720977783,
      "learning_rate": 1.563222185539782e-05,
      "loss": 0.4204134750366211,
      "step": 13450
    },
    {
      "epoch": 1.4793356614513158,
      "eval_loss": 0.5206517577171326,
      "eval_runtime": 1.2817,
      "eval_samples_per_second": 78.02,
      "eval_steps_per_second": 13.263,
      "step": 13450
    },
    {
      "epoch": 1.4848351527483707,
      "grad_norm": 3.2131149768829346,
      "learning_rate": 1.5467150874876197e-05,
      "loss": 0.40632450103759765,
      "step": 13500
    },
    {
      "epoch": 1.4848351527483707,
      "eval_loss": 0.5308406949043274,
      "eval_runtime": 1.2811,
      "eval_samples_per_second": 78.057,
      "eval_steps_per_second": 13.27,
      "step": 13500
    },
    {
      "epoch": 1.4903346440454257,
      "grad_norm": 3.364225387573242,
      "learning_rate": 1.5302079894354574e-05,
      "loss": 0.4048501205444336,
      "step": 13550
    },
    {
      "epoch": 1.4903346440454257,
      "eval_loss": 0.52863609790802,
      "eval_runtime": 1.2813,
      "eval_samples_per_second": 78.044,
      "eval_steps_per_second": 13.268,
      "step": 13550
    },
    {
      "epoch": 1.4958341353424809,
      "grad_norm": 3.1679489612579346,
      "learning_rate": 1.5137008913832946e-05,
      "loss": 0.4006618881225586,
      "step": 13600
    },
    {
      "epoch": 1.4958341353424809,
      "eval_loss": 0.517315149307251,
      "eval_runtime": 1.2806,
      "eval_samples_per_second": 78.087,
      "eval_steps_per_second": 13.275,
      "step": 13600
    },
    {
      "epoch": 1.5013336266395358,
      "grad_norm": 4.6463518142700195,
      "learning_rate": 1.4971937933311324e-05,
      "loss": 0.4259402847290039,
      "step": 13650
    },
    {
      "epoch": 1.5013336266395358,
      "eval_loss": 0.5239192843437195,
      "eval_runtime": 1.2834,
      "eval_samples_per_second": 77.921,
      "eval_steps_per_second": 13.246,
      "step": 13650
    },
    {
      "epoch": 1.506833117936591,
      "grad_norm": 3.8338677883148193,
      "learning_rate": 1.4806866952789699e-05,
      "loss": 0.45359893798828127,
      "step": 13700
    },
    {
      "epoch": 1.506833117936591,
      "eval_loss": 0.5376471877098083,
      "eval_runtime": 1.1985,
      "eval_samples_per_second": 83.437,
      "eval_steps_per_second": 14.184,
      "step": 13700
    },
    {
      "epoch": 1.512332609233646,
      "grad_norm": 4.828174114227295,
      "learning_rate": 1.4641795972268075e-05,
      "loss": 0.4245915985107422,
      "step": 13750
    },
    {
      "epoch": 1.512332609233646,
      "eval_loss": 0.545063853263855,
      "eval_runtime": 1.2015,
      "eval_samples_per_second": 83.226,
      "eval_steps_per_second": 14.148,
      "step": 13750
    },
    {
      "epoch": 1.517832100530701,
      "grad_norm": 4.063199996948242,
      "learning_rate": 1.4476724991746452e-05,
      "loss": 0.42612323760986326,
      "step": 13800
    },
    {
      "epoch": 1.517832100530701,
      "eval_loss": 0.5337764620780945,
      "eval_runtime": 1.2015,
      "eval_samples_per_second": 83.227,
      "eval_steps_per_second": 14.149,
      "step": 13800
    },
    {
      "epoch": 1.523331591827756,
      "grad_norm": 4.409724235534668,
      "learning_rate": 1.4311654011224828e-05,
      "loss": 0.4229386138916016,
      "step": 13850
    },
    {
      "epoch": 1.523331591827756,
      "eval_loss": 0.5254413485527039,
      "eval_runtime": 1.2114,
      "eval_samples_per_second": 82.546,
      "eval_steps_per_second": 14.033,
      "step": 13850
    },
    {
      "epoch": 1.5288310831248109,
      "grad_norm": 4.604098320007324,
      "learning_rate": 1.4146583030703202e-05,
      "loss": 0.4207559967041016,
      "step": 13900
    },
    {
      "epoch": 1.5288310831248109,
      "eval_loss": 0.5319836139678955,
      "eval_runtime": 1.2009,
      "eval_samples_per_second": 83.273,
      "eval_steps_per_second": 14.156,
      "step": 13900
    },
    {
      "epoch": 1.5343305744218658,
      "grad_norm": 3.5800247192382812,
      "learning_rate": 1.3981512050181579e-05,
      "loss": 0.4052052307128906,
      "step": 13950
    },
    {
      "epoch": 1.5343305744218658,
      "eval_loss": 0.5325583815574646,
      "eval_runtime": 1.2085,
      "eval_samples_per_second": 82.747,
      "eval_steps_per_second": 14.067,
      "step": 13950
    },
    {
      "epoch": 1.539830065718921,
      "grad_norm": 4.180997371673584,
      "learning_rate": 1.3816441069659955e-05,
      "loss": 0.41810825347900393,
      "step": 14000
    },
    {
      "epoch": 1.539830065718921,
      "eval_loss": 0.5244957804679871,
      "eval_runtime": 1.1981,
      "eval_samples_per_second": 83.464,
      "eval_steps_per_second": 14.189,
      "step": 14000
    },
    {
      "epoch": 1.5453295570159762,
