{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9987902250181466,
  "eval_steps": 100,
  "global_step": 516,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.009678199854827003,
      "grad_norm": 135.23733520507812,
      "learning_rate": 1.9230769230769234e-06,
      "loss": 12.7676,
      "step": 5
    },
    {
      "epoch": 0.019356399709654006,
      "grad_norm": 142.41867065429688,
      "learning_rate": 3.846153846153847e-06,
      "loss": 12.1736,
      "step": 10
    },
    {
      "epoch": 0.029034599564481005,
      "grad_norm": 142.9897003173828,
      "learning_rate": 5.769230769230769e-06,
      "loss": 11.9754,
      "step": 15
    },
    {
      "epoch": 0.03871279941930801,
      "grad_norm": 122.53395080566406,
      "learning_rate": 7.692307692307694e-06,
      "loss": 7.9422,
      "step": 20
    },
    {
      "epoch": 0.04839099927413501,
      "grad_norm": 131.50697326660156,
      "learning_rate": 9.615384615384616e-06,
      "loss": 6.1603,
      "step": 25
    },
    {
      "epoch": 0.05806919912896201,
      "grad_norm": 273.497314453125,
      "learning_rate": 9.918367346938776e-06,
      "loss": 1.798,
      "step": 30
    },
    {
      "epoch": 0.06774739898378901,
      "grad_norm": 17.278669357299805,
      "learning_rate": 9.816326530612245e-06,
      "loss": 1.0221,
      "step": 35
    },
    {
      "epoch": 0.07742559883861602,
      "grad_norm": 17.088966369628906,
      "learning_rate": 9.714285714285715e-06,
      "loss": 0.4251,
      "step": 40
    },
    {
      "epoch": 0.08710379869344302,
      "grad_norm": 58.794822692871094,
      "learning_rate": 9.612244897959185e-06,
      "loss": 0.9236,
      "step": 45
    },
    {
      "epoch": 0.09678199854827002,
      "grad_norm": 40.58847427368164,
      "learning_rate": 9.510204081632653e-06,
      "loss": 0.4787,
      "step": 50
    },
    {
      "epoch": 0.10646019840309702,
      "grad_norm": 41.08816146850586,
      "learning_rate": 9.408163265306123e-06,
      "loss": 0.6779,
      "step": 55
    },
    {
      "epoch": 0.11613839825792402,
      "grad_norm": 9.461664199829102,
      "learning_rate": 9.306122448979593e-06,
      "loss": 0.5731,
      "step": 60
    },
    {
      "epoch": 0.12581659811275103,
      "grad_norm": 15.421150207519531,
      "learning_rate": 9.204081632653062e-06,
      "loss": 0.8264,
      "step": 65
    },
    {
      "epoch": 0.13549479796757802,
      "grad_norm": 36.99074935913086,
      "learning_rate": 9.102040816326532e-06,
      "loss": 0.8976,
      "step": 70
    },
    {
      "epoch": 0.14517299782240503,
      "grad_norm": 12.443870544433594,
      "learning_rate": 9e-06,
      "loss": 0.758,
      "step": 75
    },
    {
      "epoch": 0.15485119767723204,
      "grad_norm": 34.37516784667969,
      "learning_rate": 8.89795918367347e-06,
      "loss": 0.4913,
      "step": 80
    },
    {
      "epoch": 0.16452939753205903,
      "grad_norm": 47.92347717285156,
      "learning_rate": 8.79591836734694e-06,
      "loss": 0.6342,
      "step": 85
    },
    {
      "epoch": 0.17420759738688604,
      "grad_norm": 19.53640365600586,
      "learning_rate": 8.69387755102041e-06,
      "loss": 0.7332,
      "step": 90
    },
    {
      "epoch": 0.18388579724171303,
      "grad_norm": 15.180093765258789,
      "learning_rate": 8.591836734693878e-06,
      "loss": 0.8574,
      "step": 95
    },
    {
      "epoch": 0.19356399709654004,
      "grad_norm": 7.7558770179748535,
      "learning_rate": 8.489795918367347e-06,
      "loss": 0.7241,
      "step": 100
    },
    {
      "epoch": 0.19356399709654004,
      "eval_loss": 0.636104166507721,
      "eval_mse": 0.6361041891163793,
      "eval_runtime": 12.3473,
      "eval_samples_per_second": 35.23,
      "eval_steps_per_second": 17.656,
      "step": 100
    },
    {
      "epoch": 0.20324219695136705,
      "grad_norm": 6.328822612762451,
