{
  "best_metric": 0.5393198132514954,
  "best_model_checkpoint": "/media/user/Expansion/flan-t5-small-ner/checkpoint-99955",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 99955,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02501125506477915,
      "grad_norm": 27.66358757019043,
      "learning_rate": 4.974988744935221e-05,
      "loss": 4.6267,
      "num_input_tokens_seen": 1673336,
      "step": 500
    },
    {
      "epoch": 0.0500225101295583,
      "grad_norm": 9.223219871520996,
      "learning_rate": 4.949977489870442e-05,
      "loss": 2.1909,
      "num_input_tokens_seen": 3361736,
      "step": 1000
    },
    {
      "epoch": 0.07503376519433745,
      "grad_norm": 15.481683731079102,
      "learning_rate": 4.924966234805663e-05,
      "loss": 1.8355,
      "num_input_tokens_seen": 5013800,
      "step": 1500
    },
    {
      "epoch": 0.1000450202591166,
      "grad_norm": 14.396512985229492,
      "learning_rate": 4.8999549797408836e-05,
      "loss": 1.5648,
      "num_input_tokens_seen": 6667312,
      "step": 2000
    },
    {
      "epoch": 0.12505627532389577,
      "grad_norm": 7.068989276885986,
      "learning_rate": 4.8749437246761046e-05,
      "loss": 1.4252,
      "num_input_tokens_seen": 8347016,
      "step": 2500
    },
    {
      "epoch": 0.1500675303886749,
      "grad_norm": 11.330971717834473,
      "learning_rate": 4.849932469611325e-05,
      "loss": 1.3972,
      "num_input_tokens_seen": 10008296,
      "step": 3000
    },
    {
      "epoch": 0.17507878545345407,
      "grad_norm": 9.403321266174316,
      "learning_rate": 4.824921214546546e-05,
      "loss": 1.3001,
      "num_input_tokens_seen": 11658808,
      "step": 3500
    },
    {
      "epoch": 0.2000900405182332,
      "grad_norm": 8.147115707397461,
      "learning_rate": 4.799909959481767e-05,
      "loss": 1.2625,
      "num_input_tokens_seen": 13331648,
      "step": 4000
    },
    {
      "epoch": 0.22510129558301237,
      "grad_norm": 13.405184745788574,
      "learning_rate": 4.774898704416988e-05,
      "loss": 1.1839,
      "num_input_tokens_seen": 14982440,
      "step": 4500
    },
    {
      "epoch": 0.25011255064779153,
      "grad_norm": 20.70949363708496,
      "learning_rate": 4.749887449352209e-05,
      "loss": 1.1598,
      "num_input_tokens_seen": 16633632,
      "step": 5000
    },
    {
      "epoch": 0.27512380571257067,
      "grad_norm": 16.94267463684082,
      "learning_rate": 4.72487619428743e-05,
      "loss": 1.1473,
      "num_input_tokens_seen": 18311672,
      "step": 5500
    },
    {
      "epoch": 0.3001350607773498,
      "grad_norm": 8.609989166259766,
      "learning_rate": 4.69986493922265e-05,
      "loss": 1.1098,
      "num_input_tokens_seen": 19980456,
      "step": 6000
    },
    {
      "epoch": 0.32514631584212894,
      "grad_norm": 9.003643989562988,
      "learning_rate": 4.674853684157871e-05,
      "loss": 1.0973,
      "num_input_tokens_seen": 21646328,
      "step": 6500
    },
    {
      "epoch": 0.35015757090690813,
      "grad_norm": 18.364194869995117,
      "learning_rate": 4.649842429093092e-05,
      "loss": 1.0987,
      "num_input_tokens_seen": 23277400,
      "step": 7000
    },
    {
      "epoch": 0.37516882597168727,
      "grad_norm": 13.544733047485352,
      "learning_rate": 4.624831174028313e-05,
      "loss": 1.0642,
      "num_input_tokens_seen": 24915304,
      "step": 7500
    },
    {
      "epoch": 0.4001800810364664,
      "grad_norm": 14.257452011108398,
      "learning_rate": 4.5998199189635336e-05,
      "loss": 1.0414,
      "num_input_tokens_seen": 26590576,
      "step": 8000
    },
    {
      "epoch": 0.42519133610124554,
      "grad_norm": 10.29515266418457,
      "learning_rate": 4.5748086638987546e-05,
      "loss": 1.0634,
      "num_input_tokens_seen": 28236280,
      "step": 8500
    },
    {
      "epoch": 0.45020259116602473,
      "grad_norm": 13.840631484985352,
      "learning_rate": 4.5497974088339756e-05,
      "loss": 0.9817,
      "num_input_tokens_seen": 29891480,
      "step": 9000
    },
    {
      "epoch": 0.47521384623080387,
      "grad_norm": 12.118327140808105,
      "learning_rate": 4.5247861537691966e-05,
      "loss": 1.0122,
      "num_input_tokens_seen": 31551000,
      "step": 9500
    },
    {
      "epoch": 0.5002251012955831,
      "grad_norm": 8.115203857421875,
      "learning_rate": 4.499774898704417e-05,
      "loss": 0.9802,
      "num_input_tokens_seen": 33221384,
      "step": 10000
    },
    {
      "epoch": 0.5252363563603621,
      "grad_norm": 8.905954360961914,
      "learning_rate": 4.474763643639638e-05,
      "loss": 0.9796,
      "num_input_tokens_seen": 34891392,
      "step": 10500
    },
    {
      "epoch": 0.5502476114251413,
      "grad_norm": 10.70656681060791,
      "learning_rate": 4.449752388574859e-05,
      "loss": 1.0031,
      "num_input_tokens_seen": 36518768,
      "step": 11000
    },
    {
      "epoch": 0.5752588664899204,
      "grad_norm": 12.424896240234375,
      "learning_rate": 4.42474113351008e-05,
      "loss": 0.9591,
      "num_input_tokens_seen": 38147456,
      "step": 11500
    },
    {
      "epoch": 0.6002701215546996,
      "grad_norm": 10.77695083618164,
      "learning_rate": 4.399729878445301e-05,
      "loss": 0.9338,
      "num_input_tokens_seen": 39823976,
      "step": 12000
    },
    {
      "epoch": 0.6252813766194788,
      "grad_norm": 12.77743911743164,
      "learning_rate": 4.374718623380521e-05,
      "loss": 0.9112,
      "num_input_tokens_seen": 41493480,
      "step": 12500
    },
    {
      "epoch": 0.6502926316842579,
