{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 453,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.033112582781456956,
      "grad_norm": 2.2606041431427,
      "learning_rate": 4.998497170031657e-05,
      "loss": 0.6997,
      "num_input_tokens_seen": 4912,
      "step": 5
    },
    {
      "epoch": 0.06622516556291391,
      "grad_norm": 2.3543715476989746,
      "learning_rate": 4.9939904869249616e-05,
      "loss": 0.3509,
      "num_input_tokens_seen": 9936,
      "step": 10
    },
    {
      "epoch": 0.09933774834437085,
      "grad_norm": 1.801797866821289,
      "learning_rate": 4.9864853689026556e-05,
      "loss": 0.2853,
      "num_input_tokens_seen": 14864,
      "step": 15
    },
    {
      "epoch": 0.13245033112582782,
      "grad_norm": 1.3575855493545532,
      "learning_rate": 4.975990839097764e-05,
      "loss": 0.2456,
      "num_input_tokens_seen": 19824,
      "step": 20
    },
    {
      "epoch": 0.16556291390728478,
      "grad_norm": 2.5929694175720215,
      "learning_rate": 4.9625195147054034e-05,
      "loss": 0.2084,
      "num_input_tokens_seen": 24480,
      "step": 25
    },
    {
      "epoch": 0.1986754966887417,
      "grad_norm": 0.8744802474975586,
      "learning_rate": 4.9460875918135804e-05,
      "loss": 0.1626,
      "num_input_tokens_seen": 29296,
      "step": 30
    },
    {
      "epoch": 0.23178807947019867,
      "grad_norm": 2.857471466064453,
      "learning_rate": 4.9267148259312224e-05,
      "loss": 0.1405,
      "num_input_tokens_seen": 33936,
      "step": 35
    },
    {
      "epoch": 0.26490066225165565,
      "grad_norm": 1.7763206958770752,
      "learning_rate": 4.9044245082368415e-05,
      "loss": 0.1182,
      "num_input_tokens_seen": 39056,
      "step": 40
    },
    {
      "epoch": 0.2980132450331126,
      "grad_norm": 2.78945255279541,
      "learning_rate": 4.879243437576383e-05,
      "loss": 0.1285,
      "num_input_tokens_seen": 43520,
      "step": 45
    },
    {
      "epoch": 0.33112582781456956,
      "grad_norm": 1.1319329738616943,
      "learning_rate": 4.8512018882439475e-05,
      "loss": 0.0906,
      "num_input_tokens_seen": 48656,
      "step": 50
    },
    {
      "epoch": 0.36423841059602646,
      "grad_norm": 0.8884170055389404,
      "learning_rate": 4.820333573584091e-05,
      "loss": 0.054,
      "num_input_tokens_seen": 53600,
      "step": 55
    },
    {
      "epoch": 0.3973509933774834,
      "grad_norm": 2.0057179927825928,
      "learning_rate": 4.786675605459487e-05,
      "loss": 0.073,
      "num_input_tokens_seen": 58384,
      "step": 60
    },
    {
      "epoch": 0.4304635761589404,
      "grad_norm": 1.3076105117797852,
      "learning_rate": 4.7502684496326746e-05,
      "loss": 0.0524,
      "num_input_tokens_seen": 63152,
      "step": 65
    },
    {
      "epoch": 0.46357615894039733,
      "grad_norm": 1.074171543121338,
      "learning_rate": 4.711155877115523e-05,
      "loss": 0.0534,
      "num_input_tokens_seen": 67888,
      "step": 70
    },
    {
      "epoch": 0.4966887417218543,
      "grad_norm": 1.634122371673584,
      "learning_rate": 4.669384911544927e-05,
      "loss": 0.0759,
      "num_input_tokens_seen": 72480,
      "step": 75
    },
    {
      "epoch": 0.5298013245033113,
      "grad_norm": 1.0059384107589722,
      "learning_rate": 4.625005772647979e-05,
      "loss": 0.0766,
      "num_input_tokens_seen": 77120,
      "step": 80
    },
    {
      "epoch": 0.5629139072847682,
      "grad_norm": 1.3958277702331543,
      "learning_rate": 4.578071815864602e-05,
      "loss": 0.0383,
      "num_input_tokens_seen": 81584,
      "step": 85
    },
    {
      "epoch": 0.5960264900662252,
      "grad_norm": 2.721231698989868,
      "learning_rate": 4.528639468200226e-05,
      "loss": 0.0393,
      "num_input_tokens_seen": 86416,
      "step": 90
    },
    {
      "epoch": 0.6291390728476821,
      "grad_norm": 1.4776098728179932,
