{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9973992197659298,
  "eval_steps": 500,
  "global_step": 384,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02080624187256177,
      "grad_norm": 0.6747086644172668,
      "learning_rate": 4e-05,
      "loss": 1.2614,
      "step": 4
    },
    {
      "epoch": 0.04161248374512354,
      "grad_norm": 0.8340696096420288,
      "learning_rate": 8e-05,
      "loss": 1.0737,
      "step": 8
    },
    {
      "epoch": 0.06241872561768531,
      "grad_norm": 0.35006779432296753,
      "learning_rate": 0.00012,
      "loss": 0.5388,
      "step": 12
    },
    {
      "epoch": 0.08322496749024708,
      "grad_norm": 0.13230730593204498,
      "learning_rate": 0.00016,
      "loss": 0.3531,
      "step": 16
    },
    {
      "epoch": 0.10403120936280884,
      "grad_norm": 0.2690051198005676,
      "learning_rate": 0.0002,
      "loss": 0.2815,
      "step": 20
    },
    {
      "epoch": 0.12483745123537061,
      "grad_norm": 0.13100554049015045,
      "learning_rate": 0.0001978021978021978,
      "loss": 0.228,
      "step": 24
    },
    {
      "epoch": 0.14564369310793238,
      "grad_norm": 0.12533320486545563,
      "learning_rate": 0.00019560439560439562,
      "loss": 0.2046,
      "step": 28
    },
    {
      "epoch": 0.16644993498049415,
      "grad_norm": 0.08659245818853378,
      "learning_rate": 0.00019340659340659342,
      "loss": 0.179,
      "step": 32
    },
    {
      "epoch": 0.18725617685305593,
      "grad_norm": 0.08915656059980392,
      "learning_rate": 0.00019120879120879122,
      "loss": 0.1853,
      "step": 36
    },
    {
      "epoch": 0.20806241872561768,
      "grad_norm": 0.08073730021715164,
      "learning_rate": 0.00018901098901098903,
      "loss": 0.1594,
      "step": 40
    },
    {
      "epoch": 0.22886866059817945,
      "grad_norm": 0.08706673234701157,
      "learning_rate": 0.00018681318681318683,
      "loss": 0.1623,
      "step": 44
    },
    {
      "epoch": 0.24967490247074123,
      "grad_norm": 0.08052384108304977,
      "learning_rate": 0.00018461538461538463,
      "loss": 0.1469,
      "step": 48
    },
    {
      "epoch": 0.270481144343303,
      "grad_norm": 0.07896815240383148,
      "learning_rate": 0.0001824175824175824,
      "loss": 0.1503,
      "step": 52
    },
    {
      "epoch": 0.29128738621586475,
      "grad_norm": 0.09580652415752411,
      "learning_rate": 0.00018021978021978024,
      "loss": 0.1504,
      "step": 56
    },
    {
      "epoch": 0.31209362808842656,
      "grad_norm": 0.1383538842201233,
      "learning_rate": 0.00017802197802197802,
      "loss": 0.139,
      "step": 60
    },
    {
      "epoch": 0.3328998699609883,
      "grad_norm": 0.08063507080078125,
      "learning_rate": 0.00017582417582417582,
      "loss": 0.1299,
      "step": 64
    },
    {
      "epoch": 0.35370611183355005,
      "grad_norm": 0.12305614352226257,
      "learning_rate": 0.00017362637362637365,
      "loss": 0.1299,
      "step": 68
    },
    {
      "epoch": 0.37451235370611186,
      "grad_norm": 0.144222691655159,
      "learning_rate": 0.00017142857142857143,
      "loss": 0.1456,
      "step": 72
    },
    {
      "epoch": 0.3953185955786736,
      "grad_norm": 0.10816789418458939,
      "learning_rate": 0.00016923076923076923,
      "loss": 0.1449,
      "step": 76
    },
    {
      "epoch": 0.41612483745123535,
      "grad_norm": 0.09802815318107605,
      "learning_rate": 0.00016703296703296706,
      "loss": 0.1337,
      "step": 80
    },
    {
      "epoch": 0.43693107932379716,
      "grad_norm": 0.09102603048086166,
      "learning_rate": 0.00016483516483516484,
      "loss": 0.1188,
      "step": 84
    },
    {
      "epoch": 0.4577373211963589,
      "grad_norm": 0.08224384486675262,
      "learning_rate": 0.00016263736263736264,
      "loss": 0.1253,
      "step": 88
    },
    {
      "epoch": 0.47854356306892065,
      "grad_norm": 0.08681938797235489,
      "learning_rate": 0.00016043956043956044,
      "loss": 0.138,
      "step": 92
    },
    {
      "epoch": 0.49934980494148246,
      "grad_norm": 0.1142863929271698,
      "learning_rate": 0.00015824175824175824,
      "loss": 0.1454,
      "step": 96
    },
    {
      "epoch": 0.5201560468140443,
      "grad_norm": 0.14234645664691925,
      "learning_rate": 0.00015604395604395605,
      "loss": 0.1257,
      "step": 100
    },
    {
      "epoch": 0.540962288686606,
      "grad_norm": 0.09189997613430023,
