{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 620,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0032258064516129032,
      "grad_norm": 3.971249580383301,
      "learning_rate": 1.6129032258064518e-07,
      "loss": 0.6284,
      "step": 1
    },
    {
      "epoch": 0.016129032258064516,
      "grad_norm": 5.593815326690674,
      "learning_rate": 8.064516129032258e-07,
      "loss": 0.6406,
      "step": 5
    },
    {
      "epoch": 0.03225806451612903,
      "grad_norm": 3.338022232055664,
      "learning_rate": 1.6129032258064516e-06,
      "loss": 0.6179,
      "step": 10
    },
    {
      "epoch": 0.04838709677419355,
      "grad_norm": 2.572110891342163,
      "learning_rate": 2.4193548387096776e-06,
      "loss": 0.5695,
      "step": 15
    },
    {
      "epoch": 0.06451612903225806,
      "grad_norm": 2.096151113510132,
      "learning_rate": 3.225806451612903e-06,
      "loss": 0.5072,
      "step": 20
    },
    {
      "epoch": 0.08064516129032258,
      "grad_norm": 2.135874032974243,
      "learning_rate": 4.032258064516129e-06,
      "loss": 0.4539,
      "step": 25
    },
    {
      "epoch": 0.0967741935483871,
      "grad_norm": 1.8665850162506104,
      "learning_rate": 4.838709677419355e-06,
      "loss": 0.394,
      "step": 30
    },
    {
      "epoch": 0.11290322580645161,
      "grad_norm": 1.8506455421447754,
      "learning_rate": 5.645161290322582e-06,
      "loss": 0.3099,
      "step": 35
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 1.882623314857483,
      "learning_rate": 6.451612903225806e-06,
      "loss": 0.2164,
      "step": 40
    },
    {
      "epoch": 0.14516129032258066,
      "grad_norm": 2.4444594383239746,
      "learning_rate": 7.258064516129033e-06,
      "loss": 0.1262,
      "step": 45
    },
    {
      "epoch": 0.16129032258064516,
      "grad_norm": 1.5979326963424683,
      "learning_rate": 8.064516129032258e-06,
      "loss": 0.068,
      "step": 50
    },
    {
      "epoch": 0.1774193548387097,
      "grad_norm": 3.323439359664917,
      "learning_rate": 8.870967741935484e-06,
      "loss": 0.0337,
      "step": 55
    },
    {
      "epoch": 0.1935483870967742,
      "grad_norm": 1.5633885860443115,
      "learning_rate": 9.67741935483871e-06,
      "loss": 0.0272,
      "step": 60
    },
    {
      "epoch": 0.20967741935483872,
      "grad_norm": 1.1317998170852661,
      "learning_rate": 9.99928681279855e-06,
      "loss": 0.0208,
      "step": 65
    },
    {
      "epoch": 0.22580645161290322,
      "grad_norm": 0.4592137932777405,
      "learning_rate": 9.994929183335237e-06,
      "loss": 0.0158,
      "step": 70
    },
    {
      "epoch": 0.24193548387096775,
      "grad_norm": 0.7832735180854797,
      "learning_rate": 9.986613588305435e-06,
      "loss": 0.0145,
      "step": 75
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.8761097192764282,
      "learning_rate": 9.974346616959476e-06,
      "loss": 0.0104,
      "step": 80
    },
    {
      "epoch": 0.27419354838709675,
      "grad_norm": 0.9911714196205139,
      "learning_rate": 9.95813798960538e-06,
      "loss": 0.0115,
      "step": 85
    },
    {
      "epoch": 0.2903225806451613,
      "grad_norm": 0.48290345072746277,
      "learning_rate": 9.938000549906509e-06,
      "loss": 0.0092,
      "step": 90
    },
    {
      "epoch": 0.3064516129032258,
      "grad_norm": 0.8782544136047363,
      "learning_rate": 9.913950254704291e-06,
      "loss": 0.0167,
      "step": 95
    },
    {
      "epoch": 0.3225806451612903,
      "grad_norm": 0.827684223651886,
      "learning_rate": 9.88600616137407e-06,
      "loss": 0.0087,
      "step": 100
    },
    {
      "epoch": 0.3387096774193548,