      "learning_rate": 8.387755102040817e-06,
      "loss": 0.613,
      "step": 105
    },
    {
      "epoch": 0.21292039680619404,
      "grad_norm": 3.98986554145813,
      "learning_rate": 8.285714285714287e-06,
      "loss": 0.6963,
      "step": 110
    },
    {
      "epoch": 0.22259859666102105,
      "grad_norm": 6.252445697784424,
      "learning_rate": 8.183673469387757e-06,
      "loss": 0.4936,
      "step": 115
    },
    {
      "epoch": 0.23227679651584804,
      "grad_norm": 11.744823455810547,
      "learning_rate": 8.081632653061225e-06,
      "loss": 0.6189,
      "step": 120
    },
    {
      "epoch": 0.24195499637067505,
      "grad_norm": 3.548699378967285,
      "learning_rate": 7.979591836734695e-06,
      "loss": 0.6508,
      "step": 125
    },
    {
      "epoch": 0.25163319622550206,
      "grad_norm": 32.78942108154297,
      "learning_rate": 7.877551020408164e-06,
      "loss": 0.7334,
      "step": 130
    },
    {
      "epoch": 0.26131139608032905,
      "grad_norm": 39.87502670288086,
      "learning_rate": 7.775510204081632e-06,
      "loss": 0.8856,
      "step": 135
    },
    {
      "epoch": 0.27098959593515604,
      "grad_norm": 25.449832916259766,
      "learning_rate": 7.673469387755102e-06,
      "loss": 0.6497,
      "step": 140
    },
    {
      "epoch": 0.2806677957899831,
      "grad_norm": 9.905705451965332,
      "learning_rate": 7.571428571428572e-06,
      "loss": 0.6297,
      "step": 145
    },
    {
      "epoch": 0.29034599564481006,
      "grad_norm": 10.688154220581055,
      "learning_rate": 7.469387755102041e-06,
      "loss": 0.5351,
      "step": 150
    },
    {
      "epoch": 0.30002419549963705,
      "grad_norm": 20.666561126708984,
      "learning_rate": 7.367346938775511e-06,
      "loss": 0.5918,
      "step": 155
    },
    {
      "epoch": 0.3097023953544641,
      "grad_norm": 44.254947662353516,
      "learning_rate": 7.2653061224489805e-06,
      "loss": 0.8516,
      "step": 160
    },
    {
      "epoch": 0.3193805952092911,
      "grad_norm": 18.602283477783203,
      "learning_rate": 7.16326530612245e-06,
      "loss": 0.4989,
      "step": 165
    },
    {
      "epoch": 0.32905879506411806,
      "grad_norm": 2.891568660736084,
      "learning_rate": 7.061224489795919e-06,
      "loss": 0.4556,
      "step": 170
    },
    {
      "epoch": 0.3387369949189451,
      "grad_norm": 14.327004432678223,
      "learning_rate": 6.959183673469388e-06,
      "loss": 0.6965,
      "step": 175
    },
    {
      "epoch": 0.3484151947737721,
      "grad_norm": 3.936084032058716,
      "learning_rate": 6.857142857142858e-06,
      "loss": 0.6425,
      "step": 180
    },
    {
      "epoch": 0.35809339462859907,
      "grad_norm": 6.193188667297363,
      "learning_rate": 6.755102040816327e-06,
      "loss": 0.5081,
      "step": 185
    },
    {
      "epoch": 0.36777159448342606,
      "grad_norm": 21.818361282348633,
      "learning_rate": 6.653061224489797e-06,
      "loss": 0.6029,
      "step": 190
    },
    {
      "epoch": 0.3774497943382531,
      "grad_norm": 20.763904571533203,
      "learning_rate": 6.5510204081632656e-06,
      "loss": 0.4717,
      "step": 195
    },
    {
      "epoch": 0.3871279941930801,
      "grad_norm": 15.887273788452148,
      "learning_rate": 6.4489795918367345e-06,
      "loss": 0.575,
      "step": 200
    },
    {
      "epoch": 0.3871279941930801,
      "eval_loss": 0.6364156603813171,
      "eval_mse": 0.6364156788793104,
      "eval_runtime": 12.8511,
      "eval_samples_per_second": 33.849,
      "eval_steps_per_second": 16.964,
      "step": 200
    },
    {
      "epoch": 0.39680619404790707,
      "grad_norm": 6.549495220184326,
      "learning_rate": 6.346938775510204e-06,
      "loss": 0.6062,
      "step": 205
    },
    {
      "epoch": 0.4064843939027341,
      "grad_norm": 2.362842082977295,
      "learning_rate": 6.244897959183675e-06,
