{
  "best_global_step": 2500,
  "best_metric": 0.0,
  "best_model_checkpoint": "/workspace/sosa-pii-ner-sg-v0.2.0/checkpoint-2500",
  "epoch": 61.34969325153374,
  "eval_steps": 500,
  "global_step": 10000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6134969325153374,
      "grad_norm": 122.79624938964844,
      "learning_rate": 4.950000000000001e-06,
      "loss": 11.8722998046875,
      "step": 100
    },
    {
      "epoch": 1.2269938650306749,
      "grad_norm": 826.52099609375,
      "learning_rate": 9.950000000000001e-06,
      "loss": 4.202756652832031,
      "step": 200
    },
    {
      "epoch": 1.8404907975460123,
      "grad_norm": 0.011014682240784168,
      "learning_rate": 1.4950000000000001e-05,
      "loss": 4.485827331542969,
      "step": 300
    },
    {
      "epoch": 2.4539877300613497,
      "grad_norm": 1620.895751953125,
      "learning_rate": 1.995e-05,
      "loss": 2.861741638183594,
      "step": 400
    },
    {
      "epoch": 3.067484662576687,
      "grad_norm": 0.0008813678286969662,
      "learning_rate": 2.495e-05,
      "loss": 2.1193824768066407,
      "step": 500
    },
    {
      "epoch": 3.067484662576687,
      "eval_loss": 0.7582037448883057,
      "eval_runtime": 1.2219,
      "eval_samples_per_second": 118.671,
      "eval_steps_per_second": 15.55,
      "step": 500
    },
    {
      "epoch": 3.6809815950920246,
      "grad_norm": 6.684136867523193,
      "learning_rate": 2.995e-05,
      "loss": 2.0062797546386717,
      "step": 600
    },
    {
      "epoch": 4.294478527607362,
      "grad_norm": 3.2882186928873125e-07,
      "learning_rate": 3.495e-05,
      "loss": 1.4084272766113282,
      "step": 700
    },
    {
      "epoch": 4.9079754601226995,
      "grad_norm": 0.003582573030143976,
      "learning_rate": 3.995e-05,
      "loss": 1.7337155151367187,
      "step": 800
    },
    {
      "epoch": 5.521472392638037,
      "grad_norm": 2.599556501081679e-05,
      "learning_rate": 4.495e-05,
      "loss": 0.3213422393798828,
      "step": 900
    },
    {
      "epoch": 6.134969325153374,
      "grad_norm": 5.8597619499778375e-05,
      "learning_rate": 4.995e-05,
      "loss": 1.8933323669433593,
      "step": 1000
    },
    {
      "epoch": 6.134969325153374,
      "eval_loss": 2.9267999934745603e-07,
      "eval_runtime": 1.1913,
      "eval_samples_per_second": 121.711,
      "eval_steps_per_second": 15.948,
      "step": 1000
    },
    {
      "epoch": 6.748466257668712,
      "grad_norm": 6.932016072269676e-10,
      "learning_rate": 4.998507370887433e-05,
      "loss": 3.3113247680664064,
      "step": 1100
    },
    {
      "epoch": 7.361963190184049,
      "grad_norm": 1.5232571968226694e-06,
      "learning_rate": 4.993970847717704e-05,
      "loss": 2.125959777832031,
      "step": 1200
    },
    {
      "epoch": 7.975460122699387,
      "grad_norm": 0.0008731394773349166,
      "learning_rate": 4.9863958052367894e-05,
      "loss": 2.95019775390625,
      "step": 1300
    },
    {
      "epoch": 8.588957055214724,
      "grad_norm": 1.8607582887852914e-06,
      "learning_rate": 4.9757914724671074e-05,
      "loss": 1.707820281982422,
      "step": 1400
    },
    {
      "epoch": 9.202453987730062,
      "grad_norm": 521.7967529296875,
      "learning_rate": 4.9621707691546645e-05,
      "loss": 1.2510208129882812,
      "step": 1500
    },
    {
      "epoch": 9.202453987730062,
      "eval_loss": 1.524503231048584,
      "eval_runtime": 1.2043,
      "eval_samples_per_second": 120.401,
      "eval_steps_per_second": 15.777,
      "step": 1500
    },
    {
      "epoch": 9.815950920245399,
      "grad_norm": 2.230161305397083e-15,
      "learning_rate": 4.94555029002834e-05,