      "grad_norm": 4.035894393920898,
      "learning_rate": 1.365137008913833e-05,
      "loss": 0.4168061065673828,
      "step": 14050
    },
    {
      "epoch": 1.5453295570159762,
      "eval_loss": 0.5245411396026611,
      "eval_runtime": 1.1978,
      "eval_samples_per_second": 83.485,
      "eval_steps_per_second": 14.192,
      "step": 14050
    },
    {
      "epoch": 1.5508290483130311,
      "grad_norm": 2.8827695846557617,
      "learning_rate": 1.3486299108616706e-05,
      "loss": 0.40900135040283203,
      "step": 14100
    },
    {
      "epoch": 1.5508290483130311,
      "eval_loss": 0.5175855755805969,
      "eval_runtime": 1.2709,
      "eval_samples_per_second": 78.686,
      "eval_steps_per_second": 13.377,
      "step": 14100
    },
    {
      "epoch": 1.556328539610086,
      "grad_norm": 4.7631516456604,
      "learning_rate": 1.3321228128095082e-05,
      "loss": 0.4275320434570313,
      "step": 14150
    },
    {
      "epoch": 1.556328539610086,
      "eval_loss": 0.5145242214202881,
      "eval_runtime": 1.2206,
      "eval_samples_per_second": 81.93,
      "eval_steps_per_second": 13.928,
      "step": 14150
    },
    {
      "epoch": 1.561828030907141,
      "grad_norm": 4.559270858764648,
      "learning_rate": 1.3156157147573458e-05,
      "loss": 0.3759859848022461,
      "step": 14200
    },
    {
      "epoch": 1.561828030907141,
      "eval_loss": 0.5150010585784912,
      "eval_runtime": 1.1982,
      "eval_samples_per_second": 83.457,
      "eval_steps_per_second": 14.188,
      "step": 14200
    },
    {
      "epoch": 1.567327522204196,
      "grad_norm": 3.3630456924438477,
      "learning_rate": 1.2991086167051833e-05,
      "loss": 0.39138256072998046,
      "step": 14250
    },
    {
      "epoch": 1.567327522204196,
      "eval_loss": 0.5457283854484558,
      "eval_runtime": 1.2043,
      "eval_samples_per_second": 83.038,
      "eval_steps_per_second": 14.116,
      "step": 14250
    },
    {
      "epoch": 1.572827013501251,
      "grad_norm": 3.256690740585327,
      "learning_rate": 1.2826015186530209e-05,
      "loss": 0.3982016372680664,
      "step": 14300
    },
    {
      "epoch": 1.572827013501251,
      "eval_loss": 0.5194215774536133,
      "eval_runtime": 1.2004,
      "eval_samples_per_second": 83.303,
      "eval_steps_per_second": 14.161,
      "step": 14300
    },
    {
      "epoch": 1.5783265047983062,
      "grad_norm": 4.9264020919799805,
      "learning_rate": 1.2660944206008584e-05,
      "loss": 0.37310329437255857,
      "step": 14350
    },
    {
      "epoch": 1.5783265047983062,
      "eval_loss": 0.537217915058136,
      "eval_runtime": 1.2037,
      "eval_samples_per_second": 83.077,
      "eval_steps_per_second": 14.123,
      "step": 14350
    },
    {
      "epoch": 1.5838259960953613,
      "grad_norm": 3.917881965637207,
      "learning_rate": 1.2495873225486958e-05,
      "loss": 0.40028915405273435,
      "step": 14400
    },
    {
      "epoch": 1.5838259960953613,
      "eval_loss": 0.5212844014167786,
      "eval_runtime": 1.2024,
      "eval_samples_per_second": 83.166,
      "eval_steps_per_second": 14.138,
      "step": 14400
    },
    {
      "epoch": 1.5893254873924163,
      "grad_norm": 3.8361563682556152,
      "learning_rate": 1.2330802244965334e-05,
      "loss": 0.40108360290527345,
      "step": 14450
    },
    {
      "epoch": 1.5893254873924163,
      "eval_loss": 0.5083942413330078,
      "eval_runtime": 1.2046,
      "eval_samples_per_second": 83.018,
      "eval_steps_per_second": 14.113,
      "step": 14450
    },
    {
      "epoch": 1.5948249786894713,
      "grad_norm": 3.184602737426758,
      "learning_rate": 1.216573126444371e-05,
      "loss": 0.4339041519165039,
      "step": 14500
    },
    {
      "epoch": 1.5948249786894713,
      "eval_loss": 0.5342686176300049,
      "eval_runtime": 1.2031,
      "eval_samples_per_second": 83.12,
      "eval_steps_per_second": 14.13,
      "step": 14500
    },
    {
      "epoch": 1.6003244699865262,
      "grad_norm": 4.491968154907227,
      "learning_rate": 1.2000660283922087e-05,
      "loss": 0.3967703628540039,
      "step": 14550
    },
    {
      "epoch": 1.6003244699865262,
      "eval_loss": 0.520110547542572,
      "eval_runtime": 1.2023,
      "eval_samples_per_second": 83.17,
      "eval_steps_per_second": 14.139,
      "step": 14550
    },
    {
      "epoch": 1.6058239612835812,
      "grad_norm": 3.78524112701416,
      "learning_rate": 1.1835589303400462e-05,
      "loss": 0.3790835189819336,
      "step": 14600
    },
    {
      "epoch": 1.6058239612835812,
      "eval_loss": 0.5195483565330505,
      "eval_runtime": 1.2016,
      "eval_samples_per_second": 83.223,
      "eval_steps_per_second": 14.148,
      "step": 14600