      "grad_norm": 16.060897827148438,
      "learning_rate": 4.349707368315742e-05,
      "loss": 0.915,
      "num_input_tokens_seen": 43130832,
      "step": 13000
    },
    {
      "epoch": 0.6753038867490371,
      "grad_norm": 17.562183380126953,
      "learning_rate": 4.324696113250963e-05,
      "loss": 0.9096,
      "num_input_tokens_seen": 44779392,
      "step": 13500
    },
    {
      "epoch": 0.7003151418138163,
      "grad_norm": 12.406323432922363,
      "learning_rate": 4.2996848581861835e-05,
      "loss": 0.9499,
      "num_input_tokens_seen": 46433856,
      "step": 14000
    },
    {
      "epoch": 0.7253263968785953,
      "grad_norm": 15.567843437194824,
      "learning_rate": 4.2746736031214045e-05,
      "loss": 0.923,
      "num_input_tokens_seen": 48102016,
      "step": 14500
    },
    {
      "epoch": 0.7503376519433745,
      "grad_norm": 9.45335578918457,
      "learning_rate": 4.2496623480566255e-05,
      "loss": 0.9285,
      "num_input_tokens_seen": 49796432,
      "step": 15000
    },
    {
      "epoch": 0.7753489070081536,
      "grad_norm": 7.158623695373535,
      "learning_rate": 4.2246510929918465e-05,
      "loss": 0.9023,
      "num_input_tokens_seen": 51432848,
      "step": 15500
    },
    {
      "epoch": 0.8003601620729328,
      "grad_norm": 9.542813301086426,
      "learning_rate": 4.1996398379270675e-05,
      "loss": 0.9237,
      "num_input_tokens_seen": 53083496,
      "step": 16000
    },
    {
      "epoch": 0.825371417137712,
      "grad_norm": 10.027923583984375,
      "learning_rate": 4.1746285828622885e-05,
      "loss": 0.8813,
      "num_input_tokens_seen": 54755032,
      "step": 16500
    },
    {
      "epoch": 0.8503826722024911,
      "grad_norm": 18.8748722076416,
      "learning_rate": 4.1496173277975095e-05,
      "loss": 0.9036,
      "num_input_tokens_seen": 56411184,
      "step": 17000
    },
    {
      "epoch": 0.8753939272672703,
      "grad_norm": 12.792276382446289,
      "learning_rate": 4.12460607273273e-05,
      "loss": 0.8589,
      "num_input_tokens_seen": 58070520,
      "step": 17500
    },
    {
      "epoch": 0.9004051823320495,
      "grad_norm": 6.8420491218566895,
      "learning_rate": 4.09959481766795e-05,
      "loss": 0.8855,
      "num_input_tokens_seen": 59745800,
      "step": 18000
    },
    {
      "epoch": 0.9254164373968286,
      "grad_norm": 9.066823959350586,
      "learning_rate": 4.074583562603171e-05,
      "loss": 0.8773,
      "num_input_tokens_seen": 61457288,
      "step": 18500
    },
    {
      "epoch": 0.9504276924616077,
      "grad_norm": 7.002307415008545,
      "learning_rate": 4.049572307538392e-05,
      "loss": 0.8747,
      "num_input_tokens_seen": 63139928,
      "step": 19000
    },
    {
      "epoch": 0.9754389475263868,
      "grad_norm": 14.685755729675293,
      "learning_rate": 4.024561052473613e-05,
      "loss": 0.8398,
      "num_input_tokens_seen": 64811920,
      "step": 19500
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6227446794509888,
      "eval_runtime": 96.3481,
      "eval_samples_per_second": 414.964,
      "eval_steps_per_second": 51.874,
      "num_input_tokens_seen": 66451084,
      "step": 19991
    },
    {
      "epoch": 1.0004502025911661,
      "grad_norm": 13.560747146606445,
      "learning_rate": 3.999549797408834e-05,
      "loss": 0.852,
      "num_input_tokens_seen": 66482076,
      "step": 20000
    },
    {
      "epoch": 1.025461457655945,
      "grad_norm": 4.446373462677002,
      "learning_rate": 3.974538542344055e-05,
      "loss": 0.7973,
      "num_input_tokens_seen": 68132180,
      "step": 20500
    },
    {
      "epoch": 1.0504727127207243,
      "grad_norm": 3.456674098968506,
      "learning_rate": 3.949527287279276e-05,
      "loss": 0.8215,
      "num_input_tokens_seen": 69804380,
      "step": 21000
    },
    {
      "epoch": 1.0754839677855035,
      "grad_norm": 8.283075332641602,
      "learning_rate": 3.924516032214497e-05,
      "loss": 0.8081,
      "num_input_tokens_seen": 71452668,
      "step": 21500
    },
    {
      "epoch": 1.1004952228502827,
      "grad_norm": 9.358149528503418,
      "learning_rate": 3.8995047771497175e-05,
      "loss": 0.7991,
      "num_input_tokens_seen": 73104948,
      "step": 22000
    },
    {
      "epoch": 1.1255064779150619,
      "grad_norm": 9.011244773864746,
      "learning_rate": 3.8744935220849385e-05,
      "loss": 0.7839,
      "num_input_tokens_seen": 74751164,
      "step": 22500
    },
    {
      "epoch": 1.1505177329798408,
      "grad_norm": 5.775268077850342,
      "learning_rate": 3.849482267020159e-05,
      "loss": 0.7515,
      "num_input_tokens_seen": 76431460,
      "step": 23000
    },
    {
      "epoch": 1.17552898804462,
      "grad_norm": 13.273436546325684,
      "learning_rate": 3.82447101195538e-05,
      "loss": 0.7821,
      "num_input_tokens_seen": 78092124,
      "step": 23500
    },
    {
      "epoch": 1.2005402431093992,
      "grad_norm": 10.351176261901855,
      "learning_rate": 3.799459756890601e-05,
      "loss": 0.772,
      "num_input_tokens_seen": 79736012,
      "step": 24000
    },
    {
      "epoch": 1.2255514981741784,
      "grad_norm": 14.834792137145996,
      "learning_rate": 3.774448501825822e-05,
      "loss": 0.78,
      "num_input_tokens_seen": 81414220,
      "step": 24500
    },
    {
      "epoch": 1.2505627532389576,
      "grad_norm": 14.160717964172363,
      "learning_rate": 3.749437246761043e-05,
      "loss": 0.7767,
      "num_input_tokens_seen": 83081932,
      "step": 25000
    },
    {