      "loss": 0.8807488250732421,
      "step": 1600
    },
    {
      "epoch": 10.429447852760736,
      "grad_norm": 1.159133233841203e-07,
      "learning_rate": 4.9259502845817594e-05,
      "loss": 2.1483859252929687,
      "step": 1700
    },
    {
      "epoch": 11.042944785276074,
      "grad_norm": 7.983133739567633e-14,
      "learning_rate": 4.90339463240241e-05,
      "loss": 1.1693775939941407,
      "step": 1800
    },
    {
      "epoch": 11.656441717791411,
      "grad_norm": 5.839314030244057e-19,
      "learning_rate": 4.877910814078041e-05,
      "loss": 1.9894096374511718,
      "step": 1900
    },
    {
      "epoch": 12.269938650306749,
      "grad_norm": 0.0075200870633125305,
      "learning_rate": 4.849529877715799e-05,
      "loss": 2.0999024963378905,
      "step": 2000
    },
    {
      "epoch": 12.269938650306749,
      "eval_loss": 2.2362063134551136e-07,
      "eval_runtime": 1.22,
      "eval_samples_per_second": 118.849,
      "eval_steps_per_second": 15.573,
      "step": 2000
    },
    {
      "epoch": 12.883435582822086,
      "grad_norm": 7.003300283442426e-12,
      "learning_rate": 4.818286401114894e-05,
      "loss": 0.2763525009155273,
      "step": 2100
    },
    {
      "epoch": 13.496932515337424,
      "grad_norm": 2.8572054496288975e-16,
      "learning_rate": 4.784218449638875e-05,
      "loss": 1.0676566314697267,
      "step": 2200
    },
    {
      "epoch": 14.110429447852761,
      "grad_norm": 4.104634113068911e-13,
      "learning_rate": 4.7473675298388495e-05,
      "loss": 1.6261299133300782,
      "step": 2300
    },
    {
      "epoch": 14.723926380368098,
      "grad_norm": 9.618054616633565e-12,
      "learning_rate": 4.707778538884145e-05,
      "loss": 4.111170043945313,
      "step": 2400
    },
    {
      "epoch": 15.337423312883436,
      "grad_norm": 2.7887643104208068e-21,
      "learning_rate": 4.6654997098620234e-05,
      "loss": 0.9707022857666016,
      "step": 2500
    },
    {
      "epoch": 15.337423312883436,
      "eval_loss": 0.0,
      "eval_runtime": 1.2135,
      "eval_samples_per_second": 119.487,
      "eval_steps_per_second": 15.657,
      "step": 2500
    },
    {
      "epoch": 15.950920245398773,
      "grad_norm": 3.5642793834724858e-19,
      "learning_rate": 4.6205825530130944e-05,
      "loss": 1.7202511596679688,
      "step": 2600
    },
    {
      "epoch": 16.56441717791411,
      "grad_norm": 2.1279852879807493e-11,
      "learning_rate": 4.57308179297402e-05,
      "loss": 0.4121376419067383,
      "step": 2700
    },
    {
      "epoch": 17.177914110429448,
      "grad_norm": 1.2521302323875716e-06,
      "learning_rate": 4.523055302103977e-05,
      "loss": 1.2150499725341797,
      "step": 2800
    },
    {
      "epoch": 17.791411042944784,
      "grad_norm": 2.4915639329492478e-08,
      "learning_rate": 4.4705640299761007e-05,
      "loss": 1.4591110229492188,
      "step": 2900
    },
    {
      "epoch": 18.404907975460123,
      "grad_norm": 4.819107894855901e-13,
      "learning_rate": 4.4156719291198166e-05,
      "loss": 0.8009672546386719,
      "step": 3000
    },
    {
      "epoch": 18.404907975460123,
      "eval_loss": 0.0,
      "eval_runtime": 1.1691,
      "eval_samples_per_second": 124.031,
      "eval_steps_per_second": 16.252,
      "step": 3000
    },
    {
      "epoch": 19.01840490797546,
      "grad_norm": 1.261542019580789e-16,
      "learning_rate": 4.3584458771045406e-05,
      "loss": 1.43816650390625,
      "step": 3100
    },
    {
      "epoch": 19.631901840490798,
      "grad_norm": 3467.762939453125,
      "learning_rate": 4.298955595059654e-05,
      "loss": 2.2927120971679686,
      "step": 3200
    },
    {
      "epoch": 20.245398773006134,