      "grad_norm": 0.4351416826248169,
      "learning_rate": 9.854190412724114e-06,
      "loss": 0.0092,
      "step": 105
    },
    {
      "epoch": 0.3548387096774194,
      "grad_norm": 0.617416262626648,
      "learning_rate": 9.818528219449705e-06,
      "loss": 0.0106,
      "step": 110
    },
    {
      "epoch": 0.3709677419354839,
      "grad_norm": 0.3410218060016632,
      "learning_rate": 9.779047840156288e-06,
      "loss": 0.0092,
      "step": 115
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 0.6016420722007751,
      "learning_rate": 9.735780558967434e-06,
      "loss": 0.0081,
      "step": 120
    },
    {
      "epoch": 0.4032258064516129,
      "grad_norm": 0.34005704522132874,
      "learning_rate": 9.688760660735403e-06,
      "loss": 0.0075,
      "step": 125
    },
    {
      "epoch": 0.41935483870967744,
      "grad_norm": 1.3894850015640259,
      "learning_rate": 9.638025403873939e-06,
      "loss": 0.0074,
      "step": 130
    },
    {
      "epoch": 0.43548387096774194,
      "grad_norm": 0.3171682059764862,
      "learning_rate": 9.58361499083483e-06,
      "loss": 0.007,
      "step": 135
    },
    {
      "epoch": 0.45161290322580644,
      "grad_norm": 0.5876194834709167,
      "learning_rate": 9.525572536251608e-06,
      "loss": 0.0085,
      "step": 140
    },
    {
      "epoch": 0.46774193548387094,
      "grad_norm": 0.47260814905166626,
      "learning_rate": 9.46394403277566e-06,
      "loss": 0.0067,
      "step": 145
    },
    {
      "epoch": 0.4838709677419355,
      "grad_norm": 0.6115548014640808,
      "learning_rate": 9.398778314631801e-06,
      "loss": 0.0084,
      "step": 150
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.44270601868629456,
      "learning_rate": 9.330127018922195e-06,
      "loss": 0.0063,
      "step": 155
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.5065975785255432,
      "learning_rate": 9.258044544709276e-06,
      "loss": 0.0079,
      "step": 160
    },
    {
      "epoch": 0.532258064516129,
      "grad_norm": 0.9441617131233215,
      "learning_rate": 9.182588009910119e-06,
      "loss": 0.0075,
      "step": 165
    },
    {
      "epoch": 0.5483870967741935,
      "grad_norm": 0.7031365036964417,
      "learning_rate": 9.103817206036383e-06,
      "loss": 0.0067,
      "step": 170
    },
    {
      "epoch": 0.5645161290322581,
      "grad_norm": 0.6422185301780701,
      "learning_rate": 9.021794550815713e-06,
      "loss": 0.0088,
      "step": 175
    },
    {
      "epoch": 0.5806451612903226,
      "grad_norm": 0.547900378704071,
      "learning_rate": 8.936585038732143e-06,
      "loss": 0.006,
      "step": 180
    },
    {
      "epoch": 0.5967741935483871,
      "grad_norm": 0.6972706913948059,
      "learning_rate": 8.848256189524661e-06,
      "loss": 0.0057,
      "step": 185
    },
    {
      "epoch": 0.6129032258064516,
      "grad_norm": 0.37197422981262207,
      "learning_rate": 8.756877994684818e-06,
      "loss": 0.0049,
      "step": 190
    },
    {
      "epoch": 0.6290322580645161,
      "grad_norm": 0.2147480994462967,
      "learning_rate": 8.66252286199567e-06,
      "loss": 0.0081,
      "step": 195
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.44903531670570374,
      "learning_rate": 8.565265558156101e-06,
      "loss": 0.0055,
      "step": 200
    },
    {
      "epoch": 0.6612903225806451,
      "grad_norm": 1.0128227472305298,
      "learning_rate": 8.465183149535939e-06,
      "loss": 0.0054,
      "step": 205
    },
    {
      "epoch": 0.6774193548387096,
      "grad_norm": 0.4877210557460785,
      "learning_rate": 8.362354941108803e-06,
      "loss": 0.0057,
      "step": 210
    },
    {