      "learning_rate": 4.476768160385632e-05,
      "loss": 0.0589,
      "num_input_tokens_seen": 91248,
      "step": 95
    },
    {
      "epoch": 0.6622516556291391,
      "grad_norm": 1.1105955839157104,
      "learning_rate": 4.4225202554255227e-05,
      "loss": 0.0351,
      "num_input_tokens_seen": 95936,
      "step": 100
    },
    {
      "epoch": 0.695364238410596,
      "grad_norm": 1.1301405429840088,
      "learning_rate": 4.3659609736217344e-05,
      "loss": 0.0417,
      "num_input_tokens_seen": 100704,
      "step": 105
    },
    {
      "epoch": 0.7284768211920529,
      "grad_norm": 1.869552493095398,
      "learning_rate": 4.3071583141612135e-05,
      "loss": 0.0437,
      "num_input_tokens_seen": 105376,
      "step": 110
    },
    {
      "epoch": 0.7615894039735099,
      "grad_norm": 1.0497004985809326,
      "learning_rate": 4.2461829733630435e-05,
      "loss": 0.0498,
      "num_input_tokens_seen": 110208,
      "step": 115
    },
    {
      "epoch": 0.7947019867549668,
      "grad_norm": 0.4084171652793884,
      "learning_rate": 4.1831082596828106e-05,
      "loss": 0.0239,
      "num_input_tokens_seen": 114704,
      "step": 120
    },
    {
      "epoch": 0.8278145695364238,
      "grad_norm": 0.4082948565483093,
      "learning_rate": 4.118010005576485e-05,
      "loss": 0.0228,
      "num_input_tokens_seen": 119744,
      "step": 125
    },
    {
      "epoch": 0.8609271523178808,
      "grad_norm": 0.246117502450943,
      "learning_rate": 4.050966476329793e-05,
      "loss": 0.039,
      "num_input_tokens_seen": 124736,
      "step": 130
    },
    {
      "epoch": 0.8940397350993378,
      "grad_norm": 0.5470453500747681,
      "learning_rate": 3.9820582759626825e-05,
      "loss": 0.05,
      "num_input_tokens_seen": 129552,
      "step": 135
    },
    {
      "epoch": 0.9271523178807947,
      "grad_norm": 0.6097426414489746,
      "learning_rate": 3.911368250322014e-05,
      "loss": 0.02,
      "num_input_tokens_seen": 134400,
      "step": 140
    },
    {
      "epoch": 0.9602649006622517,
      "grad_norm": 0.4274413585662842,
      "learning_rate": 3.8389813874789856e-05,
      "loss": 0.0159,
      "num_input_tokens_seen": 139424,
      "step": 145
    },
    {
      "epoch": 0.9933774834437086,
      "grad_norm": 0.1949557512998581,
      "learning_rate": 3.764984715551032e-05,
      "loss": 0.017,
      "num_input_tokens_seen": 144368,
      "step": 150
    },
    {
      "epoch": 1.0264900662251655,
      "grad_norm": 0.9226788878440857,
      "learning_rate": 3.6894671980710574e-05,
      "loss": 0.0298,
      "num_input_tokens_seen": 149040,
      "step": 155
    },
    {
      "epoch": 1.0596026490066226,
      "grad_norm": 1.5730527639389038,
      "learning_rate": 3.612519627029787e-05,
      "loss": 0.0357,
      "num_input_tokens_seen": 153712,
      "step": 160
    },
    {
      "epoch": 1.0927152317880795,
      "grad_norm": 0.5750863552093506,
      "learning_rate": 3.534234513719821e-05,
      "loss": 0.0185,
      "num_input_tokens_seen": 158640,
      "step": 165
    },
    {
      "epoch": 1.1258278145695364,
      "grad_norm": 0.4966561198234558,
      "learning_rate": 3.4547059775126445e-05,
      "loss": 0.0339,
      "num_input_tokens_seen": 163552,
      "step": 170
    },
    {
      "epoch": 1.1589403973509933,
      "grad_norm": 0.6601276993751526,
      "learning_rate": 3.3740296327022984e-05,
      "loss": 0.0224,
      "num_input_tokens_seen": 168352,
      "step": 175
    },
    {
      "epoch": 1.1920529801324504,
      "grad_norm": 1.2051963806152344,
      "learning_rate": 3.292302473551757e-05,
      "loss": 0.0192,
      "num_input_tokens_seen": 173312,
      "step": 180
    },
    {
      "epoch": 1.2251655629139073,
      "grad_norm": 0.48197436332702637,
      "learning_rate": 3.20962275768022e-05,
      "loss": 0.0275,
      "num_input_tokens_seen": 178160,