      "epoch": 1.2755740083037366,
      "grad_norm": 8.410615921020508,
      "learning_rate": 3.724425991696264e-05,
      "loss": 0.7665,
      "num_input_tokens_seen": 84745948,
      "step": 25500
    },
    {
      "epoch": 1.3005852633685158,
      "grad_norm": 7.881125450134277,
      "learning_rate": 3.699414736631484e-05,
      "loss": 0.7626,
      "num_input_tokens_seen": 86421180,
      "step": 26000
    },
    {
      "epoch": 1.325596518433295,
      "grad_norm": 21.633901596069336,
      "learning_rate": 3.674403481566705e-05,
      "loss": 0.7645,
      "num_input_tokens_seen": 88075204,
      "step": 26500
    },
    {
      "epoch": 1.3506077734980741,
      "grad_norm": 14.725602149963379,
      "learning_rate": 3.649392226501926e-05,
      "loss": 0.751,
      "num_input_tokens_seen": 89740116,
      "step": 27000
    },
    {
      "epoch": 1.3756190285628533,
      "grad_norm": 6.119060039520264,
      "learning_rate": 3.6243809714371465e-05,
      "loss": 0.756,
      "num_input_tokens_seen": 91410556,
      "step": 27500
    },
    {
      "epoch": 1.4006302836276325,
      "grad_norm": 6.520070552825928,
      "learning_rate": 3.5993697163723675e-05,
      "loss": 0.7526,
      "num_input_tokens_seen": 93116396,
      "step": 28000
    },
    {
      "epoch": 1.4256415386924115,
      "grad_norm": 7.963521480560303,
      "learning_rate": 3.5743584613075885e-05,
      "loss": 0.7645,
      "num_input_tokens_seen": 94761716,
      "step": 28500
    },
    {
      "epoch": 1.4506527937571907,
      "grad_norm": 11.38167953491211,
      "learning_rate": 3.5493472062428095e-05,
      "loss": 0.7624,
      "num_input_tokens_seen": 96449700,
      "step": 29000
    },
    {
      "epoch": 1.4756640488219699,
      "grad_norm": 15.715912818908691,
      "learning_rate": 3.5243359511780305e-05,
      "loss": 0.7509,
      "num_input_tokens_seen": 98102252,
      "step": 29500
    },
    {
      "epoch": 1.500675303886749,
      "grad_norm": 7.735713005065918,
      "learning_rate": 3.499324696113251e-05,
      "loss": 0.7738,
      "num_input_tokens_seen": 99780396,
      "step": 30000
    },
    {
      "epoch": 1.525686558951528,
      "grad_norm": 8.079352378845215,
      "learning_rate": 3.474313441048472e-05,
      "loss": 0.7522,
      "num_input_tokens_seen": 101479956,
      "step": 30500
    },
    {
      "epoch": 1.5506978140163072,
      "grad_norm": 8.290655136108398,
      "learning_rate": 3.449302185983693e-05,
      "loss": 0.7381,
      "num_input_tokens_seen": 103149500,
      "step": 31000
    },
    {
      "epoch": 1.5757090690810864,
      "grad_norm": 8.904264450073242,
      "learning_rate": 3.424290930918914e-05,
      "loss": 0.7467,
      "num_input_tokens_seen": 104812996,
      "step": 31500
    },
    {
      "epoch": 1.6007203241458656,
      "grad_norm": 7.439008712768555,
      "learning_rate": 3.399279675854135e-05,
      "loss": 0.7507,
      "num_input_tokens_seen": 106479036,
      "step": 32000
    },
    {
      "epoch": 1.6257315792106448,
      "grad_norm": 7.584664344787598,
      "learning_rate": 3.374268420789355e-05,
      "loss": 0.7168,
      "num_input_tokens_seen": 108141364,
      "step": 32500
    },
    {
      "epoch": 1.650742834275424,
      "grad_norm": 8.953302383422852,
      "learning_rate": 3.349257165724576e-05,
      "loss": 0.7469,
      "num_input_tokens_seen": 109799916,
      "step": 33000
    },
    {
      "epoch": 1.6757540893402032,
      "grad_norm": 10.678362846374512,
      "learning_rate": 3.324245910659797e-05,
      "loss": 0.7468,
      "num_input_tokens_seen": 111436748,
      "step": 33500
    },
    {
      "epoch": 1.7007653444049824,
      "grad_norm": 11.628217697143555,
      "learning_rate": 3.2992346555950175e-05,
      "loss": 0.7358,
      "num_input_tokens_seen": 113068476,
      "step": 34000
    },
    {
      "epoch": 1.7257765994697614,
      "grad_norm": 12.741203308105469,
      "learning_rate": 3.2742234005302385e-05,
      "loss": 0.7402,
      "num_input_tokens_seen": 114748860,
      "step": 34500
    },
    {
      "epoch": 1.7507878545345406,
      "grad_norm": 9.066828727722168,
      "learning_rate": 3.2492121454654595e-05,
      "loss": 0.7728,
      "num_input_tokens_seen": 116441684,
      "step": 35000
    },
    {
      "epoch": 1.7757991095993197,
      "grad_norm": 7.780086517333984,
      "learning_rate": 3.2242008904006805e-05,
      "loss": 0.7424,
      "num_input_tokens_seen": 118093652,
      "step": 35500
    },
    {
      "epoch": 1.8008103646640987,
      "grad_norm": 5.290003299713135,
      "learning_rate": 3.1991896353359015e-05,
      "loss": 0.7121,
      "num_input_tokens_seen": 119756772,
      "step": 36000
    },
    {
      "epoch": 1.825821619728878,
      "grad_norm": 13.356730461120605,
      "learning_rate": 3.1741783802711225e-05,
      "loss": 0.789,
      "num_input_tokens_seen": 121419852,
      "step": 36500
    },
    {
      "epoch": 1.850832874793657,
      "grad_norm": 4.2140727043151855,
      "learning_rate": 3.149167125206343e-05,
      "loss": 0.7501,
      "num_input_tokens_seen": 123080420,
      "step": 37000
    },
    {
      "epoch": 1.8758441298584363,
      "grad_norm": 15.408193588256836,
      "learning_rate": 3.124155870141564e-05,
      "loss": 0.7576,
      "num_input_tokens_seen": 124733724,
      "step": 37500
    },
    {
      "epoch": 1.9008553849232155,
      "grad_norm": 8.88025951385498,
      "learning_rate": 3.099144615076784e-05,
      "loss": 0.7315,
      "num_input_tokens_seen": 126386636,
      "step": 38000
    },
    {