    },
    {
      "epoch": 1.6113234525806361,
      "grad_norm": 4.135509014129639,
      "learning_rate": 1.1670518322878838e-05,
      "loss": 0.40242374420166016,
      "step": 14650
    },
    {
      "epoch": 1.6113234525806361,
      "eval_loss": 0.516440212726593,
      "eval_runtime": 1.2033,
      "eval_samples_per_second": 83.105,
      "eval_steps_per_second": 14.128,
      "step": 14650
    },
    {
      "epoch": 1.6168229438776913,
      "grad_norm": 4.210612773895264,
      "learning_rate": 1.1505447342357214e-05,
      "loss": 0.4028606414794922,
      "step": 14700
    },
    {
      "epoch": 1.6168229438776913,
      "eval_loss": 0.5266108512878418,
      "eval_runtime": 1.2087,
      "eval_samples_per_second": 82.733,
      "eval_steps_per_second": 14.065,
      "step": 14700
    },
    {
      "epoch": 1.6223224351747465,
      "grad_norm": 5.338522911071777,
      "learning_rate": 1.1340376361835589e-05,
      "loss": 0.39550567626953126,
      "step": 14750
    },
    {
      "epoch": 1.6223224351747465,
      "eval_loss": 0.5249260663986206,
      "eval_runtime": 1.2038,
      "eval_samples_per_second": 83.073,
      "eval_steps_per_second": 14.122,
      "step": 14750
    },
    {
      "epoch": 1.6278219264718015,
      "grad_norm": 2.723923921585083,
      "learning_rate": 1.1175305381313965e-05,
      "loss": 0.41064441680908204,
      "step": 14800
    },
    {
      "epoch": 1.6278219264718015,
      "eval_loss": 0.520072877407074,
      "eval_runtime": 1.2005,
      "eval_samples_per_second": 83.302,
      "eval_steps_per_second": 14.161,
      "step": 14800
    },
    {
      "epoch": 1.6333214177688564,
      "grad_norm": 3.793158531188965,
      "learning_rate": 1.1010234400792341e-05,
      "loss": 0.38922351837158203,
      "step": 14850
    },
    {
      "epoch": 1.6333214177688564,
      "eval_loss": 0.5236958861351013,
      "eval_runtime": 1.2009,
      "eval_samples_per_second": 83.269,
      "eval_steps_per_second": 14.156,
      "step": 14850
    },
    {
      "epoch": 1.6388209090659114,
      "grad_norm": 5.206042766571045,
      "learning_rate": 1.0845163420270717e-05,
      "loss": 0.3783760070800781,
      "step": 14900
    },
    {
      "epoch": 1.6388209090659114,
      "eval_loss": 0.5220252871513367,
      "eval_runtime": 1.2755,
      "eval_samples_per_second": 78.399,
      "eval_steps_per_second": 13.328,
      "step": 14900
    },
    {
      "epoch": 1.6443204003629663,
      "grad_norm": 3.5335276126861572,
      "learning_rate": 1.0680092439749092e-05,
      "loss": 0.36626754760742186,
      "step": 14950
    },
    {
      "epoch": 1.6443204003629663,
      "eval_loss": 0.5257189869880676,
      "eval_runtime": 1.2584,
      "eval_samples_per_second": 79.467,
      "eval_steps_per_second": 13.509,
      "step": 14950
    },
    {
      "epoch": 1.6498198916600213,
      "grad_norm": 5.903299331665039,
      "learning_rate": 1.0515021459227468e-05,
      "loss": 0.4300186538696289,
      "step": 15000
    },
    {
      "epoch": 1.6498198916600213,
      "eval_loss": 0.5119779109954834,
      "eval_runtime": 1.2824,
      "eval_samples_per_second": 77.977,
      "eval_steps_per_second": 13.256,
      "step": 15000
    },
    {
      "epoch": 1.6553193829570765,
      "grad_norm": 4.042174339294434,
      "learning_rate": 1.0349950478705845e-05,
      "loss": 0.4231399154663086,
      "step": 15050
    },
    {
      "epoch": 1.6553193829570765,
      "eval_loss": 0.5127305388450623,
      "eval_runtime": 1.2793,
      "eval_samples_per_second": 78.169,
      "eval_steps_per_second": 13.289,
      "step": 15050
    },
    {
      "epoch": 1.6608188742541314,
      "grad_norm": 4.595501899719238,
      "learning_rate": 1.018487949818422e-05,
      "loss": 0.3916609573364258,
      "step": 15100
    },
    {
      "epoch": 1.6608188742541314,
      "eval_loss": 0.5223040580749512,
      "eval_runtime": 1.2795,
      "eval_samples_per_second": 78.156,
      "eval_steps_per_second": 13.286,
      "step": 15100
    },
    {
      "epoch": 1.6663183655511866,
      "grad_norm": 4.4538798332214355,
      "learning_rate": 1.0019808517662595e-05,
      "loss": 0.4184587860107422,
      "step": 15150
    },
    {
      "epoch": 1.6663183655511866,
      "eval_loss": 0.534669041633606,
      "eval_runtime": 1.2782,
      "eval_samples_per_second": 78.233,
      "eval_steps_per_second": 13.3,
      "step": 15150
    },
    {
      "epoch": 1.6718178568482416,
      "grad_norm": 3.8044581413269043,
      "learning_rate": 9.854737537140972e-06,
      "loss": 0.39158470153808594,
      "step": 15200
    },
    {
      "epoch": 1.6718178568482416,
      "eval_loss": 0.5418866872787476,
      "eval_runtime": 1.2799,
      "eval_samples_per_second": 78.131,