      "epoch": 0.6935483870967742,
      "grad_norm": 0.2644139230251312,
      "learning_rate": 8.256862413611113e-06,
      "loss": 0.005,
      "step": 215
    },
    {
      "epoch": 0.7096774193548387,
      "grad_norm": 0.6257811784744263,
      "learning_rate": 8.148789158977012e-06,
      "loss": 0.0055,
      "step": 220
    },
    {
      "epoch": 0.7258064516129032,
      "grad_norm": 0.19504040479660034,
      "learning_rate": 8.038220814100403e-06,
      "loss": 0.005,
      "step": 225
    },
    {
      "epoch": 0.7419354838709677,
      "grad_norm": 0.5125346779823303,
      "learning_rate": 7.925244992976538e-06,
      "loss": 0.0055,
      "step": 230
    },
    {
      "epoch": 0.7580645161290323,
      "grad_norm": 0.46777665615081787,
      "learning_rate": 7.809951217276986e-06,
      "loss": 0.0052,
      "step": 235
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.5273892283439636,
      "learning_rate": 7.692430845412946e-06,
      "loss": 0.006,
      "step": 240
    },
    {
      "epoch": 0.7903225806451613,
      "grad_norm": 0.5478794574737549,
      "learning_rate": 7.572777000143145e-06,
      "loss": 0.0078,
      "step": 245
    },
    {
      "epoch": 0.8064516129032258,
      "grad_norm": 0.35614484548568726,
      "learning_rate": 7.451084494783668e-06,
      "loss": 0.0051,
      "step": 250
    },
    {
      "epoch": 0.8225806451612904,
      "grad_norm": 0.42776939272880554,
      "learning_rate": 7.327449758078194e-06,
      "loss": 0.0057,
      "step": 255
    },
    {
      "epoch": 0.8387096774193549,
      "grad_norm": 0.19282685220241547,
      "learning_rate": 7.201970757788172e-06,
      "loss": 0.0039,
      "step": 260
    },
    {
      "epoch": 0.8548387096774194,
      "grad_norm": 0.7167965173721313,
      "learning_rate": 7.074746923063497e-06,
      "loss": 0.0042,
      "step": 265
    },
    {
      "epoch": 0.8709677419354839,
      "grad_norm": 3.5436365604400635,
      "learning_rate": 6.945879065655164e-06,
      "loss": 0.0042,
      "step": 270
    },
    {
      "epoch": 0.8870967741935484,
      "grad_norm": 0.3570103347301483,
      "learning_rate": 6.815469300032374e-06,
      "loss": 0.0043,
      "step": 275
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 0.252421110868454,
      "learning_rate": 6.6836209624673575e-06,
      "loss": 0.0056,
      "step": 280
    },
    {
      "epoch": 0.9193548387096774,
      "grad_norm": 0.2856729030609131,
      "learning_rate": 6.5504385291520554e-06,
      "loss": 0.0052,
      "step": 285
    },
    {
      "epoch": 0.9354838709677419,
      "grad_norm": 0.25228211283683777,
      "learning_rate": 6.41602753341152e-06,
      "loss": 0.0055,
      "step": 290
    },
    {
      "epoch": 0.9516129032258065,
      "grad_norm": 0.29258614778518677,
      "learning_rate": 6.2804944820796596e-06,
      "loss": 0.0037,
      "step": 295
    },
    {
      "epoch": 0.967741935483871,
      "grad_norm": 0.1690083146095276,
      "learning_rate": 6.143946771103561e-06,
      "loss": 0.0032,
      "step": 300
    },
    {
      "epoch": 0.9838709677419355,
      "grad_norm": 0.45113542675971985,
      "learning_rate": 6.006492600443301e-06,
      "loss": 0.0036,
      "step": 305
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.34520477056503296,
      "learning_rate": 5.8682408883346535e-06,
      "loss": 0.0049,
      "step": 310
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.004980116616934538,
      "eval_runtime": 3.8044,
      "eval_samples_per_second": 0.789,
      "eval_steps_per_second": 0.789,
      "step": 310
    },
    {
      "epoch": 1.0161290322580645,
      "grad_norm": 0.19288980960845947,
      "learning_rate": 5.729301184982622e-06,