      "epoch": 1.9258666399879947,
      "grad_norm": 15.850674629211426,
      "learning_rate": 3.074133360012005e-05,
      "loss": 0.7289,
      "num_input_tokens_seen": 128054932,
      "step": 38500
    },
    {
      "epoch": 1.9508778950527739,
      "grad_norm": 10.460667610168457,
      "learning_rate": 3.049122104947226e-05,
      "loss": 0.7375,
      "num_input_tokens_seen": 129731780,
      "step": 39000
    },
    {
      "epoch": 1.975889150117553,
      "grad_norm": 4.816532135009766,
      "learning_rate": 3.024110849882447e-05,
      "loss": 0.7203,
      "num_input_tokens_seen": 131377564,
      "step": 39500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.5678554773330688,
      "eval_runtime": 97.2769,
      "eval_samples_per_second": 411.002,
      "eval_steps_per_second": 51.379,
      "num_input_tokens_seen": 132976438,
      "step": 39982
    },
    {
      "epoch": 2.0009004051823323,
      "grad_norm": 8.531465530395508,
      "learning_rate": 2.999099594817668e-05,
      "loss": 0.7337,
      "num_input_tokens_seen": 133038726,
      "step": 40000
    },
    {
      "epoch": 2.025911660247111,
      "grad_norm": 17.74102783203125,
      "learning_rate": 2.974088339752889e-05,
      "loss": 0.6798,
      "num_input_tokens_seen": 134681590,
      "step": 40500
    },
    {
      "epoch": 2.05092291531189,
      "grad_norm": 16.203670501708984,
      "learning_rate": 2.9490770846881098e-05,
      "loss": 0.692,
      "num_input_tokens_seen": 136354910,
      "step": 41000
    },
    {
      "epoch": 2.0759341703766694,
      "grad_norm": 11.238871574401855,
      "learning_rate": 2.9240658296233308e-05,
      "loss": 0.653,
      "num_input_tokens_seen": 138014246,
      "step": 41500
    },
    {
      "epoch": 2.1009454254414486,
      "grad_norm": 8.781373023986816,
      "learning_rate": 2.899054574558551e-05,
      "loss": 0.6742,
      "num_input_tokens_seen": 139676526,
      "step": 42000
    },
    {
      "epoch": 2.1259566805062278,
      "grad_norm": 7.73007869720459,
      "learning_rate": 2.874043319493772e-05,
      "loss": 0.6739,
      "num_input_tokens_seen": 141326846,
      "step": 42500
    },
    {
      "epoch": 2.150967935571007,
      "grad_norm": 6.6758904457092285,
      "learning_rate": 2.849032064428993e-05,
      "loss": 0.6767,
      "num_input_tokens_seen": 142999126,
      "step": 43000
    },
    {
      "epoch": 2.175979190635786,
      "grad_norm": 9.964508056640625,
      "learning_rate": 2.824020809364214e-05,
      "loss": 0.6649,
      "num_input_tokens_seen": 144643454,
      "step": 43500
    },
    {
      "epoch": 2.2009904457005653,
      "grad_norm": 7.9148664474487305,
      "learning_rate": 2.7990095542994348e-05,
      "loss": 0.678,
      "num_input_tokens_seen": 146327686,
      "step": 44000
    },
    {
      "epoch": 2.2260017007653445,
      "grad_norm": 5.838576316833496,
      "learning_rate": 2.7739982992346558e-05,
      "loss": 0.6629,
      "num_input_tokens_seen": 147996750,
      "step": 44500
    },
    {
      "epoch": 2.2510129558301237,
      "grad_norm": 9.018148422241211,
      "learning_rate": 2.7489870441698768e-05,
      "loss": 0.6673,
      "num_input_tokens_seen": 149658382,
      "step": 45000
    },
    {
      "epoch": 2.276024210894903,
      "grad_norm": 5.56981897354126,
      "learning_rate": 2.7239757891050978e-05,
      "loss": 0.658,
      "num_input_tokens_seen": 151279470,
      "step": 45500
    },
    {
      "epoch": 2.3010354659596817,
      "grad_norm": 3.9373059272766113,
      "learning_rate": 2.698964534040318e-05,
      "loss": 0.6747,
      "num_input_tokens_seen": 152950878,
      "step": 46000
    },
    {
      "epoch": 2.326046721024461,
      "grad_norm": 7.596631050109863,
      "learning_rate": 2.6739532789755388e-05,
      "loss": 0.6824,
      "num_input_tokens_seen": 154603110,
      "step": 46500
    },
    {
      "epoch": 2.35105797608924,
      "grad_norm": 7.714618682861328,
      "learning_rate": 2.6489420239107598e-05,
      "loss": 0.6662,
      "num_input_tokens_seen": 156262254,
      "step": 47000
    },
    {
      "epoch": 2.3760692311540192,
      "grad_norm": 11.400321006774902,
      "learning_rate": 2.6239307688459808e-05,
      "loss": 0.6478,
      "num_input_tokens_seen": 157940526,
      "step": 47500
    },
    {
      "epoch": 2.4010804862187984,
      "grad_norm": 5.944780349731445,
      "learning_rate": 2.5989195137812018e-05,
      "loss": 0.6701,
      "num_input_tokens_seen": 159597926,
      "step": 48000
    },
    {
      "epoch": 2.4260917412835776,
      "grad_norm": 7.971735954284668,
      "learning_rate": 2.5739082587164225e-05,
      "loss": 0.6815,
      "num_input_tokens_seen": 161249054,
      "step": 48500
    },
    {
      "epoch": 2.451102996348357,
      "grad_norm": 8.019645690917969,
      "learning_rate": 2.5488970036516435e-05,
      "loss": 0.6823,
      "num_input_tokens_seen": 162937710,
      "step": 49000
    },
    {
      "epoch": 2.476114251413136,
      "grad_norm": 14.52238655090332,
      "learning_rate": 2.5238857485868645e-05,
      "loss": 0.6662,
      "num_input_tokens_seen": 164579550,
      "step": 49500
    },
    {
      "epoch": 2.501125506477915,
      "grad_norm": 8.065009117126465,
      "learning_rate": 2.498874493522085e-05,
      "loss": 0.6855,
      "num_input_tokens_seen": 166259486,
      "step": 50000
    },
    {
      "epoch": 2.526136761542694,
      "grad_norm": 3.0121171474456787,
      "learning_rate": 2.473863238457306e-05,
      "loss": 0.6597,
      "num_input_tokens_seen": 167925014,
      "step": 50500