      "grad_norm": 1.2736173400693559e-20,
      "learning_rate": 4.237273562730054e-05,
      "loss": 0.5510644149780274,
      "step": 3300
    },
    {
      "epoch": 20.858895705521473,
      "grad_norm": 1.1253607073991034e-10,
      "learning_rate": 4.173474930170744e-05,
      "loss": 0.22771228790283204,
      "step": 3400
    },
    {
      "epoch": 21.47239263803681,
      "grad_norm": 9.94370239482123e-08,
      "learning_rate": 4.1076374261880735e-05,
      "loss": 0.2858289909362793,
      "step": 3500
    },
    {
      "epoch": 21.47239263803681,
      "eval_loss": 7.82068309490569e-06,
      "eval_runtime": 1.1652,
      "eval_samples_per_second": 124.441,
      "eval_steps_per_second": 16.306,
      "step": 3500
    },
    {
      "epoch": 22.085889570552148,
      "grad_norm": 4.48467963214506e-19,
      "learning_rate": 4.039841263639155e-05,
      "loss": 0.2277687644958496,
      "step": 3600
    },
    {
      "epoch": 22.699386503067483,
      "grad_norm": 0.0,
      "learning_rate": 3.970169041704855e-05,
      "loss": 0.2763387298583984,
      "step": 3700
    },
    {
      "epoch": 23.312883435582823,
      "grad_norm": 2.8488761913761373e-13,
      "learning_rate": 3.898705645255418e-05,
      "loss": 0.6940188598632813,
      "step": 3800
    },
    {
      "epoch": 23.926380368098158,
      "grad_norm": 2.6114647700273143e-19,
      "learning_rate": 3.8255381414313245e-05,
      "loss": 0.33693092346191406,
      "step": 3900
    },
    {
      "epoch": 24.539877300613497,
      "grad_norm": 2.0227130517400105e-13,
      "learning_rate": 3.750755673565396e-05,
      "loss": 0.6311358642578125,
      "step": 4000
    },
    {
      "epoch": 24.539877300613497,
      "eval_loss": 0.0,
      "eval_runtime": 1.1791,
      "eval_samples_per_second": 122.98,
      "eval_steps_per_second": 16.115,
      "step": 4000
    },
    {
      "epoch": 25.153374233128833,
      "grad_norm": 0.0,
      "learning_rate": 3.67444935257537e-05,
      "loss": 1.4305121567304013e-08,
      "step": 4100
    },
    {
      "epoch": 25.766871165644172,
      "grad_norm": 0.0,
      "learning_rate": 3.596712145959285e-05,
      "loss": 0.39916488647460935,
      "step": 4200
    },
    {
      "epoch": 26.380368098159508,
      "grad_norm": 1.677425138166402e-16,
      "learning_rate": 3.5176387645289034e-05,
      "loss": 1.7148970800917596e-06,
      "step": 4300
    },
    {
      "epoch": 26.993865030674847,
      "grad_norm": 4.223529970204254e-08,
      "learning_rate": 3.437325547019179e-05,
      "loss": 0.0009235091507434845,
      "step": 4400
    },
    {
      "epoch": 27.607361963190183,
      "grad_norm": 0.0,
      "learning_rate": 3.355870342714344e-05,
      "loss": 0.3235731887817383,
      "step": 4500
    },
    {
      "epoch": 27.607361963190183,
      "eval_loss": 0.0,
      "eval_runtime": 1.2786,
      "eval_samples_per_second": 113.404,
      "eval_steps_per_second": 14.86,
      "step": 4500
    },
    {
      "epoch": 28.220858895705522,
      "grad_norm": 6.967167728161305e-13,
      "learning_rate": 3.27337239223363e-05,
      "loss": 0.5219675827026368,
      "step": 4600
    },
    {
      "epoch": 28.834355828220858,
      "grad_norm": 2.996475469152238e-19,
      "learning_rate": 3.189932206621865e-05,
      "loss": 1.4364779663085938,
      "step": 4700
    },
    {
      "epoch": 29.447852760736197,
      "grad_norm": 8.039356462002055e-16,
      "learning_rate": 3.10565144489224e-05,
      "loss": 0.5538373565673829,
      "step": 4800
    },
    {
      "epoch": 30.061349693251532,
      "grad_norm": 0.0,
      "learning_rate": 3.020632790170467e-05,
      "loss": 0.710223388671875,
      "step": 4900
    },
    {