      "loss": 0.0034,
      "step": 315
    },
    {
      "epoch": 1.032258064516129,
      "grad_norm": 0.19823557138442993,
      "learning_rate": 5.5897835857542315e-06,
      "loss": 0.0026,
      "step": 320
    },
    {
      "epoch": 1.0483870967741935,
      "grad_norm": 0.09697025269269943,
      "learning_rate": 5.449798643939305e-06,
      "loss": 0.0024,
      "step": 325
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 0.23041202127933502,
      "learning_rate": 5.30945728314841e-06,
      "loss": 0.0028,
      "step": 330
    },
    {
      "epoch": 1.0806451612903225,
      "grad_norm": 0.27025359869003296,
      "learning_rate": 5.168870709417342e-06,
      "loss": 0.0034,
      "step": 335
    },
    {
      "epoch": 1.096774193548387,
      "grad_norm": 0.3000248968601227,
      "learning_rate": 5.0281503230878304e-06,
      "loss": 0.0033,
      "step": 340
    },
    {
      "epoch": 1.1129032258064515,
      "grad_norm": 0.22583173215389252,
      "learning_rate": 4.887407630534271e-06,
      "loss": 0.0027,
      "step": 345
    },
    {
      "epoch": 1.129032258064516,
      "grad_norm": 0.21011537313461304,
      "learning_rate": 4.746754155806437e-06,
      "loss": 0.0026,
      "step": 350
    },
    {
      "epoch": 1.1451612903225807,
      "grad_norm": 0.13884232938289642,
      "learning_rate": 4.606301352258192e-06,
      "loss": 0.0028,
      "step": 355
    },
    {
      "epoch": 1.1612903225806452,
      "grad_norm": 0.25201186537742615,
      "learning_rate": 4.466160514232206e-06,
      "loss": 0.0027,
      "step": 360
    },
    {
      "epoch": 1.1774193548387097,
      "grad_norm": 0.22268442809581757,
      "learning_rate": 4.326442688870697e-06,
      "loss": 0.0028,
      "step": 365
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 0.21970783174037933,
      "learning_rate": 4.187258588122019e-06,
      "loss": 0.0031,
      "step": 370
    },
    {
      "epoch": 1.2096774193548387,
      "grad_norm": 0.26229333877563477,
      "learning_rate": 4.048718501012895e-06,
      "loss": 0.0026,
      "step": 375
    },
    {
      "epoch": 1.2258064516129032,
      "grad_norm": 0.25772520899772644,
      "learning_rate": 3.910932206255742e-06,
      "loss": 0.0022,
      "step": 380
    },
    {
      "epoch": 1.2419354838709677,
      "grad_norm": 0.4050711691379547,
      "learning_rate": 3.77400888526038e-06,
      "loss": 0.0023,
      "step": 385
    },
    {
      "epoch": 1.2580645161290323,
      "grad_norm": 0.2486872673034668,
      "learning_rate": 3.6380570356190346e-06,
      "loss": 0.0036,
      "step": 390
    },
    {
      "epoch": 1.2741935483870968,
      "grad_norm": 0.20115166902542114,
      "learning_rate": 3.5031843851332105e-06,
      "loss": 0.0017,
      "step": 395
    },
    {
      "epoch": 1.2903225806451613,
      "grad_norm": 0.19394518435001373,
      "learning_rate": 3.3694978064505258e-06,
      "loss": 0.0029,
      "step": 400
    },
    {
      "epoch": 1.3064516129032258,
      "grad_norm": 0.25958162546157837,
      "learning_rate": 3.2371032323791757e-06,
      "loss": 0.003,
      "step": 405
    },
    {
      "epoch": 1.3225806451612903,
      "grad_norm": 0.27680277824401855,
      "learning_rate": 3.10610557194712e-06,
      "loss": 0.002,
      "step": 410
    },
    {
      "epoch": 1.3387096774193548,
      "grad_norm": 0.31953132152557373,
      "learning_rate": 2.97660862727252e-06,
      "loss": 0.0039,
      "step": 415
    },
    {
      "epoch": 1.3548387096774195,
      "grad_norm": 0.3594481647014618,
      "learning_rate": 2.848715011311271e-06,
      "loss": 0.0031,
      "step": 420
    },
    {
      "epoch": 1.370967741935484,