      "eval_steps_per_second": 13.282,
      "step": 15200
    },
    {
      "epoch": 1.6773173481452965,
      "grad_norm": 2.9677321910858154,
      "learning_rate": 9.689666556619348e-06,
      "loss": 0.43468849182128905,
      "step": 15250
    },
    {
      "epoch": 1.6773173481452965,
      "eval_loss": 0.526294469833374,
      "eval_runtime": 1.2805,
      "eval_samples_per_second": 78.096,
      "eval_steps_per_second": 13.276,
      "step": 15250
    },
    {
      "epoch": 1.6828168394423515,
      "grad_norm": 3.6569182872772217,
      "learning_rate": 9.52459557609772e-06,
      "loss": 0.4084419631958008,
      "step": 15300
    },
    {
      "epoch": 1.6828168394423515,
      "eval_loss": 0.5179707407951355,
      "eval_runtime": 1.2802,
      "eval_samples_per_second": 78.114,
      "eval_steps_per_second": 13.279,
      "step": 15300
    },
    {
      "epoch": 1.6883163307394065,
      "grad_norm": 4.213144302368164,
      "learning_rate": 9.359524595576097e-06,
      "loss": 0.40570945739746095,
      "step": 15350
    },
    {
      "epoch": 1.6883163307394065,
      "eval_loss": 0.523230791091919,
      "eval_runtime": 1.2787,
      "eval_samples_per_second": 78.203,
      "eval_steps_per_second": 13.294,
      "step": 15350
    },
    {
      "epoch": 1.6938158220364616,
      "grad_norm": 4.362399578094482,
      "learning_rate": 9.194453615054473e-06,
      "loss": 0.40546306610107424,
      "step": 15400
    },
    {
      "epoch": 1.6938158220364616,
      "eval_loss": 0.5279385447502136,
      "eval_runtime": 1.2871,
      "eval_samples_per_second": 77.697,
      "eval_steps_per_second": 13.208,
      "step": 15400
    },
    {
      "epoch": 1.6993153133335166,
      "grad_norm": 5.424959182739258,
      "learning_rate": 9.02938263453285e-06,
      "loss": 0.39811588287353517,
      "step": 15450
    },
    {
      "epoch": 1.6993153133335166,
      "eval_loss": 0.538982093334198,
      "eval_runtime": 1.3011,
      "eval_samples_per_second": 76.856,
      "eval_steps_per_second": 13.065,
      "step": 15450
    },
    {
      "epoch": 1.7048148046305718,
      "grad_norm": 3.6755897998809814,
      "learning_rate": 8.864311654011224e-06,
      "loss": 0.4292662811279297,
      "step": 15500
    },
    {
      "epoch": 1.7048148046305718,
      "eval_loss": 0.5277052521705627,
      "eval_runtime": 1.2769,
      "eval_samples_per_second": 78.312,
      "eval_steps_per_second": 13.313,
      "step": 15500
    },
    {
      "epoch": 1.7103142959276267,
      "grad_norm": 3.7990050315856934,
      "learning_rate": 8.6992406734896e-06,
      "loss": 0.38744674682617186,
      "step": 15550
    },
    {
      "epoch": 1.7103142959276267,
      "eval_loss": 0.5234823226928711,
      "eval_runtime": 1.2814,
      "eval_samples_per_second": 78.04,
      "eval_steps_per_second": 13.267,
      "step": 15550
    },
    {
      "epoch": 1.7158137872246817,
      "grad_norm": 5.55524206161499,
      "learning_rate": 8.534169692967977e-06,
      "loss": 0.39183277130126953,
      "step": 15600
    },
    {
      "epoch": 1.7158137872246817,
      "eval_loss": 0.5209484100341797,
      "eval_runtime": 1.2795,
      "eval_samples_per_second": 78.157,
      "eval_steps_per_second": 13.287,
      "step": 15600
    },
    {
      "epoch": 1.7213132785217367,
      "grad_norm": 4.018246173858643,
      "learning_rate": 8.369098712446351e-06,
      "loss": 0.4041017532348633,
      "step": 15650
    },
    {
      "epoch": 1.7213132785217367,
      "eval_loss": 0.526258111000061,
      "eval_runtime": 1.2793,
      "eval_samples_per_second": 78.17,
      "eval_steps_per_second": 13.289,
      "step": 15650
    },
    {
      "epoch": 1.7268127698187916,
      "grad_norm": 4.710935592651367,
      "learning_rate": 8.204027731924728e-06,
      "loss": 0.3836952209472656,
      "step": 15700
    },
    {
      "epoch": 1.7268127698187916,
      "eval_loss": 0.5209237933158875,
      "eval_runtime": 1.279,
      "eval_samples_per_second": 78.187,
      "eval_steps_per_second": 13.292,
      "step": 15700
    },
    {
      "epoch": 1.7323122611158468,
      "grad_norm": 3.7639029026031494,
      "learning_rate": 8.038956751403104e-06,
      "loss": 0.3907876968383789,
      "step": 15750
    },
    {
      "epoch": 1.7323122611158468,
      "eval_loss": 0.5245873928070068,
      "eval_runtime": 1.2785,
      "eval_samples_per_second": 78.214,
      "eval_steps_per_second": 13.296,
      "step": 15750
    },
    {
      "epoch": 1.7378117524129018,
      "grad_norm": 3.944993257522583,
      "learning_rate": 7.87388577088148e-06,
      "loss": 0.3886819839477539,
      "step": 15800
    },
    {
      "epoch": 1.7378117524129018,
      "eval_loss": 0.5302055478096008,
      "eval_runtime": 1.2805,