      "epoch": 30.67484662576687,
      "grad_norm": 0.0005261774640530348,
      "learning_rate": 2.934979824591205e-05,
      "loss": 0.07732938766479493,
      "step": 5000
    },
    {
      "epoch": 30.67484662576687,
      "eval_loss": 0.0,
      "eval_runtime": 1.2859,
      "eval_samples_per_second": 112.763,
      "eval_steps_per_second": 14.776,
      "step": 5000
    },
    {
      "epoch": 31.288343558282207,
      "grad_norm": 1.3684467784196713e-13,
      "learning_rate": 2.8487969030991845e-05,
      "loss": 0.9899538421630859,
      "step": 5100
    },
    {
      "epoch": 31.901840490797547,
      "grad_norm": 5.159969204718038e-17,
      "learning_rate": 2.7621890263087813e-05,
      "loss": 0.3169578552246094,
      "step": 5200
    },
    {
      "epoch": 32.515337423312886,
      "grad_norm": 4.4620050384559795e-13,
      "learning_rate": 2.6752617125769443e-05,
      "loss": 0.2662870597839355,
      "step": 5300
    },
    {
      "epoch": 33.12883435582822,
      "grad_norm": 0.0,
      "learning_rate": 2.58812086944533e-05,
      "loss": 0.17050649642944335,
      "step": 5400
    },
    {
      "epoch": 33.74233128834356,
      "grad_norm": 0.0,
      "learning_rate": 2.5008726646082754e-05,
      "loss": 1.7459046936035156,
      "step": 5500
    },
    {
      "epoch": 33.74233128834356,
      "eval_loss": 5.335756301879883,
      "eval_runtime": 1.1988,
      "eval_samples_per_second": 120.95,
      "eval_steps_per_second": 15.849,
      "step": 5500
    },
    {
      "epoch": 34.355828220858896,
      "grad_norm": 5.29302938111809e-21,
      "learning_rate": 2.4136233965638195e-05,
      "loss": 1.847508087158203,
      "step": 5600
    },
    {
      "epoch": 34.969325153374236,
      "grad_norm": 1.2452759512406584e-19,
      "learning_rate": 2.326479365105355e-05,
      "loss": 1.1052408599853516,
      "step": 5700
    },
    {
      "epoch": 35.58282208588957,
      "grad_norm": 0.0,
      "learning_rate": 2.239546741811704e-05,
      "loss": 0.27631362915039065,
      "step": 5800
    },
    {
      "epoch": 36.19631901840491,
      "grad_norm": 0.0,
      "learning_rate": 2.1529314406934078e-05,
      "loss": 0.5526204299926758,
      "step": 5900
    },
    {
      "epoch": 36.809815950920246,
      "grad_norm": 0.0,
      "learning_rate": 2.066738989152813e-05,
      "loss": 0.27631025314331054,
      "step": 6000
    },
    {
      "epoch": 36.809815950920246,
      "eval_loss": 0.0,
      "eval_runtime": 1.3119,
      "eval_samples_per_second": 110.528,
      "eval_steps_per_second": 14.483,
      "step": 6000
    },
    {
      "epoch": 37.423312883435585,
      "grad_norm": 7.06288941510227e-20,
      "learning_rate": 1.9810743994151926e-05,
      "loss": 0.5526204299926758,
      "step": 6100
    },
    {
      "epoch": 38.03680981595092,
      "grad_norm": 0.0,
      "learning_rate": 1.8960420405875244e-05,
      "loss": 3.576279254957626e-09,
      "step": 6200
    },
    {
      "epoch": 38.65030674846626,
      "grad_norm": 0.0,
      "learning_rate": 1.8117455115008085e-05,
      "loss": 0.13815510749816895,
      "step": 6300
    },
    {
      "epoch": 39.263803680981596,
      "grad_norm": 0.0,
      "learning_rate": 1.728287514490851e-05,
      "loss": 0.5305731964111328,
      "step": 6400
    },
    {
      "epoch": 39.877300613496935,
      "grad_norm": 0.0,
      "learning_rate": 1.6457697302712918e-05,
      "loss": 0.5526210021972656,
      "step": 6500
    },
    {
      "epoch": 39.877300613496935,
      "eval_loss": 0.0,
      "eval_runtime": 1.3426,
      "eval_samples_per_second": 107.997,
      "eval_steps_per_second": 14.151,
      "step": 6500
    },
    {
      "epoch": 40.49079754601227,