      "grad_norm": 0.15407758951187134,
      "learning_rate": 2.72252606654683e-06,
      "loss": 0.0032,
      "step": 425
    },
    {
      "epoch": 1.3870967741935485,
      "grad_norm": 0.25268280506134033,
      "learning_rate": 2.5981417846867753e-06,
      "loss": 0.0029,
      "step": 430
    },
    {
      "epoch": 1.403225806451613,
      "grad_norm": 0.19317582249641418,
      "learning_rate": 2.4756607274296844e-06,
      "loss": 0.0035,
      "step": 435
    },
    {
      "epoch": 1.4193548387096775,
      "grad_norm": 0.15693552792072296,
      "learning_rate": 2.3551799483651894e-06,
      "loss": 0.0026,
      "step": 440
    },
    {
      "epoch": 1.435483870967742,
      "grad_norm": 0.19608916342258453,
      "learning_rate": 2.236794916069007e-06,
      "loss": 0.0028,
      "step": 445
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.403870552778244,
      "learning_rate": 2.120599438453968e-06,
      "loss": 0.0032,
      "step": 450
    },
    {
      "epoch": 1.467741935483871,
      "grad_norm": 0.16400307416915894,
      "learning_rate": 2.0066855884369246e-06,
      "loss": 0.0025,
      "step": 455
    },
    {
      "epoch": 1.4838709677419355,
      "grad_norm": 0.954981803894043,
      "learning_rate": 1.8951436309804766e-06,
      "loss": 0.0024,
      "step": 460
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.23671939969062805,
      "learning_rate": 1.7860619515673034e-06,
      "loss": 0.0029,
      "step": 465
    },
    {
      "epoch": 1.5161290322580645,
      "grad_norm": 0.1934683918952942,
      "learning_rate": 1.6795269861638041e-06,
      "loss": 0.0033,
      "step": 470
    },
    {
      "epoch": 1.532258064516129,
      "grad_norm": 0.12341190874576569,
      "learning_rate": 1.5756231527285181e-06,
      "loss": 0.0027,
      "step": 475
    },
    {
      "epoch": 1.5483870967741935,
      "grad_norm": 0.44817498326301575,
      "learning_rate": 1.4744327843196043e-06,
      "loss": 0.0034,
      "step": 480
    },
    {
      "epoch": 1.564516129032258,
      "grad_norm": 0.29806482791900635,
      "learning_rate": 1.3760360638544012e-06,
      "loss": 0.0031,
      "step": 485
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 0.19129404425621033,
      "learning_rate": 1.280510960572745e-06,
      "loss": 0.0017,
      "step": 490
    },
    {
      "epoch": 1.596774193548387,
      "grad_norm": 0.21360230445861816,
      "learning_rate": 1.1879331682543972e-06,
      "loss": 0.0034,
      "step": 495
    },
    {
      "epoch": 1.6129032258064515,
      "grad_norm": 0.2776956260204315,
      "learning_rate": 1.0983760452395415e-06,
      "loss": 0.0021,
      "step": 500
    },
    {
      "epoch": 1.629032258064516,
      "grad_norm": 0.15755566954612732,
      "learning_rate": 1.01191055629987e-06,
      "loss": 0.0019,
      "step": 505
    },
    {
      "epoch": 1.6451612903225805,
      "grad_norm": 0.3595326840877533,
      "learning_rate": 9.286052164063369e-07,
      "loss": 0.0023,
      "step": 510
    },
    {
      "epoch": 1.661290322580645,
      "grad_norm": 0.19125986099243164,
      "learning_rate": 8.485260364381187e-07,
      "loss": 0.0041,
      "step": 515
    },
    {
      "epoch": 1.6774193548387095,
      "grad_norm": 0.3362486958503723,
      "learning_rate": 7.717364708758024e-07,
      "loss": 0.002,
      "step": 520
    },
    {
      "epoch": 1.6935483870967742,
      "grad_norm": 0.23303864896297455,
      "learning_rate": 6.982973675202676e-07,
      "loss": 0.0017,
      "step": 525
    },
    {
      "epoch": 1.7096774193548387,
      "grad_norm": 0.13133780658245087,
      "learning_rate": 6.282669192770896e-07,
      "loss": 0.0024,