      "loss": 0.5902,
      "step": 210
    },
    {
      "epoch": 0.4161625937575611,
      "grad_norm": 6.210005760192871,
      "learning_rate": 6.142857142857144e-06,
      "loss": 0.6235,
      "step": 215
    },
    {
      "epoch": 0.4258407936123881,
      "grad_norm": 0.35702061653137207,
      "learning_rate": 6.040816326530613e-06,
      "loss": 0.6959,
      "step": 220
    },
    {
      "epoch": 0.4355189934672151,
      "grad_norm": 7.42579460144043,
      "learning_rate": 5.9387755102040825e-06,
      "loss": 0.8113,
      "step": 225
    },
    {
      "epoch": 0.4451971933220421,
      "grad_norm": 15.467649459838867,
      "learning_rate": 5.8367346938775515e-06,
      "loss": 0.753,
      "step": 230
    },
    {
      "epoch": 0.4548753931768691,
      "grad_norm": 5.005227565765381,
      "learning_rate": 5.73469387755102e-06,
      "loss": 0.423,
      "step": 235
    },
    {
      "epoch": 0.4645535930316961,
      "grad_norm": 9.86463737487793,
      "learning_rate": 5.63265306122449e-06,
      "loss": 0.5652,
      "step": 240
    },
    {
      "epoch": 0.4742317928865231,
      "grad_norm": 0.07020189613103867,
      "learning_rate": 5.530612244897959e-06,
      "loss": 0.508,
      "step": 245
    },
    {
      "epoch": 0.4839099927413501,
      "grad_norm": 1.7268608808517456,
      "learning_rate": 5.428571428571429e-06,
      "loss": 0.7836,
      "step": 250
    },
    {
      "epoch": 0.4935881925961771,
      "grad_norm": 15.658587455749512,
      "learning_rate": 5.326530612244898e-06,
      "loss": 0.6653,
      "step": 255
    },
    {
      "epoch": 0.5032663924510041,
      "grad_norm": 3.4803199768066406,
      "learning_rate": 5.2244897959183684e-06,
      "loss": 0.7674,
      "step": 260
    },
    {
      "epoch": 0.5129445923058311,
      "grad_norm": 5.9674506187438965,
      "learning_rate": 5.122448979591837e-06,
      "loss": 0.5348,
      "step": 265
    },
    {
      "epoch": 0.5226227921606581,
      "grad_norm": 8.432785034179688,
      "learning_rate": 5.020408163265307e-06,
      "loss": 0.678,
      "step": 270
    },
    {
      "epoch": 0.5323009920154851,
      "grad_norm": 13.345314025878906,
      "learning_rate": 4.918367346938776e-06,
      "loss": 0.5572,
      "step": 275
    },
    {
      "epoch": 0.5419791918703121,
      "grad_norm": 12.001265525817871,
      "learning_rate": 4.816326530612245e-06,
      "loss": 0.5397,
      "step": 280
    },
    {
      "epoch": 0.5516573917251392,
      "grad_norm": 1.87912118434906,
      "learning_rate": 4.714285714285715e-06,
      "loss": 0.4944,
      "step": 285
    },
    {
      "epoch": 0.5613355915799662,
      "grad_norm": 3.5236661434173584,
      "learning_rate": 4.612244897959184e-06,
      "loss": 0.5333,
      "step": 290
    },
    {
      "epoch": 0.5710137914347931,
      "grad_norm": 12.931561470031738,
      "learning_rate": 4.5102040816326535e-06,
      "loss": 0.5476,
      "step": 295
    },
    {
      "epoch": 0.5806919912896201,
      "grad_norm": 6.103638172149658,
      "learning_rate": 4.408163265306123e-06,
      "loss": 0.6298,
      "step": 300
    },
    {
      "epoch": 0.5806919912896201,
      "eval_loss": 0.6253479719161987,
      "eval_mse": 0.625347970545977,
      "eval_runtime": 12.7924,
      "eval_samples_per_second": 34.005,
      "eval_steps_per_second": 17.041,
      "step": 300
    },
    {
      "epoch": 0.5903701911444471,
      "grad_norm": 7.156700611114502,
      "learning_rate": 4.306122448979592e-06,
      "loss": 0.8688,
      "step": 305
    },
    {
      "epoch": 0.6000483909992741,
      "grad_norm": 1.5767498016357422,
      "learning_rate": 4.204081632653061e-06,
      "loss": 0.6039,
      "step": 310
    },
    {
      "epoch": 0.6097265908541012,
      "grad_norm": 10.190150260925293,
      "learning_rate": 4.102040816326531e-06,
      "loss": 0.5012,
      "step": 315
    },