      "grad_norm": 0.0,
      "learning_rate": 1.5642926940513113e-05,
      "loss": 0.0,
      "step": 6600
    },
    {
      "epoch": 41.104294478527606,
      "grad_norm": 0.0,
      "learning_rate": 1.4839556730489673e-05,
      "loss": 0.2902725791931152,
      "step": 6700
    },
    {
      "epoch": 41.717791411042946,
      "grad_norm": 0.0,
      "learning_rate": 1.404856545549384e-05,
      "loss": 0.3396176910400391,
      "step": 6800
    },
    {
      "epoch": 42.331288343558285,
      "grad_norm": 0.0,
      "learning_rate": 1.3270916816551298e-05,
      "loss": 0.21853748321533203,
      "step": 6900
    },
    {
      "epoch": 42.94478527607362,
      "grad_norm": 0.0,
      "learning_rate": 1.2507558258741047e-05,
      "loss": 0.0058324956893920895,
      "step": 7000
    },
    {
      "epoch": 42.94478527607362,
      "eval_loss": 0.0,
      "eval_runtime": 1.3584,
      "eval_samples_per_second": 106.741,
      "eval_steps_per_second": 13.987,
      "step": 7000
    },
    {
      "epoch": 43.558282208588956,
      "grad_norm": 0.0,
      "learning_rate": 1.1759419816879374e-05,
      "loss": 0.5526205062866211,
      "step": 7100
    },
    {
      "epoch": 44.171779141104295,
      "grad_norm": 1.5112887576364335e-18,
      "learning_rate": 1.1027412982415814e-05,
      "loss": 0.5676006317138672,
      "step": 7200
    },
    {
      "epoch": 44.785276073619634,
      "grad_norm": 0.0,
      "learning_rate": 1.0312429592921141e-05,
      "loss": 0.09628434181213379,
      "step": 7300
    },
    {
      "epoch": 45.39877300613497,
      "grad_norm": 6.760388327718285e-18,
      "learning_rate": 9.615340745520713e-06,
      "loss": 0.31535978317260743,
      "step": 7400
    },
    {
      "epoch": 46.012269938650306,
      "grad_norm": 0.0,
      "learning_rate": 8.936995735596782e-06,
      "loss": 0.01817405104637146,
      "step": 7500
    },
    {
      "epoch": 46.012269938650306,
      "eval_loss": 0.0,
      "eval_runtime": 1.3665,
      "eval_samples_per_second": 106.11,
      "eval_steps_per_second": 13.904,
      "step": 7500
    },
    {
      "epoch": 46.625766871165645,
      "grad_norm": 1.2129035917335421e-19,
      "learning_rate": 8.278221022052898e-06,
      "loss": 0.0,
      "step": 7600
    },
    {
      "epoch": 47.239263803680984,
      "grad_norm": 0.0,
      "learning_rate": 7.639819220401059e-06,
      "loss": 3.337863745400682e-08,
      "step": 7700
    },
    {
      "epoch": 47.852760736196316,
      "grad_norm": 0.0,
      "learning_rate": 7.022568124898293e-06,
      "loss": 0.27631628036499023,
      "step": 7800
    },
    {
      "epoch": 48.466257668711656,
      "grad_norm": 0.0,
      "learning_rate": 6.4272197609242635e-06,
      "loss": 0.2763102149963379,
      "step": 7900
    },
    {
      "epoch": 49.079754601226995,
      "grad_norm": 0.0,
      "learning_rate": 5.854499468754062e-06,
      "loss": 0.0,
      "step": 8000
    },
    {
      "epoch": 49.079754601226995,
      "eval_loss": 0.0,
      "eval_runtime": 1.3614,
      "eval_samples_per_second": 106.508,
      "eval_steps_per_second": 13.956,
      "step": 8000
    },
    {
      "epoch": 49.693251533742334,
      "grad_norm": 4.3718546781346644e-16,
      "learning_rate": 5.305105019842907e-06,
      "loss": 0.0,
      "step": 8100
    },
    {
      "epoch": 50.306748466257666,
      "grad_norm": 0.0,
      "learning_rate": 4.779705766699069e-06,
      "loss": 0.0,
      "step": 8200
    },
    {
      "epoch": 50.920245398773005,
      "grad_norm": 0.0,
      "learning_rate": 4.278941827380953e-06,
      "loss": 0.0,
      "step": 8300
    },
    {
      "epoch": 51.533742331288344,
      "grad_norm": 3.7337580774301615e-15,