      "step": 185
    },
    {
      "epoch": 1.2582781456953642,
      "grad_norm": 0.3365241289138794,
      "learning_rate": 3.126089887931515e-05,
      "loss": 0.0086,
      "num_input_tokens_seen": 182944,
      "step": 190
    },
    {
      "epoch": 1.2913907284768211,
      "grad_norm": 0.5984787940979004,
      "learning_rate": 3.0418042928656414e-05,
      "loss": 0.0166,
      "num_input_tokens_seen": 187920,
      "step": 195
    },
    {
      "epoch": 1.3245033112582782,
      "grad_norm": 0.3351554274559021,
      "learning_rate": 2.9568673060171326e-05,
      "loss": 0.0167,
      "num_input_tokens_seen": 192992,
      "step": 200
    },
    {
      "epoch": 1.3576158940397351,
      "grad_norm": 0.21267688274383545,
      "learning_rate": 2.8713810440653926e-05,
      "loss": 0.0137,
      "num_input_tokens_seen": 197616,
      "step": 205
    },
    {
      "epoch": 1.390728476821192,
      "grad_norm": 0.17382262647151947,
      "learning_rate": 2.7854482840634965e-05,
      "loss": 0.0142,
      "num_input_tokens_seen": 202400,
      "step": 210
    },
    {
      "epoch": 1.423841059602649,
      "grad_norm": 0.552691638469696,
      "learning_rate": 2.6991723398730383e-05,
      "loss": 0.0136,
      "num_input_tokens_seen": 207216,
      "step": 215
    },
    {
      "epoch": 1.4569536423841059,
      "grad_norm": 0.4015306532382965,
      "learning_rate": 2.6126569379535985e-05,
      "loss": 0.0184,
      "num_input_tokens_seen": 211744,
      "step": 220
    },
    {
      "epoch": 1.490066225165563,
      "grad_norm": 0.20611760020256042,
      "learning_rate": 2.526006092656161e-05,
      "loss": 0.0098,
      "num_input_tokens_seen": 216608,
      "step": 225
    },
    {
      "epoch": 1.5231788079470199,
      "grad_norm": 0.3923095762729645,
      "learning_rate": 2.4393239811704e-05,
      "loss": 0.012,
      "num_input_tokens_seen": 221552,
      "step": 230
    },
    {
      "epoch": 1.5562913907284768,
      "grad_norm": 0.2283228635787964,
      "learning_rate": 2.3527148182762054e-05,
      "loss": 0.0106,
      "num_input_tokens_seen": 226272,
      "step": 235
    },
    {
      "epoch": 1.589403973509934,
      "grad_norm": 1.2066081762313843,
      "learning_rate": 2.2662827310499995e-05,
      "loss": 0.0128,
      "num_input_tokens_seen": 231072,
      "step": 240
    },
    {
      "epoch": 1.6225165562913908,
      "grad_norm": 0.39357009530067444,
      "learning_rate": 2.1801316336765126e-05,
      "loss": 0.0139,
      "num_input_tokens_seen": 235728,
      "step": 245
    },
    {
      "epoch": 1.6556291390728477,
      "grad_norm": 0.2383226603269577,
      "learning_rate": 2.0943651025164932e-05,
      "loss": 0.0084,
      "num_input_tokens_seen": 240560,
      "step": 250
    },
    {
      "epoch": 1.6887417218543046,
      "grad_norm": 1.2794650793075562,
      "learning_rate": 2.0090862515805898e-05,
      "loss": 0.0143,
      "num_input_tokens_seen": 245408,
      "step": 255
    },
    {
      "epoch": 1.7218543046357615,
      "grad_norm": 0.5334519147872925,
      "learning_rate": 1.9243976085590824e-05,
      "loss": 0.011,
      "num_input_tokens_seen": 250400,
      "step": 260
    },
    {
      "epoch": 1.7549668874172184,
      "grad_norm": 0.32287150621414185,
      "learning_rate": 1.840400991556541e-05,
      "loss": 0.0127,
      "num_input_tokens_seen": 255216,
      "step": 265
    },
    {
      "epoch": 1.7880794701986755,
      "grad_norm": 0.7233603596687317,
      "learning_rate": 1.7571973866795815e-05,
      "loss": 0.0127,
      "num_input_tokens_seen": 260080,
      "step": 270
    },
    {
      "epoch": 1.8211920529801324,
      "grad_norm": 0.2672172784805298,
      "learning_rate": 1.6748868266249114e-05,
      "loss": 0.0122,
      "num_input_tokens_seen": 264848,
      "step": 275
    },
    {
      "epoch": 1.8543046357615895,
      "grad_norm": 0.32350099086761475,