      "eval_samples_per_second": 78.095,
      "eval_steps_per_second": 13.276,
      "step": 15800
    },
    {
      "epoch": 1.743311243709957,
      "grad_norm": 3.7543132305145264,
      "learning_rate": 7.708814790359855e-06,
      "loss": 0.4201182174682617,
      "step": 15850
    },
    {
      "epoch": 1.743311243709957,
      "eval_loss": 0.5063754320144653,
      "eval_runtime": 1.2803,
      "eval_samples_per_second": 78.105,
      "eval_steps_per_second": 13.278,
      "step": 15850
    },
    {
      "epoch": 1.748810735007012,
      "grad_norm": 2.934755325317383,
      "learning_rate": 7.543743809838231e-06,
      "loss": 0.3904559326171875,
      "step": 15900
    },
    {
      "epoch": 1.748810735007012,
      "eval_loss": 0.5102057456970215,
      "eval_runtime": 1.2789,
      "eval_samples_per_second": 78.19,
      "eval_steps_per_second": 13.292,
      "step": 15900
    },
    {
      "epoch": 1.7543102263040669,
      "grad_norm": 4.1210246086120605,
      "learning_rate": 7.378672829316606e-06,
      "loss": 0.3794166946411133,
      "step": 15950
    },
    {
      "epoch": 1.7543102263040669,
      "eval_loss": 0.5126526355743408,
      "eval_runtime": 1.2826,
      "eval_samples_per_second": 77.967,
      "eval_steps_per_second": 13.254,
      "step": 15950
    },
    {
      "epoch": 1.7598097176011218,
      "grad_norm": 3.7067854404449463,
      "learning_rate": 7.213601848794982e-06,
      "loss": 0.3692531967163086,
      "step": 16000
    },
    {
      "epoch": 1.7598097176011218,
      "eval_loss": 0.5274832248687744,
      "eval_runtime": 1.2797,
      "eval_samples_per_second": 78.143,
      "eval_steps_per_second": 13.284,
      "step": 16000
    },
    {
      "epoch": 1.7653092088981768,
      "grad_norm": 3.6420602798461914,
      "learning_rate": 7.048530868273357e-06,
      "loss": 0.3824466705322266,
      "step": 16050
    },
    {
      "epoch": 1.7653092088981768,
      "eval_loss": 0.5196187496185303,
      "eval_runtime": 1.2795,
      "eval_samples_per_second": 78.158,
      "eval_steps_per_second": 13.287,
      "step": 16050
    },
    {
      "epoch": 1.770808700195232,
      "grad_norm": 4.638594150543213,
      "learning_rate": 6.883459887751733e-06,
      "loss": 0.4514438629150391,
      "step": 16100
    },
    {
      "epoch": 1.770808700195232,
      "eval_loss": 0.5215907096862793,
      "eval_runtime": 1.2805,
      "eval_samples_per_second": 78.097,
      "eval_steps_per_second": 13.277,
      "step": 16100
    },
    {
      "epoch": 1.776308191492287,
      "grad_norm": 3.9953904151916504,
      "learning_rate": 6.718388907230109e-06,
      "loss": 0.387623176574707,
      "step": 16150
    },
    {
      "epoch": 1.776308191492287,
      "eval_loss": 0.5224502682685852,
      "eval_runtime": 1.2817,
      "eval_samples_per_second": 78.022,
      "eval_steps_per_second": 13.264,
      "step": 16150
    },
    {
      "epoch": 1.781807682789342,
      "grad_norm": 4.487403869628906,
      "learning_rate": 6.553317926708485e-06,
      "loss": 0.4063478088378906,
      "step": 16200
    },
    {
      "epoch": 1.781807682789342,
      "eval_loss": 0.5166334509849548,
      "eval_runtime": 1.277,
      "eval_samples_per_second": 78.307,
      "eval_steps_per_second": 13.312,
      "step": 16200
    },
    {
      "epoch": 1.787307174086397,
      "grad_norm": 3.7964556217193604,
      "learning_rate": 6.3882469461868605e-06,
      "loss": 0.3855398559570313,
      "step": 16250
    },
    {
      "epoch": 1.787307174086397,
      "eval_loss": 0.5154201984405518,
      "eval_runtime": 1.2833,
      "eval_samples_per_second": 77.926,
      "eval_steps_per_second": 13.247,
      "step": 16250
    },
    {
      "epoch": 1.792806665383452,
      "grad_norm": 4.513696193695068,
      "learning_rate": 6.223175965665237e-06,
      "loss": 0.3669796371459961,
      "step": 16300
    },
    {
      "epoch": 1.792806665383452,
      "eval_loss": 0.5084086656570435,
      "eval_runtime": 1.28,
      "eval_samples_per_second": 78.125,
      "eval_steps_per_second": 13.281,
      "step": 16300
    },
    {
      "epoch": 1.798306156680507,
      "grad_norm": 3.982877254486084,
      "learning_rate": 6.058104985143612e-06,
      "loss": 0.38849113464355467,
      "step": 16350
    },
    {
      "epoch": 1.798306156680507,
      "eval_loss": 0.5200368762016296,
      "eval_runtime": 1.2802,
      "eval_samples_per_second": 78.112,
      "eval_steps_per_second": 13.279,
      "step": 16350
    },
    {
      "epoch": 1.803805647977562,
      "grad_norm": 3.997793436050415,
      "learning_rate": 5.8930340046219876e-06,
      "loss": 0.39702865600585935,
      "step": 16400
    },
    {
      "epoch": 1.803805647977562,
      "eval_loss": 0.5119373798370361,
      "eval_runtime": 1.283,