    },
    {
      "epoch": 2.551148016607473,
      "grad_norm": 9.93840217590332,
      "learning_rate": 2.4488519833925268e-05,
      "loss": 0.6672,
      "num_input_tokens_seen": 169584230,
      "step": 51000
    },
    {
      "epoch": 2.5761592716722523,
      "grad_norm": 7.8001627922058105,
      "learning_rate": 2.4238407283277475e-05,
      "loss": 0.6419,
      "num_input_tokens_seen": 171205846,
      "step": 51500
    },
    {
      "epoch": 2.6011705267370315,
      "grad_norm": 5.621837139129639,
      "learning_rate": 2.3988294732629685e-05,
      "loss": 0.6679,
      "num_input_tokens_seen": 172867766,
      "step": 52000
    },
    {
      "epoch": 2.6261817818018107,
      "grad_norm": 18.287431716918945,
      "learning_rate": 2.3738182181981895e-05,
      "loss": 0.6601,
      "num_input_tokens_seen": 174508502,
      "step": 52500
    },
    {
      "epoch": 2.65119303686659,
      "grad_norm": 7.687650203704834,
      "learning_rate": 2.34880696313341e-05,
      "loss": 0.6722,
      "num_input_tokens_seen": 176179174,
      "step": 53000
    },
    {
      "epoch": 2.676204291931369,
      "grad_norm": 9.807682037353516,
      "learning_rate": 2.3237957080686308e-05,
      "loss": 0.666,
      "num_input_tokens_seen": 177874198,
      "step": 53500
    },
    {
      "epoch": 2.7012155469961483,
      "grad_norm": 9.2701416015625,
      "learning_rate": 2.2987844530038518e-05,
      "loss": 0.6811,
      "num_input_tokens_seen": 179531678,
      "step": 54000
    },
    {
      "epoch": 2.7262268020609275,
      "grad_norm": 8.37064266204834,
      "learning_rate": 2.2737731979390728e-05,
      "loss": 0.6505,
      "num_input_tokens_seen": 181197542,
      "step": 54500
    },
    {
      "epoch": 2.7512380571257067,
      "grad_norm": 5.556591033935547,
      "learning_rate": 2.2487619428742935e-05,
      "loss": 0.6711,
      "num_input_tokens_seen": 182849270,
      "step": 55000
    },
    {
      "epoch": 2.776249312190486,
      "grad_norm": 7.93866491317749,
      "learning_rate": 2.2237506878095145e-05,
      "loss": 0.6664,
      "num_input_tokens_seen": 184520526,
      "step": 55500
    },
    {
      "epoch": 2.801260567255265,
      "grad_norm": 6.768641471862793,
      "learning_rate": 2.198739432744735e-05,
      "loss": 0.6699,
      "num_input_tokens_seen": 186239974,
      "step": 56000
    },
    {
      "epoch": 2.8262718223200443,
      "grad_norm": 5.911066055297852,
      "learning_rate": 2.173728177679956e-05,
      "loss": 0.6649,
      "num_input_tokens_seen": 187875982,
      "step": 56500
    },
    {
      "epoch": 2.851283077384823,
      "grad_norm": 9.964897155761719,
      "learning_rate": 2.1487169226151768e-05,
      "loss": 0.6874,
      "num_input_tokens_seen": 189505118,
      "step": 57000
    },
    {
      "epoch": 2.876294332449602,
      "grad_norm": 8.109452247619629,
      "learning_rate": 2.1237056675503978e-05,
      "loss": 0.6762,
      "num_input_tokens_seen": 191184886,
      "step": 57500
    },
    {
      "epoch": 2.9013055875143814,
      "grad_norm": 8.556594848632812,
      "learning_rate": 2.0986944124856188e-05,
      "loss": 0.6491,
      "num_input_tokens_seen": 192859070,
      "step": 58000
    },
    {
      "epoch": 2.9263168425791606,
      "grad_norm": 5.430099010467529,
      "learning_rate": 2.0736831574208394e-05,
      "loss": 0.661,
      "num_input_tokens_seen": 194533102,
      "step": 58500
    },
    {
      "epoch": 2.9513280976439398,
      "grad_norm": 9.806259155273438,
      "learning_rate": 2.04867190235606e-05,
      "loss": 0.645,
      "num_input_tokens_seen": 196171870,
      "step": 59000
    },
    {
      "epoch": 2.976339352708719,
      "grad_norm": 8.950848579406738,
      "learning_rate": 2.023660647291281e-05,
      "loss": 0.6479,
      "num_input_tokens_seen": 197877830,
      "step": 59500
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.560497522354126,
      "eval_runtime": 98.7193,
      "eval_samples_per_second": 404.997,
      "eval_steps_per_second": 50.628,
      "num_input_tokens_seen": 199402582,
      "step": 59973
    },
    {
      "epoch": 3.001350607773498,
      "grad_norm": 6.855441093444824,
      "learning_rate": 1.998649392226502e-05,
      "loss": 0.6187,
      "num_input_tokens_seen": 199490934,
      "step": 60000
    },
    {
      "epoch": 3.0263618628382774,
      "grad_norm": 8.57907772064209,
      "learning_rate": 1.973638137161723e-05,
      "loss": 0.652,
      "num_input_tokens_seen": 201164870,
      "step": 60500
    },
    {
      "epoch": 3.0513731179030565,
      "grad_norm": 15.578742027282715,
      "learning_rate": 1.9486268820969438e-05,
      "loss": 0.6127,
      "num_input_tokens_seen": 202824222,
      "step": 61000
    },
    {
      "epoch": 3.0763843729678357,
      "grad_norm": 9.083669662475586,
      "learning_rate": 1.9236156270321644e-05,
      "loss": 0.6146,
      "num_input_tokens_seen": 204495334,
      "step": 61500
    },
    {
      "epoch": 3.1013956280326145,
      "grad_norm": 10.12027359008789,
      "learning_rate": 1.8986043719673854e-05,
      "loss": 0.6341,
      "num_input_tokens_seen": 206136214,
      "step": 62000
    },
    {
      "epoch": 3.1264068830973937,
      "grad_norm": 10.482580184936523,
      "learning_rate": 1.8735931169026064e-05,
      "loss": 0.603,
      "num_input_tokens_seen": 207809294,
      "step": 62500
    },
    {
      "epoch": 3.151418138162173,
      "grad_norm": 7.722796440124512,
      "learning_rate": 1.848581861837827e-05,
      "loss": 0.6184,
      "num_input_tokens_seen": 209485534,