    {
      "epoch": 0.6194047907089282,
      "grad_norm": 7.6610026359558105,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.6778,
      "step": 320
    },
    {
      "epoch": 0.6290829905637552,
      "grad_norm": 9.915760040283203,
      "learning_rate": 3.89795918367347e-06,
      "loss": 0.4987,
      "step": 325
    },
    {
      "epoch": 0.6387611904185821,
      "grad_norm": 11.606775283813477,
      "learning_rate": 3.795918367346939e-06,
      "loss": 0.4232,
      "step": 330
    },
    {
      "epoch": 0.6484393902734091,
      "grad_norm": 0.6899937987327576,
      "learning_rate": 3.6938775510204083e-06,
      "loss": 0.3689,
      "step": 335
    },
    {
      "epoch": 0.6581175901282361,
      "grad_norm": 2.4227399826049805,
      "learning_rate": 3.5918367346938777e-06,
      "loss": 0.7523,
      "step": 340
    },
    {
      "epoch": 0.6677957899830631,
      "grad_norm": 6.039433479309082,
      "learning_rate": 3.4897959183673474e-06,
      "loss": 0.8179,
      "step": 345
    },
    {
      "epoch": 0.6774739898378902,
      "grad_norm": 1.8034197092056274,
      "learning_rate": 3.3877551020408168e-06,
      "loss": 0.7031,
      "step": 350
    },
    {
      "epoch": 0.6871521896927172,
      "grad_norm": 9.077332496643066,
      "learning_rate": 3.285714285714286e-06,
      "loss": 0.6106,
      "step": 355
    },
    {
      "epoch": 0.6968303895475442,
      "grad_norm": 1.226553201675415,
      "learning_rate": 3.183673469387755e-06,
      "loss": 0.68,
      "step": 360
    },
    {
      "epoch": 0.7065085894023712,
      "grad_norm": 2.4295260906219482,
      "learning_rate": 3.0816326530612244e-06,
      "loss": 0.5769,
      "step": 365
    },
    {
      "epoch": 0.7161867892571981,
      "grad_norm": 17.398645401000977,
      "learning_rate": 2.979591836734694e-06,
      "loss": 0.7025,
      "step": 370
    },
    {
      "epoch": 0.7258649891120251,
      "grad_norm": 1.2020399570465088,
      "learning_rate": 2.8775510204081636e-06,
      "loss": 0.7725,
      "step": 375
    },
    {
      "epoch": 0.7355431889668521,
      "grad_norm": 16.19696807861328,
      "learning_rate": 2.775510204081633e-06,
      "loss": 0.5855,
      "step": 380
    },
    {
      "epoch": 0.7452213888216792,
      "grad_norm": 5.417294979095459,
      "learning_rate": 2.6734693877551023e-06,
      "loss": 0.5507,
      "step": 385
    },
    {
      "epoch": 0.7548995886765062,
      "grad_norm": 3.608414649963379,
      "learning_rate": 2.571428571428571e-06,
      "loss": 0.6533,
      "step": 390
    },
    {
      "epoch": 0.7645777885313332,
      "grad_norm": 7.825292110443115,
      "learning_rate": 2.469387755102041e-06,
      "loss": 0.6263,
      "step": 395
    },
    {
      "epoch": 0.7742559883861602,
      "grad_norm": 3.606358289718628,
      "learning_rate": 2.3673469387755103e-06,
      "loss": 0.4298,
      "step": 400
    },
    {
      "epoch": 0.7742559883861602,
      "eval_loss": 0.611698567867279,
      "eval_mse": 0.6116985452586207,
      "eval_runtime": 12.4253,
      "eval_samples_per_second": 35.009,
      "eval_steps_per_second": 17.545,
      "step": 400
    },
    {
      "epoch": 0.7839341882409872,
      "grad_norm": 0.6020415425300598,
      "learning_rate": 2.2653061224489797e-06,
      "loss": 0.5142,
      "step": 405
    },
    {
      "epoch": 0.7936123880958141,
      "grad_norm": 1.7960638999938965,
      "learning_rate": 2.1632653061224495e-06,
      "loss": 0.531,
      "step": 410
    },
    {
      "epoch": 0.8032905879506412,
      "grad_norm": 6.039422988891602,
      "learning_rate": 2.0612244897959184e-06,
      "loss": 0.6542,
      "step": 415
    },
    {
      "epoch": 0.8129687878054682,
      "grad_norm": 4.238173007965088,
      "learning_rate": 1.9591836734693877e-06,
      "loss": 0.6658,
      "step": 420
    },
    {
      "epoch": 0.8226469876602952,