      "eval_samples_per_second": 77.941,
      "eval_steps_per_second": 13.25,
      "step": 16400
    },
    {
      "epoch": 1.8093051392746171,
      "grad_norm": 3.6325302124023438,
      "learning_rate": 5.727963024100363e-06,
      "loss": 0.37990386962890627,
      "step": 16450
    },
    {
      "epoch": 1.8093051392746171,
      "eval_loss": 0.5215651988983154,
      "eval_runtime": 1.2798,
      "eval_samples_per_second": 78.139,
      "eval_steps_per_second": 13.284,
      "step": 16450
    },
    {
      "epoch": 1.814804630571672,
      "grad_norm": 4.198485374450684,
      "learning_rate": 5.562892043578738e-06,
      "loss": 0.412078857421875,
      "step": 16500
    },
    {
      "epoch": 1.814804630571672,
      "eval_loss": 0.5170506238937378,
      "eval_runtime": 1.2894,
      "eval_samples_per_second": 77.558,
      "eval_steps_per_second": 13.185,
      "step": 16500
    },
    {
      "epoch": 1.8203041218687273,
      "grad_norm": 4.591159820556641,
      "learning_rate": 5.397821063057115e-06,
      "loss": 0.37816055297851564,
      "step": 16550
    },
    {
      "epoch": 1.8203041218687273,
      "eval_loss": 0.5147603750228882,
      "eval_runtime": 1.2799,
      "eval_samples_per_second": 78.134,
      "eval_steps_per_second": 13.283,
      "step": 16550
    },
    {
      "epoch": 1.8258036131657822,
      "grad_norm": 4.216943264007568,
      "learning_rate": 5.23275008253549e-06,
      "loss": 0.39028087615966794,
      "step": 16600
    },
    {
      "epoch": 1.8258036131657822,
      "eval_loss": 0.5204047560691833,
      "eval_runtime": 1.2795,
      "eval_samples_per_second": 78.156,
      "eval_steps_per_second": 13.286,
      "step": 16600
    },
    {
      "epoch": 1.8313031044628372,
      "grad_norm": 4.006322383880615,
      "learning_rate": 5.067679102013866e-06,
      "loss": 0.38647769927978515,
      "step": 16650
    },
    {
      "epoch": 1.8313031044628372,
      "eval_loss": 0.5153352618217468,
      "eval_runtime": 1.279,
      "eval_samples_per_second": 78.184,
      "eval_steps_per_second": 13.291,
      "step": 16650
    },
    {
      "epoch": 1.8368025957598921,
      "grad_norm": 4.710324287414551,
      "learning_rate": 4.902608121492242e-06,
      "loss": 0.356781005859375,
      "step": 16700
    },
    {
      "epoch": 1.8368025957598921,
      "eval_loss": 0.5207862257957458,
      "eval_runtime": 1.2799,
      "eval_samples_per_second": 78.134,
      "eval_steps_per_second": 13.283,
      "step": 16700
    },
    {
      "epoch": 1.842302087056947,
      "grad_norm": 4.920437812805176,
      "learning_rate": 4.737537140970618e-06,
      "loss": 0.37074081420898436,
      "step": 16750
    },
    {
      "epoch": 1.842302087056947,
      "eval_loss": 0.5112919807434082,
      "eval_runtime": 1.2801,
      "eval_samples_per_second": 78.118,
      "eval_steps_per_second": 13.28,
      "step": 16750
    },
    {
      "epoch": 1.8478015783540023,
      "grad_norm": 4.515045166015625,
      "learning_rate": 4.5724661604489934e-06,
      "loss": 0.4274590301513672,
      "step": 16800
    },
    {
      "epoch": 1.8478015783540023,
      "eval_loss": 0.5242478847503662,
      "eval_runtime": 1.279,
      "eval_samples_per_second": 78.188,
      "eval_steps_per_second": 13.292,
      "step": 16800
    },
    {
      "epoch": 1.8533010696510572,
      "grad_norm": 3.6244614124298096,
      "learning_rate": 4.40739517992737e-06,
      "loss": 0.3897795867919922,
      "step": 16850
    },
    {
      "epoch": 1.8533010696510572,
      "eval_loss": 0.5210970044136047,
      "eval_runtime": 1.2792,
      "eval_samples_per_second": 78.176,
      "eval_steps_per_second": 13.29,
      "step": 16850
    },
    {
      "epoch": 1.8588005609481124,
      "grad_norm": 4.448500633239746,
      "learning_rate": 4.242324199405744e-06,
      "loss": 0.43310935974121095,
      "step": 16900
    },
    {
      "epoch": 1.8588005609481124,
      "eval_loss": 0.5130022764205933,
      "eval_runtime": 1.2867,
      "eval_samples_per_second": 77.716,
      "eval_steps_per_second": 13.212,
      "step": 16900
    },
    {
      "epoch": 1.8643000522451674,
      "grad_norm": 5.259810924530029,
      "learning_rate": 4.07725321888412e-06,
      "loss": 0.4260225677490234,
      "step": 16950
    },
    {
      "epoch": 1.8643000522451674,
      "eval_loss": 0.5134211778640747,
      "eval_runtime": 1.2967,
      "eval_samples_per_second": 77.117,
      "eval_steps_per_second": 13.11,
      "step": 16950
    },
    {
      "epoch": 1.8697995435422223,
      "grad_norm": 4.863224983215332,
      "learning_rate": 3.912182238362496e-06,
      "loss": 0.3758648681640625,
      "step": 17000
    },
    {
      "epoch": 1.8697995435422223,
      "eval_loss": 0.5177444219589233,