      "step": 63000
    },
    {
      "epoch": 3.176429393226952,
      "grad_norm": 7.449066162109375,
      "learning_rate": 1.8235706067730478e-05,
      "loss": 0.621,
      "num_input_tokens_seen": 211143158,
      "step": 63500
    },
    {
      "epoch": 3.2014406482917313,
      "grad_norm": 8.766199111938477,
      "learning_rate": 1.7985593517082688e-05,
      "loss": 0.6165,
      "num_input_tokens_seen": 212777414,
      "step": 64000
    },
    {
      "epoch": 3.2264519033565104,
      "grad_norm": 4.193557262420654,
      "learning_rate": 1.7735480966434898e-05,
      "loss": 0.6188,
      "num_input_tokens_seen": 214420798,
      "step": 64500
    },
    {
      "epoch": 3.2514631584212896,
      "grad_norm": 6.699706554412842,
      "learning_rate": 1.7485368415787104e-05,
      "loss": 0.6095,
      "num_input_tokens_seen": 216073590,
      "step": 65000
    },
    {
      "epoch": 3.276474413486069,
      "grad_norm": 8.79476547241211,
      "learning_rate": 1.7235255865139314e-05,
      "loss": 0.6208,
      "num_input_tokens_seen": 217746214,
      "step": 65500
    },
    {
      "epoch": 3.301485668550848,
      "grad_norm": 6.685282230377197,
      "learning_rate": 1.698514331449152e-05,
      "loss": 0.6058,
      "num_input_tokens_seen": 219433446,
      "step": 66000
    },
    {
      "epoch": 3.326496923615627,
      "grad_norm": 10.743680953979492,
      "learning_rate": 1.673503076384373e-05,
      "loss": 0.6318,
      "num_input_tokens_seen": 221089694,
      "step": 66500
    },
    {
      "epoch": 3.3515081786804064,
      "grad_norm": 8.36410903930664,
      "learning_rate": 1.6484918213195938e-05,
      "loss": 0.6236,
      "num_input_tokens_seen": 222760502,
      "step": 67000
    },
    {
      "epoch": 3.376519433745185,
      "grad_norm": 7.1238274574279785,
      "learning_rate": 1.6234805662548148e-05,
      "loss": 0.6103,
      "num_input_tokens_seen": 224417582,
      "step": 67500
    },
    {
      "epoch": 3.4015306888099643,
      "grad_norm": 7.042121887207031,
      "learning_rate": 1.5984693111900358e-05,
      "loss": 0.6157,
      "num_input_tokens_seen": 226068982,
      "step": 68000
    },
    {
      "epoch": 3.4265419438747435,
      "grad_norm": 9.31881332397461,
      "learning_rate": 1.5734580561252564e-05,
      "loss": 0.6263,
      "num_input_tokens_seen": 227701038,
      "step": 68500
    },
    {
      "epoch": 3.4515531989395227,
      "grad_norm": 7.049442768096924,
      "learning_rate": 1.548446801060477e-05,
      "loss": 0.6237,
      "num_input_tokens_seen": 229359710,
      "step": 69000
    },
    {
      "epoch": 3.476564454004302,
      "grad_norm": 7.746445178985596,
      "learning_rate": 1.5234355459956981e-05,
      "loss": 0.6376,
      "num_input_tokens_seen": 231028950,
      "step": 69500
    },
    {
      "epoch": 3.501575709069081,
      "grad_norm": 4.588512420654297,
      "learning_rate": 1.4984242909309191e-05,
      "loss": 0.6189,
      "num_input_tokens_seen": 232663446,
      "step": 70000
    },
    {
      "epoch": 3.5265869641338603,
      "grad_norm": 9.873016357421875,
      "learning_rate": 1.47341303586614e-05,
      "loss": 0.5935,
      "num_input_tokens_seen": 234333558,
      "step": 70500
    },
    {
      "epoch": 3.5515982191986395,
      "grad_norm": 8.153191566467285,
      "learning_rate": 1.4484017808013606e-05,
      "loss": 0.6403,
      "num_input_tokens_seen": 236006758,
      "step": 71000
    },
    {
      "epoch": 3.5766094742634187,
      "grad_norm": 5.909561634063721,
      "learning_rate": 1.4233905257365814e-05,
      "loss": 0.6152,
      "num_input_tokens_seen": 237655630,
      "step": 71500
    },
    {
      "epoch": 3.6016207293281974,
      "grad_norm": 9.481532096862793,
      "learning_rate": 1.3983792706718024e-05,
      "loss": 0.5916,
      "num_input_tokens_seen": 239300238,
      "step": 72000
    },
    {
      "epoch": 3.6266319843929766,
      "grad_norm": 4.988440990447998,
      "learning_rate": 1.3733680156070232e-05,
      "loss": 0.6275,
      "num_input_tokens_seen": 240971214,
      "step": 72500
    },
    {
      "epoch": 3.651643239457756,
      "grad_norm": 6.159299850463867,
      "learning_rate": 1.3483567605422439e-05,
      "loss": 0.6101,
      "num_input_tokens_seen": 242634286,
      "step": 73000
    },
    {
      "epoch": 3.676654494522535,
      "grad_norm": 4.264859199523926,
      "learning_rate": 1.3233455054774649e-05,
      "loss": 0.6045,
      "num_input_tokens_seen": 244293870,
      "step": 73500
    },
    {
      "epoch": 3.701665749587314,
      "grad_norm": 5.82095193862915,
      "learning_rate": 1.2983342504126857e-05,
      "loss": 0.624,
      "num_input_tokens_seen": 245956374,
      "step": 74000
    },
    {
      "epoch": 3.7266770046520934,
      "grad_norm": 10.4242525100708,
      "learning_rate": 1.2733229953479067e-05,
      "loss": 0.6231,
      "num_input_tokens_seen": 247566166,
      "step": 74500
    },
    {
      "epoch": 3.7516882597168726,
      "grad_norm": 6.536423206329346,
      "learning_rate": 1.2483117402831276e-05,
      "loss": 0.6159,
      "num_input_tokens_seen": 249233118,
      "step": 75000
    },
    {
      "epoch": 3.776699514781652,
      "grad_norm": 10.467476844787598,
      "learning_rate": 1.2233004852183482e-05,
      "loss": 0.6252,
      "num_input_tokens_seen": 250919822,
      "step": 75500
    },
    {
      "epoch": 3.801710769846431,
      "grad_norm": 13.297423362731934,
      "learning_rate": 1.1982892301535692e-05,
      "loss": 0.6133,
      "num_input_tokens_seen": 252600838,