      "grad_norm": 12.702580451965332,
      "learning_rate": 1.8571428571428573e-06,
      "loss": 0.5881,
      "step": 425
    },
    {
      "epoch": 0.8323251875151222,
      "grad_norm": 2.6721410751342773,
      "learning_rate": 1.7551020408163267e-06,
      "loss": 0.4565,
      "step": 430
    },
    {
      "epoch": 0.8420033873699492,
      "grad_norm": 10.180371284484863,
      "learning_rate": 1.6530612244897962e-06,
      "loss": 0.7646,
      "step": 435
    },
    {
      "epoch": 0.8516815872247762,
      "grad_norm": 14.619568824768066,
      "learning_rate": 1.5510204081632654e-06,
      "loss": 0.5797,
      "step": 440
    },
    {
      "epoch": 0.8613597870796031,
      "grad_norm": 3.0513336658477783,
      "learning_rate": 1.4489795918367347e-06,
      "loss": 0.6342,
      "step": 445
    },
    {
      "epoch": 0.8710379869344302,
      "grad_norm": 2.8715620040893555,
      "learning_rate": 1.3469387755102043e-06,
      "loss": 0.4666,
      "step": 450
    },
    {
      "epoch": 0.8807161867892572,
      "grad_norm": 12.445976257324219,
      "learning_rate": 1.2448979591836734e-06,
      "loss": 0.6886,
      "step": 455
    },
    {
      "epoch": 0.8903943866440842,
      "grad_norm": 9.058150291442871,
      "learning_rate": 1.142857142857143e-06,
      "loss": 0.4226,
      "step": 460
    },
    {
      "epoch": 0.9000725864989112,
      "grad_norm": 3.5630202293395996,
      "learning_rate": 1.0408163265306123e-06,
      "loss": 0.5195,
      "step": 465
    },
    {
      "epoch": 0.9097507863537382,
      "grad_norm": 14.264552116394043,
      "learning_rate": 9.387755102040817e-07,
      "loss": 0.8617,
      "step": 470
    },
    {
      "epoch": 0.9194289862085652,
      "grad_norm": 7.2072062492370605,
      "learning_rate": 8.367346938775512e-07,
      "loss": 0.5227,
      "step": 475
    },
    {
      "epoch": 0.9291071860633922,
      "grad_norm": 7.209239482879639,
      "learning_rate": 7.346938775510205e-07,
      "loss": 0.7242,
      "step": 480
    },
    {
      "epoch": 0.9387853859182193,
      "grad_norm": 7.206480026245117,
      "learning_rate": 6.326530612244898e-07,
      "loss": 0.4023,
      "step": 485
    },
    {
      "epoch": 0.9484635857730462,
      "grad_norm": 14.362146377563477,
      "learning_rate": 5.306122448979592e-07,
      "loss": 0.6686,
      "step": 490
    },
    {
      "epoch": 0.9581417856278732,
      "grad_norm": 2.965012550354004,
      "learning_rate": 4.285714285714286e-07,
      "loss": 0.4549,
      "step": 495
    },
    {
      "epoch": 0.9678199854827002,
      "grad_norm": 4.2699127197265625,
      "learning_rate": 3.2653061224489803e-07,
      "loss": 0.5672,
      "step": 500
    },
    {
      "epoch": 0.9678199854827002,
      "eval_loss": 0.621571958065033,
      "eval_mse": 0.6215719288793103,
      "eval_runtime": 12.4978,
      "eval_samples_per_second": 34.806,
      "eval_steps_per_second": 17.443,
      "step": 500
    },
    {
      "epoch": 0.9774981853375272,
      "grad_norm": 23.406326293945312,
      "learning_rate": 2.2448979591836735e-07,
      "loss": 0.7287,
      "step": 505
    },
    {
      "epoch": 0.9871763851923542,
      "grad_norm": 8.980780601501465,
      "learning_rate": 1.2244897959183673e-07,
      "loss": 0.5979,
      "step": 510
    },
    {
      "epoch": 0.9968545850471813,
      "grad_norm": 1.8055081367492676,
      "learning_rate": 2.0408163265306127e-08,
      "loss": 0.5709,
      "step": 515
    },
    {
      "epoch": 0.9987902250181466,
      "step": 516,
      "total_flos": 8688901375918080.0,
      "train_loss": 1.1010994948157968,
      "train_runtime": 478.9806,
      "train_samples_per_second": 17.255,
      "train_steps_per_second": 1.077
    }
  ],
  "logging_steps": 5,
  "max_steps": 516,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8688901375918080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}