      "eval_runtime": 1.28,
      "eval_samples_per_second": 78.125,
      "eval_steps_per_second": 13.281,
      "step": 17000
    },
    {
      "epoch": 1.8752990348392773,
      "grad_norm": 4.33119535446167,
      "learning_rate": 3.747111257840872e-06,
      "loss": 0.3959685516357422,
      "step": 17050
    },
    {
      "epoch": 1.8752990348392773,
      "eval_loss": 0.5147886872291565,
      "eval_runtime": 1.2779,
      "eval_samples_per_second": 78.252,
      "eval_steps_per_second": 13.303,
      "step": 17050
    },
    {
      "epoch": 1.8807985261363322,
      "grad_norm": 4.343754768371582,
      "learning_rate": 3.582040277319247e-06,
      "loss": 0.3876182556152344,
      "step": 17100
    },
    {
      "epoch": 1.8807985261363322,
      "eval_loss": 0.5101519227027893,
      "eval_runtime": 1.2814,
      "eval_samples_per_second": 78.041,
      "eval_steps_per_second": 13.267,
      "step": 17100
    },
    {
      "epoch": 1.8862980174333874,
      "grad_norm": 4.579135894775391,
      "learning_rate": 3.416969296797623e-06,
      "loss": 0.3915593338012695,
      "step": 17150
    },
    {
      "epoch": 1.8862980174333874,
      "eval_loss": 0.5131881833076477,
      "eval_runtime": 1.3052,
      "eval_samples_per_second": 76.615,
      "eval_steps_per_second": 13.025,
      "step": 17150
    },
    {
      "epoch": 1.8917975087304424,
      "grad_norm": 4.940543174743652,
      "learning_rate": 3.251898316275999e-06,
      "loss": 0.38781646728515623,
      "step": 17200
    },
    {
      "epoch": 1.8917975087304424,
      "eval_loss": 0.514817476272583,
      "eval_runtime": 1.2836,
      "eval_samples_per_second": 77.907,
      "eval_steps_per_second": 13.244,
      "step": 17200
    },
    {
      "epoch": 1.8972970000274976,
      "grad_norm": 5.684414386749268,
      "learning_rate": 3.0868273357543743e-06,
      "loss": 0.40284725189208986,
      "step": 17250
    },
    {
      "epoch": 1.8972970000274976,
      "eval_loss": 0.5099514126777649,
      "eval_runtime": 1.3521,
      "eval_samples_per_second": 73.959,
      "eval_steps_per_second": 12.573,
      "step": 17250
    },
    {
      "epoch": 1.9027964913245525,
      "grad_norm": 4.87332820892334,
      "learning_rate": 2.92175635523275e-06,
      "loss": 0.40561714172363283,
      "step": 17300
    },
    {
      "epoch": 1.9027964913245525,
      "eval_loss": 0.5140570402145386,
      "eval_runtime": 1.2856,
      "eval_samples_per_second": 77.787,
      "eval_steps_per_second": 13.224,
      "step": 17300
    },
    {
      "epoch": 1.9082959826216075,
      "grad_norm": 4.406585216522217,
      "learning_rate": 2.756685374711126e-06,
      "loss": 0.4014255523681641,
      "step": 17350
    },
    {
      "epoch": 1.9082959826216075,
      "eval_loss": 0.5200029611587524,
      "eval_runtime": 1.2949,
      "eval_samples_per_second": 77.224,
      "eval_steps_per_second": 13.128,
      "step": 17350
    },
    {
      "epoch": 1.9137954739186624,
      "grad_norm": 3.8450374603271484,
      "learning_rate": 2.591614394189502e-06,
      "loss": 0.3946284103393555,
      "step": 17400
    },
    {
      "epoch": 1.9137954739186624,
      "eval_loss": 0.5157837867736816,
      "eval_runtime": 1.2818,
      "eval_samples_per_second": 78.013,
      "eval_steps_per_second": 13.262,
      "step": 17400
    },
    {
      "epoch": 1.9192949652157174,
      "grad_norm": 2.9785866737365723,
      "learning_rate": 2.4265434136678772e-06,
      "loss": 0.38735130310058596,
      "step": 17450
    },
    {
      "epoch": 1.9192949652157174,
      "eval_loss": 0.5129509568214417,
      "eval_runtime": 1.2915,
      "eval_samples_per_second": 77.427,
      "eval_steps_per_second": 13.163,
      "step": 17450
    },
    {
      "epoch": 1.9247944565127726,
      "grad_norm": 4.774247646331787,
      "learning_rate": 2.2614724331462527e-06,
      "loss": 0.3915607452392578,
      "step": 17500
    },
    {
      "epoch": 1.9247944565127726,
      "eval_loss": 0.512159526348114,
      "eval_runtime": 1.3529,
      "eval_samples_per_second": 73.915,
      "eval_steps_per_second": 12.566,
      "step": 17500
    },
    {
      "epoch": 1.9302939478098275,
      "grad_norm": 3.1161727905273438,
      "learning_rate": 2.0964014526246285e-06,
      "loss": 0.3839557647705078,
      "step": 17550
    },
    {
      "epoch": 1.9302939478098275,
      "eval_loss": 0.5124543905258179,
      "eval_runtime": 1.3002,
      "eval_samples_per_second": 76.909,
      "eval_steps_per_second": 13.075,
      "step": 17550
    },
    {
      "epoch": 1.9357934391068827,
      "grad_norm": 4.420716762542725,
      "learning_rate": 1.9313304721030043e-06,
      "loss": 0.4010445022583008,
      "step": 17600
    },
    {
      "epoch": 1.9357934391068827,