      "step": 76000
    },
    {
      "epoch": 3.82672202491121,
      "grad_norm": 6.729821681976318,
      "learning_rate": 1.1732779750887899e-05,
      "loss": 0.6201,
      "num_input_tokens_seen": 254292558,
      "step": 76500
    },
    {
      "epoch": 3.8517332799759894,
      "grad_norm": 5.975412845611572,
      "learning_rate": 1.1482667200240109e-05,
      "loss": 0.5976,
      "num_input_tokens_seen": 255961510,
      "step": 77000
    },
    {
      "epoch": 3.8767445350407685,
      "grad_norm": 16.30948257446289,
      "learning_rate": 1.1232554649592317e-05,
      "loss": 0.6023,
      "num_input_tokens_seen": 257630246,
      "step": 77500
    },
    {
      "epoch": 3.9017557901055477,
      "grad_norm": 7.327265739440918,
      "learning_rate": 1.0982442098944526e-05,
      "loss": 0.6145,
      "num_input_tokens_seen": 259305118,
      "step": 78000
    },
    {
      "epoch": 3.9267670451703265,
      "grad_norm": 12.45727825164795,
      "learning_rate": 1.0732329548296734e-05,
      "loss": 0.6311,
      "num_input_tokens_seen": 260978934,
      "step": 78500
    },
    {
      "epoch": 3.9517783002351057,
      "grad_norm": 10.317325592041016,
      "learning_rate": 1.0482216997648942e-05,
      "loss": 0.6346,
      "num_input_tokens_seen": 262670814,
      "step": 79000
    },
    {
      "epoch": 3.976789555299885,
      "grad_norm": 7.8411149978637695,
      "learning_rate": 1.023210444700115e-05,
      "loss": 0.6023,
      "num_input_tokens_seen": 264314614,
      "step": 79500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.54269939661026,
      "eval_runtime": 96.9182,
      "eval_samples_per_second": 412.523,
      "eval_steps_per_second": 51.569,
      "num_input_tokens_seen": 265875340,
      "step": 79964
    },
    {
      "epoch": 4.0018008103646645,
      "grad_norm": 6.620047569274902,
      "learning_rate": 9.98199189635336e-06,
      "loss": 0.6268,
      "num_input_tokens_seen": 266010940,
      "step": 80000
    },
    {
      "epoch": 4.026812065429443,
      "grad_norm": 10.007366180419922,
      "learning_rate": 9.731879345705567e-06,
      "loss": 0.5924,
      "num_input_tokens_seen": 267660364,
      "step": 80500
    },
    {
      "epoch": 4.051823320494222,
      "grad_norm": 6.680395603179932,
      "learning_rate": 9.481766795057777e-06,
      "loss": 0.5786,
      "num_input_tokens_seen": 269338492,
      "step": 81000
    },
    {
      "epoch": 4.076834575559001,
      "grad_norm": 4.809377670288086,
      "learning_rate": 9.231654244409984e-06,
      "loss": 0.5942,
      "num_input_tokens_seen": 271024236,
      "step": 81500
    },
    {
      "epoch": 4.10184583062378,
      "grad_norm": 8.463695526123047,
      "learning_rate": 8.981541693762194e-06,
      "loss": 0.5796,
      "num_input_tokens_seen": 272672620,
      "step": 82000
    },
    {
      "epoch": 4.12685708568856,
      "grad_norm": 10.12741470336914,
      "learning_rate": 8.731429143114402e-06,
      "loss": 0.5879,
      "num_input_tokens_seen": 274353676,
      "step": 82500
    },
    {
      "epoch": 4.151868340753339,
      "grad_norm": 15.428593635559082,
      "learning_rate": 8.48131659246661e-06,
      "loss": 0.5977,
      "num_input_tokens_seen": 275998164,
      "step": 83000
    },
    {
      "epoch": 4.176879595818118,
      "grad_norm": 10.350814819335938,
      "learning_rate": 8.231204041818819e-06,
      "loss": 0.566,
      "num_input_tokens_seen": 277685356,
      "step": 83500
    },
    {
      "epoch": 4.201890850882897,
      "grad_norm": 11.962939262390137,
      "learning_rate": 7.981091491171027e-06,
      "loss": 0.5671,
      "num_input_tokens_seen": 279358548,
      "step": 84000
    },
    {
      "epoch": 4.226902105947676,
      "grad_norm": 10.32712459564209,
      "learning_rate": 7.730978940523236e-06,
      "loss": 0.5785,
      "num_input_tokens_seen": 280991044,
      "step": 84500
    },
    {
      "epoch": 4.2519133610124555,
      "grad_norm": 5.896986484527588,
      "learning_rate": 7.480866389875445e-06,
      "loss": 0.6051,
      "num_input_tokens_seen": 282646764,
      "step": 85000
    },
    {
      "epoch": 4.276924616077235,
      "grad_norm": 7.187685966491699,
      "learning_rate": 7.230753839227652e-06,
      "loss": 0.5943,
      "num_input_tokens_seen": 284342508,
      "step": 85500
    },
    {
      "epoch": 4.301935871142014,
      "grad_norm": 6.680044174194336,
      "learning_rate": 6.980641288579861e-06,
      "loss": 0.5765,
      "num_input_tokens_seen": 286036340,
      "step": 86000
    },
    {
      "epoch": 4.326947126206793,
      "grad_norm": 4.963362693786621,
      "learning_rate": 6.73052873793207e-06,
      "loss": 0.6137,
      "num_input_tokens_seen": 287681564,
      "step": 86500
    },
    {
      "epoch": 4.351958381271572,
      "grad_norm": 12.112903594970703,
      "learning_rate": 6.480416187284279e-06,
      "loss": 0.5983,
      "num_input_tokens_seen": 289353828,
      "step": 87000
    },
    {
      "epoch": 4.3769696363363515,
      "grad_norm": 5.938944339752197,
      "learning_rate": 6.230303636636486e-06,
      "loss": 0.6017,
      "num_input_tokens_seen": 291011668,
      "step": 87500
    },
    {
      "epoch": 4.401980891401131,
      "grad_norm": 4.485511302947998,
      "learning_rate": 5.980191085988695e-06,
      "loss": 0.5898,
      "num_input_tokens_seen": 292675092,
      "step": 88000
    },
    {
      "epoch": 4.42699214646591,
      "grad_norm": 9.15986442565918,
      "learning_rate": 5.730078535340903e-06,
      "loss": 0.5744,
      "num_input_tokens_seen": 294338212,