      "learning_rate": 1.5935682704136183e-05,
      "loss": 0.0169,
      "num_input_tokens_seen": 269776,
      "step": 280
    },
    {
      "epoch": 1.8874172185430464,
      "grad_norm": 0.26331964135169983,
      "learning_rate": 1.5133394844163093e-05,
      "loss": 0.0242,
      "num_input_tokens_seen": 274752,
      "step": 285
    },
    {
      "epoch": 1.9205298013245033,
      "grad_norm": 0.25610876083374023,
      "learning_rate": 1.4342969248121185e-05,
      "loss": 0.0079,
      "num_input_tokens_seen": 279440,
      "step": 290
    },
    {
      "epoch": 1.9536423841059603,
      "grad_norm": 1.2221907377243042,
      "learning_rate": 1.3565356216229268e-05,
      "loss": 0.0194,
      "num_input_tokens_seen": 284288,
      "step": 295
    },
    {
      "epoch": 1.9867549668874172,
      "grad_norm": 0.46571576595306396,
      "learning_rate": 1.2801490644621789e-05,
      "loss": 0.0133,
      "num_input_tokens_seen": 289216,
      "step": 300
    },
    {
      "epoch": 2.019867549668874,
      "grad_norm": 0.06845066696405411,
      "learning_rate": 1.2052290901357025e-05,
      "loss": 0.0049,
      "num_input_tokens_seen": 293992,
      "step": 305
    },
    {
      "epoch": 2.052980132450331,
      "grad_norm": 0.3654076159000397,
      "learning_rate": 1.1318657722296097e-05,
      "loss": 0.0121,
      "num_input_tokens_seen": 299048,
      "step": 310
    },
    {
      "epoch": 2.0860927152317883,
      "grad_norm": 0.1736595779657364,
      "learning_rate": 1.0601473128180855e-05,
      "loss": 0.0102,
      "num_input_tokens_seen": 303768,
      "step": 315
    },
    {
      "epoch": 2.119205298013245,
      "grad_norm": 0.15334352850914001,
      "learning_rate": 9.90159936421197e-06,
      "loss": 0.0072,
      "num_input_tokens_seen": 308872,
      "step": 320
    },
    {
      "epoch": 2.152317880794702,
      "grad_norm": 0.15292225778102875,
      "learning_rate": 9.219877863402682e-06,
      "loss": 0.0066,
      "num_input_tokens_seen": 313800,
      "step": 325
    },
    {
      "epoch": 2.185430463576159,
      "grad_norm": 0.12052378058433533,
      "learning_rate": 8.55712823495419e-06,
      "loss": 0.0119,
      "num_input_tokens_seen": 318536,
      "step": 330
    },
    {
      "epoch": 2.218543046357616,
      "grad_norm": 0.16140712797641754,
      "learning_rate": 7.91414727886898e-06,
      "loss": 0.0057,
      "num_input_tokens_seen": 323512,
      "step": 335
    },
    {
      "epoch": 2.251655629139073,
      "grad_norm": 0.49767032265663147,
      "learning_rate": 7.291708027986988e-06,
      "loss": 0.0136,
      "num_input_tokens_seen": 328552,
      "step": 340
    },
    {
      "epoch": 2.2847682119205297,
      "grad_norm": 0.10487841814756393,
      "learning_rate": 6.690558818595943e-06,
      "loss": 0.0078,
      "num_input_tokens_seen": 333272,
      "step": 345
    },
    {
      "epoch": 2.3178807947019866,
      "grad_norm": 0.2247195988893509,
      "learning_rate": 6.111422390733715e-06,
      "loss": 0.0141,
      "num_input_tokens_seen": 337816,
      "step": 350
    },
    {
      "epoch": 2.3509933774834435,
      "grad_norm": 0.15797987580299377,
      "learning_rate": 5.55499501926394e-06,
      "loss": 0.014,
      "num_input_tokens_seen": 342792,
      "step": 355
    },
    {
      "epoch": 2.384105960264901,
      "grad_norm": 0.33236005902290344,
      "learning_rate": 5.02194567676986e-06,
      "loss": 0.0045,
      "num_input_tokens_seen": 347288,
      "step": 360
    },
    {
      "epoch": 2.4172185430463577,
      "grad_norm": 0.3886609375476837,
      "learning_rate": 4.51291522927268e-06,
      "loss": 0.0062,
      "num_input_tokens_seen": 352088,
      "step": 365
    },
    {
      "epoch": 2.4503311258278146,
      "grad_norm": 0.3580506145954132,
      "learning_rate": 4.028515665741439e-06,
      "loss": 0.0028,
      "num_input_tokens_seen": 357096,