      "step": 530
    },
    {
      "epoch": 1.7258064516129032,
      "grad_norm": 0.35981041193008423,
      "learning_rate": 5.617006180446688e-07,
      "loss": 0.0033,
      "step": 535
    },
    {
      "epoch": 1.7419354838709677,
      "grad_norm": 0.41394540667533875,
      "learning_rate": 4.986512107426283e-07,
      "loss": 0.003,
      "step": 540
    },
    {
      "epoch": 1.7580645161290323,
      "grad_norm": 0.24306242167949677,
      "learning_rate": 4.3916865751533313e-07,
      "loss": 0.003,
      "step": 545
    },
    {
      "epoch": 1.7741935483870968,
      "grad_norm": 0.1294822096824646,
      "learning_rate": 3.8330009214363197e-07,
      "loss": 0.0028,
      "step": 550
    },
    {
      "epoch": 1.7903225806451613,
      "grad_norm": 0.12696751952171326,
      "learning_rate": 3.310897846962041e-07,
      "loss": 0.0027,
      "step": 555
    },
    {
      "epoch": 1.8064516129032258,
      "grad_norm": 0.27052465081214905,
      "learning_rate": 2.8257910645009935e-07,
      "loss": 0.0034,
      "step": 560
    },
    {
      "epoch": 1.8225806451612905,
      "grad_norm": 0.21007302403450012,
      "learning_rate": 2.3780649710827552e-07,
      "loss": 0.0029,
      "step": 565
    },
    {
      "epoch": 1.838709677419355,
      "grad_norm": 0.20920442044734955,
      "learning_rate": 1.9680743434010385e-07,
      "loss": 0.0026,
      "step": 570
    },
    {
      "epoch": 1.8548387096774195,
      "grad_norm": 0.2021329551935196,
      "learning_rate": 1.5961440566897913e-07,
      "loss": 0.0026,
      "step": 575
    },
    {
      "epoch": 1.870967741935484,
      "grad_norm": 0.23637109994888306,
      "learning_rate": 1.2625688272930925e-07,
      "loss": 0.0036,
      "step": 580
    },
    {
      "epoch": 1.8870967741935485,
      "grad_norm": 0.17650996148586273,
      "learning_rate": 9.676129791329481e-08,
      "loss": 0.0024,
      "step": 585
    },
    {
      "epoch": 1.903225806451613,
      "grad_norm": 0.19747471809387207,
      "learning_rate": 7.115102342598101e-08,
      "loss": 0.0035,
      "step": 590
    },
    {
      "epoch": 1.9193548387096775,
      "grad_norm": 0.6039708852767944,
      "learning_rate": 4.944635276520393e-08,
      "loss": 0.0029,
      "step": 595
    },
    {
      "epoch": 1.935483870967742,
      "grad_norm": 0.3589779734611511,
      "learning_rate": 3.166448464108629e-08,
      "loss": 0.0049,
      "step": 600
    },
    {
      "epoch": 1.9516129032258065,
      "grad_norm": 0.12553617358207703,
      "learning_rate": 1.781950934783505e-08,
      "loss": 0.0027,
      "step": 605
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.1768651306629181,
      "learning_rate": 7.922397598642551e-09,
      "loss": 0.0018,
      "step": 610
    },
    {
      "epoch": 1.9838709677419355,
      "grad_norm": 0.24496199190616608,
      "learning_rate": 1.980991832524759e-09,
      "loss": 0.0021,
      "step": 615
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2647761106491089,
      "learning_rate": 0.0,
      "loss": 0.0026,
      "step": 620
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.004049910232424736,
      "eval_runtime": 3.8097,
      "eval_samples_per_second": 0.787,
      "eval_steps_per_second": 0.787,
      "step": 620
    },
    {
      "epoch": 2.0,
      "step": 620,
      "total_flos": 1.1181005894949274e+17,
      "train_loss": 0.03632537112270873,
      "train_runtime": 2624.7531,
      "train_samples_per_second": 0.236,
      "train_steps_per_second": 0.236
    }
  ],
  "logging_steps": 5,
  "max_steps": 620,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.1181005894949274e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}