      "step": 88500
    },
    {
      "epoch": 4.452003401530689,
      "grad_norm": 3.6591997146606445,
      "learning_rate": 5.479965984693112e-06,
      "loss": 0.5948,
      "num_input_tokens_seen": 296004820,
      "step": 89000
    },
    {
      "epoch": 4.477014656595468,
      "grad_norm": 9.19853401184082,
      "learning_rate": 5.2298534340453205e-06,
      "loss": 0.5838,
      "num_input_tokens_seen": 297661964,
      "step": 89500
    },
    {
      "epoch": 4.5020259116602475,
      "grad_norm": 13.491796493530273,
      "learning_rate": 4.979740883397529e-06,
      "loss": 0.5726,
      "num_input_tokens_seen": 299312356,
      "step": 90000
    },
    {
      "epoch": 4.527037166725027,
      "grad_norm": 6.374147415161133,
      "learning_rate": 4.729628332749737e-06,
      "loss": 0.5728,
      "num_input_tokens_seen": 300978468,
      "step": 90500
    },
    {
      "epoch": 4.552048421789806,
      "grad_norm": 7.507421970367432,
      "learning_rate": 4.479515782101945e-06,
      "loss": 0.5903,
      "num_input_tokens_seen": 302639252,
      "step": 91000
    },
    {
      "epoch": 4.577059676854585,
      "grad_norm": 12.31728744506836,
      "learning_rate": 4.229403231454155e-06,
      "loss": 0.5916,
      "num_input_tokens_seen": 304289124,
      "step": 91500
    },
    {
      "epoch": 4.602070931919363,
      "grad_norm": 11.238248825073242,
      "learning_rate": 3.979290680806363e-06,
      "loss": 0.5617,
      "num_input_tokens_seen": 305968436,
      "step": 92000
    },
    {
      "epoch": 4.6270821869841425,
      "grad_norm": 6.74647331237793,
      "learning_rate": 3.7291781301585712e-06,
      "loss": 0.6249,
      "num_input_tokens_seen": 307616156,
      "step": 92500
    },
    {
      "epoch": 4.652093442048922,
      "grad_norm": 7.845546722412109,
      "learning_rate": 3.4790655795107795e-06,
      "loss": 0.6015,
      "num_input_tokens_seen": 309294188,
      "step": 93000
    },
    {
      "epoch": 4.677104697113701,
      "grad_norm": 5.631568431854248,
      "learning_rate": 3.2289530288629883e-06,
      "loss": 0.5747,
      "num_input_tokens_seen": 310930388,
      "step": 93500
    },
    {
      "epoch": 4.70211595217848,
      "grad_norm": 4.305506229400635,
      "learning_rate": 2.978840478215197e-06,
      "loss": 0.5957,
      "num_input_tokens_seen": 312600876,
      "step": 94000
    },
    {
      "epoch": 4.727127207243259,
      "grad_norm": 12.092133522033691,
      "learning_rate": 2.7287279275674053e-06,
      "loss": 0.5952,
      "num_input_tokens_seen": 314275796,
      "step": 94500
    },
    {
      "epoch": 4.7521384623080385,
      "grad_norm": 7.043518543243408,
      "learning_rate": 2.478615376919614e-06,
      "loss": 0.6013,
      "num_input_tokens_seen": 315945468,
      "step": 95000
    },
    {
      "epoch": 4.777149717372818,
      "grad_norm": 6.208098888397217,
      "learning_rate": 2.2285028262718224e-06,
      "loss": 0.591,
      "num_input_tokens_seen": 317595388,
      "step": 95500
    },
    {
      "epoch": 4.802160972437597,
      "grad_norm": 3.588547706604004,
      "learning_rate": 1.978390275624031e-06,
      "loss": 0.5846,
      "num_input_tokens_seen": 319229212,
      "step": 96000
    },
    {
      "epoch": 4.827172227502376,
      "grad_norm": 10.502739906311035,
      "learning_rate": 1.7282777249762395e-06,
      "loss": 0.5904,
      "num_input_tokens_seen": 320908604,
      "step": 96500
    },
    {
      "epoch": 4.852183482567155,
      "grad_norm": 8.170723915100098,
      "learning_rate": 1.4781651743284478e-06,
      "loss": 0.5925,
      "num_input_tokens_seen": 322558268,
      "step": 97000
    },
    {
      "epoch": 4.8771947376319345,
      "grad_norm": 10.083109855651855,
      "learning_rate": 1.2280526236806563e-06,
      "loss": 0.5977,
      "num_input_tokens_seen": 324205708,
      "step": 97500
    },
    {
      "epoch": 4.902205992696714,
      "grad_norm": 6.591386795043945,
      "learning_rate": 9.779400730328649e-07,
      "loss": 0.5633,
      "num_input_tokens_seen": 325850036,
      "step": 98000
    },
    {
      "epoch": 4.927217247761493,
      "grad_norm": 7.133991241455078,
      "learning_rate": 7.278275223850733e-07,
      "loss": 0.5786,
      "num_input_tokens_seen": 327509276,
      "step": 98500
    },
    {
      "epoch": 4.952228502826272,
      "grad_norm": 5.090227127075195,
      "learning_rate": 4.777149717372818e-07,
      "loss": 0.5886,
      "num_input_tokens_seen": 329175052,
      "step": 99000
    },
    {
      "epoch": 4.977239757891051,
      "grad_norm": 7.157599925994873,
      "learning_rate": 2.276024210894903e-07,
      "loss": 0.5879,
      "num_input_tokens_seen": 330819060,
      "step": 99500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.5393198132514954,
      "eval_runtime": 97.8527,
      "eval_samples_per_second": 408.584,
      "eval_steps_per_second": 51.077,
      "num_input_tokens_seen": 332318598,
      "step": 99955
    },
    {
      "epoch": 5.0,
      "num_input_tokens_seen": 332318598,
      "step": 99955,
      "total_flos": 1.2062750373789696e+17,
      "train_loss": 0.7601320325591829,
      "train_runtime": 7988.2275,
      "train_samples_per_second": 100.099,
      "train_steps_per_second": 12.513,
      "train_tokens_per_second": 41593.134
    }
  ],
  "logging_steps": 500,
  "max_steps": 99955,
  "num_input_tokens_seen": 332318598,
  "num_train_epochs": 5,
  "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": 1.2062750373789696e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}