      "step": 370
    },
    {
      "epoch": 2.4834437086092715,
      "grad_norm": 0.045303523540496826,
      "learning_rate": 3.5693293623207086e-06,
      "loss": 0.0022,
      "num_input_tokens_seen": 361928,
      "step": 375
    },
    {
      "epoch": 2.5165562913907285,
      "grad_norm": 0.3307873010635376,
      "learning_rate": 3.135908382160771e-06,
      "loss": 0.0061,
      "num_input_tokens_seen": 366632,
      "step": 380
    },
    {
      "epoch": 2.5496688741721854,
      "grad_norm": 0.31569671630859375,
      "learning_rate": 2.728773811691923e-06,
      "loss": 0.0077,
      "num_input_tokens_seen": 371352,
      "step": 385
    },
    {
      "epoch": 2.5827814569536423,
      "grad_norm": 0.25220000743865967,
      "learning_rate": 2.348415134141102e-06,
      "loss": 0.0053,
      "num_input_tokens_seen": 375976,
      "step": 390
    },
    {
      "epoch": 2.6158940397350996,
      "grad_norm": 0.12679828703403473,
      "learning_rate": 1.995289641043768e-06,
      "loss": 0.0021,
      "num_input_tokens_seen": 381016,
      "step": 395
    },
    {
      "epoch": 2.6490066225165565,
      "grad_norm": 0.2858022153377533,
      "learning_rate": 1.6698218824588164e-06,
      "loss": 0.0063,
      "num_input_tokens_seen": 385688,
      "step": 400
    },
    {
      "epoch": 2.6821192052980134,
      "grad_norm": 0.3448869287967682,
      "learning_rate": 1.3724031565473112e-06,
      "loss": 0.0052,
      "num_input_tokens_seen": 390584,
      "step": 405
    },
    {
      "epoch": 2.7152317880794703,
      "grad_norm": 0.26856377720832825,
      "learning_rate": 1.1033910391288065e-06,
      "loss": 0.0051,
      "num_input_tokens_seen": 395576,
      "step": 410
    },
    {
      "epoch": 2.748344370860927,
      "grad_norm": 0.3648998737335205,
      "learning_rate": 8.631089537808307e-07,
      "loss": 0.0084,
      "num_input_tokens_seen": 400328,
      "step": 415
    },
    {
      "epoch": 2.781456953642384,
      "grad_norm": 1.5257205963134766,
      "learning_rate": 6.51845782998356e-07,
      "loss": 0.0122,
      "num_input_tokens_seen": 405192,
      "step": 420
    },
    {
      "epoch": 2.814569536423841,
      "grad_norm": 0.4184490144252777,
      "learning_rate": 4.698555208807853e-07,
      "loss": 0.006,
      "num_input_tokens_seen": 409912,
      "step": 425
    },
    {
      "epoch": 2.847682119205298,
      "grad_norm": 0.39113691449165344,
      "learning_rate": 3.1735696776400703e-07,
      "loss": 0.0044,
      "num_input_tokens_seen": 414792,
      "step": 430
    },
    {
      "epoch": 2.880794701986755,
      "grad_norm": 0.49995261430740356,
      "learning_rate": 1.9453346716462317e-07,
      "loss": 0.0091,
      "num_input_tokens_seen": 419752,
      "step": 435
    },
    {
      "epoch": 2.9139072847682117,
      "grad_norm": 0.45024681091308594,
      "learning_rate": 1.0153268535264827e-07,
      "loss": 0.005,
      "num_input_tokens_seen": 424808,
      "step": 440
    },
    {
      "epoch": 2.9470198675496686,
      "grad_norm": 0.11354193091392517,
      "learning_rate": 3.846643381766879e-08,
      "loss": 0.0051,
      "num_input_tokens_seen": 429704,
      "step": 445
    },
    {
      "epoch": 2.980132450331126,
      "grad_norm": 0.07164571434259415,
      "learning_rate": 5.41053484192644e-09,
      "loss": 0.0049,
      "num_input_tokens_seen": 434536,
      "step": 450
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 437216,
      "step": 453,
      "total_flos": 1.8708380691726336e+16,
      "train_loss": 0.044493223137528556,
      "train_runtime": 988.3228,
      "train_samples_per_second": 7.331,
      "train_steps_per_second": 0.458
    }
  ],
  "logging_steps": 5,
  "max_steps": 453,
  "num_input_tokens_seen": 437216,
  "num_train_epochs": 3,
  "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": 1.8708380691726336e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}