      "learning_rate": 3.8034233056118475e-06,
      "loss": 0.0,
      "step": 8400
    },
    {
      "epoch": 52.147239263803684,
      "grad_norm": 1.975971800123751e-15,
      "learning_rate": 3.3537295474625222e-06,
      "loss": 0.0,
      "step": 8500
    },
    {
      "epoch": 52.147239263803684,
      "eval_loss": 0.0,
      "eval_runtime": 1.1682,
      "eval_samples_per_second": 124.12,
      "eval_steps_per_second": 16.264,
      "step": 8500
    },
    {
      "epoch": 52.760736196319016,
      "grad_norm": 0.0,
      "learning_rate": 2.930408435507248e-06,
      "loss": 6.270605081226676e-07,
      "step": 8600
    },
    {
      "epoch": 53.374233128834355,
      "grad_norm": 0.0,
      "learning_rate": 2.5339757213133502e-06,
      "loss": 0.0,
      "step": 8700
    },
    {
      "epoch": 53.987730061349694,
      "grad_norm": 0.0,
      "learning_rate": 2.164914397077275e-06,
      "loss": 0.2763102149963379,
      "step": 8800
    },
    {
      "epoch": 54.60122699386503,
      "grad_norm": 0.0,
      "learning_rate": 1.8236741071730761e-06,
      "loss": 0.13815511703491212,
      "step": 8900
    },
    {
      "epoch": 55.214723926380366,
      "grad_norm": 0.0,
      "learning_rate": 1.510670600329961e-06,
      "loss": 0.0,
      "step": 9000
    },
    {
      "epoch": 55.214723926380366,
      "eval_loss": 0.0,
      "eval_runtime": 1.1602,
      "eval_samples_per_second": 124.982,
      "eval_steps_per_second": 16.377,
      "step": 9000
    },
    {
      "epoch": 55.828220858895705,
      "grad_norm": 0.0,
      "learning_rate": 1.2262852231065242e-06,
      "loss": 0.0,
      "step": 9100
    },
    {
      "epoch": 56.441717791411044,
      "grad_norm": 0.0,
      "learning_rate": 9.708644552787027e-07,
      "loss": 0.2763102149963379,
      "step": 9200
    },
    {
      "epoch": 57.05521472392638,
      "grad_norm": 0.0,
      "learning_rate": 7.44719487707543e-07,
      "loss": 0.0,
      "step": 9300
    },
    {
      "epoch": 57.668711656441715,
      "grad_norm": 0.0,
      "learning_rate": 5.481258432010695e-07,
      "loss": 0.0,
      "step": 9400
    },
    {
      "epoch": 58.282208588957054,
      "grad_norm": 0.0,
      "learning_rate": 3.813230408321794e-07,
      "loss": 0.0,
      "step": 9500
    },
    {
      "epoch": 58.282208588957054,
      "eval_loss": 0.0,
      "eval_runtime": 1.2389,
      "eval_samples_per_second": 117.042,
      "eval_steps_per_second": 15.337,
      "step": 9500
    },
    {
      "epoch": 58.895705521472394,
      "grad_norm": 0.0,
      "learning_rate": 2.445143041215653e-07,
      "loss": 0.00040464144200086594,
      "step": 9600
    },
    {
      "epoch": 59.50920245398773,
      "grad_norm": 0.0,
      "learning_rate": 1.3786631344113176e-07,
      "loss": 0.13815510749816895,
      "step": 9700
    },
    {
      "epoch": 60.122699386503065,
      "grad_norm": 0.0,
      "learning_rate": 6.150900293966089e-08,
      "loss": 0.0,
      "step": 9800
    },
    {
      "epoch": 60.736196319018404,
      "grad_norm": 0.0,
      "learning_rate": 1.5535402238056607e-08,
      "loss": 0.0,
      "step": 9900
    },
    {
      "epoch": 61.34969325153374,
      "grad_norm": 0.0,
      "learning_rate": 1.5230870842319888e-12,
      "loss": 0.2918341445922852,
      "step": 10000
    },
    {
      "epoch": 61.34969325153374,
      "eval_loss": 0.0,
      "eval_runtime": 1.1467,
      "eval_samples_per_second": 126.451,
      "eval_steps_per_second": 16.569,
      "step": 10000
    }
  ],
  "logging_steps": 100,
  "max_steps": 10000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 62,
  "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": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}