      "eval_loss": 0.5172660946846008,
      "eval_runtime": 1.2925,
      "eval_samples_per_second": 77.37,
      "eval_steps_per_second": 13.153,
      "step": 17600
    },
    {
      "epoch": 1.9412929304039377,
      "grad_norm": 4.979782581329346,
      "learning_rate": 1.76625949158138e-06,
      "loss": 0.3870741653442383,
      "step": 17650
    },
    {
      "epoch": 1.9412929304039377,
      "eval_loss": 0.5163105130195618,
      "eval_runtime": 1.2824,
      "eval_samples_per_second": 77.978,
      "eval_steps_per_second": 13.256,
      "step": 17650
    },
    {
      "epoch": 1.9467924217009926,
      "grad_norm": 5.315701484680176,
      "learning_rate": 1.6011885110597558e-06,
      "loss": 0.3857357406616211,
      "step": 17700
    },
    {
      "epoch": 1.9467924217009926,
      "eval_loss": 0.5164580345153809,
      "eval_runtime": 1.2821,
      "eval_samples_per_second": 77.995,
      "eval_steps_per_second": 13.259,
      "step": 17700
    },
    {
      "epoch": 1.9522919129980476,
      "grad_norm": 3.6524667739868164,
      "learning_rate": 1.4361175305381314e-06,
      "loss": 0.42781547546386717,
      "step": 17750
    },
    {
      "epoch": 1.9522919129980476,
      "eval_loss": 0.5149794816970825,
      "eval_runtime": 1.3408,
      "eval_samples_per_second": 74.583,
      "eval_steps_per_second": 12.679,
      "step": 17750
    },
    {
      "epoch": 1.9577914042951026,
      "grad_norm": 4.06256103515625,
      "learning_rate": 1.2710465500165073e-06,
      "loss": 0.380059700012207,
      "step": 17800
    },
    {
      "epoch": 1.9577914042951026,
      "eval_loss": 0.5115500688552856,
      "eval_runtime": 1.3186,
      "eval_samples_per_second": 75.841,
      "eval_steps_per_second": 12.893,
      "step": 17800
    },
    {
      "epoch": 1.9632908955921577,
      "grad_norm": 3.9045357704162598,
      "learning_rate": 1.1059755694948827e-06,
      "loss": 0.38892536163330077,
      "step": 17850
    },
    {
      "epoch": 1.9632908955921577,
      "eval_loss": 0.5084894895553589,
      "eval_runtime": 1.2809,
      "eval_samples_per_second": 78.07,
      "eval_steps_per_second": 13.272,
      "step": 17850
    },
    {
      "epoch": 1.9687903868892127,
      "grad_norm": 4.216691970825195,
      "learning_rate": 9.409045889732585e-07,
      "loss": 0.40333850860595705,
      "step": 17900
    },
    {
      "epoch": 1.9687903868892127,
      "eval_loss": 0.5091243982315063,
      "eval_runtime": 1.3023,
      "eval_samples_per_second": 76.788,
      "eval_steps_per_second": 13.054,
      "step": 17900
    },
    {
      "epoch": 1.9742898781862679,
      "grad_norm": 4.339031219482422,
      "learning_rate": 7.758336084516343e-07,
      "loss": 0.41892166137695314,
      "step": 17950
    },
    {
      "epoch": 1.9742898781862679,
      "eval_loss": 0.5089672207832336,
      "eval_runtime": 1.3698,
      "eval_samples_per_second": 73.001,
      "eval_steps_per_second": 12.41,
      "step": 17950
    },
    {
      "epoch": 1.9797893694833228,
      "grad_norm": 5.501232147216797,
      "learning_rate": 6.107626279300099e-07,
      "loss": 0.38524158477783205,
      "step": 18000
    },
    {
      "epoch": 1.9797893694833228,
      "eval_loss": 0.5088917016983032,
      "eval_runtime": 1.3056,
      "eval_samples_per_second": 76.593,
      "eval_steps_per_second": 13.021,
      "step": 18000
    },
    {
      "epoch": 1.9852888607803778,
      "grad_norm": 4.044425010681152,
      "learning_rate": 4.456916474083856e-07,
      "loss": 0.36035297393798826,
      "step": 18050
    },
    {
      "epoch": 1.9852888607803778,
      "eval_loss": 0.50870680809021,
      "eval_runtime": 1.2937,
      "eval_samples_per_second": 77.298,
      "eval_steps_per_second": 13.141,
      "step": 18050
    },
    {
      "epoch": 1.9907883520774328,
      "grad_norm": 3.8273727893829346,
      "learning_rate": 2.8062066688676135e-07,
      "loss": 0.3866265869140625,
      "step": 18100
    },
    {
      "epoch": 1.9907883520774328,
      "eval_loss": 0.5090622901916504,
      "eval_runtime": 1.2874,
      "eval_samples_per_second": 77.679,
      "eval_steps_per_second": 13.205,
      "step": 18100
    },
    {
      "epoch": 1.9962878433744877,
      "grad_norm": 5.9300537109375,
      "learning_rate": 1.15549686365137e-07,
      "loss": 0.3838529586791992,
      "step": 18150
    },
    {
      "epoch": 1.9962878433744877,
      "eval_loss": 0.5087066292762756,
      "eval_runtime": 1.2885,
      "eval_samples_per_second": 77.61,
      "eval_steps_per_second": 13.194,
      "step": 18150
    }
  ],
  "logging_steps": 50,
  "max_steps": 18184,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.6375279506569626e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}