      "learning_rate": 0.00015384615384615385,
      "loss": 0.1241,
      "step": 104
    },
    {
      "epoch": 0.5617685305591678,
      "grad_norm": 0.09716198593378067,
      "learning_rate": 0.00015164835164835165,
      "loss": 0.1257,
      "step": 108
    },
    {
      "epoch": 0.5825747724317295,
      "grad_norm": 0.10805213451385498,
      "learning_rate": 0.00014945054945054946,
      "loss": 0.1202,
      "step": 112
    },
    {
      "epoch": 0.6033810143042913,
      "grad_norm": 0.11224936693906784,
      "learning_rate": 0.00014725274725274726,
      "loss": 0.1325,
      "step": 116
    },
    {
      "epoch": 0.6241872561768531,
      "grad_norm": 0.0994434505701065,
      "learning_rate": 0.00014505494505494506,
      "loss": 0.1127,
      "step": 120
    },
    {
      "epoch": 0.6449934980494149,
      "grad_norm": 0.1242934837937355,
      "learning_rate": 0.00014285714285714287,
      "loss": 0.1286,
      "step": 124
    },
    {
      "epoch": 0.6657997399219766,
      "grad_norm": 0.0908965989947319,
      "learning_rate": 0.00014065934065934067,
      "loss": 0.1245,
      "step": 128
    },
    {
      "epoch": 0.6866059817945384,
      "grad_norm": 0.1325254738330841,
      "learning_rate": 0.00013846153846153847,
      "loss": 0.1233,
      "step": 132
    },
    {
      "epoch": 0.7074122236671001,
      "grad_norm": 0.11704779416322708,
      "learning_rate": 0.00013626373626373628,
      "loss": 0.1172,
      "step": 136
    },
    {
      "epoch": 0.7282184655396619,
      "grad_norm": 0.10394897311925888,
      "learning_rate": 0.00013406593406593405,
      "loss": 0.1337,
      "step": 140
    },
    {
      "epoch": 0.7490247074122237,
      "grad_norm": 0.14531978964805603,
      "learning_rate": 0.00013186813186813188,
      "loss": 0.1344,
      "step": 144
    },
    {
      "epoch": 0.7698309492847855,
      "grad_norm": 0.10536228120326996,
      "learning_rate": 0.0001296703296703297,
      "loss": 0.1153,
      "step": 148
    },
    {
      "epoch": 0.7906371911573472,
      "grad_norm": 0.46365121006965637,
      "learning_rate": 0.00012747252747252746,
      "loss": 0.1248,
      "step": 152
    },
    {
      "epoch": 0.811443433029909,
      "grad_norm": 0.148798406124115,
      "learning_rate": 0.00012527472527472527,
      "loss": 0.1255,
      "step": 156
    },
    {
      "epoch": 0.8322496749024707,
      "grad_norm": 0.10342266410589218,
      "learning_rate": 0.0001230769230769231,
      "loss": 0.1172,
      "step": 160
    },
    {
      "epoch": 0.8530559167750326,
      "grad_norm": 0.09427472203969955,
      "learning_rate": 0.00012087912087912087,
      "loss": 0.1076,
      "step": 164
    },
    {
      "epoch": 0.8738621586475943,
      "grad_norm": 0.1485118865966797,
      "learning_rate": 0.00011868131868131869,
      "loss": 0.1218,
      "step": 168
    },
    {
      "epoch": 0.8946684005201561,
      "grad_norm": 0.18458151817321777,
      "learning_rate": 0.0001164835164835165,
      "loss": 0.1287,
      "step": 172
    },
    {
      "epoch": 0.9154746423927178,
      "grad_norm": 0.1004214808344841,
      "learning_rate": 0.00011428571428571428,
      "loss": 0.1265,
      "step": 176
    },
    {
      "epoch": 0.9362808842652796,
      "grad_norm": 0.10855648666620255,
      "learning_rate": 0.0001120879120879121,
      "loss": 0.103,
      "step": 180
    },
    {
      "epoch": 0.9570871261378413,
      "grad_norm": 0.15261195600032806,
      "learning_rate": 0.0001098901098901099,
      "loss": 0.1251,
      "step": 184
    },
    {
      "epoch": 0.9778933680104032,
      "grad_norm": 0.12982791662216187,
      "learning_rate": 0.0001076923076923077,
      "loss": 0.1162,
      "step": 188
    },
    {
      "epoch": 0.9986996098829649,
      "grad_norm": 0.09743143618106842,
      "learning_rate": 0.0001054945054945055,
      "loss": 0.1126,
      "step": 192
    },
    {
      "epoch": 1.0195058517555267,
      "grad_norm": 0.0987514778971672,
      "learning_rate": 0.00010329670329670331,
      "loss": 0.1096,
      "step": 196
    },
    {
      "epoch": 1.0403120936280885,
      "grad_norm": 0.11746949702501297,
      "learning_rate": 0.0001010989010989011,
      "loss": 0.1064,
      "step": 200
    },
    {
      "epoch": 1.0611183355006502,
      "grad_norm": 0.12490434944629669,
      "learning_rate": 9.89010989010989e-05,
      "loss": 0.0924,
      "step": 204
    },
    {
      "epoch": 1.081924577373212,
      "grad_norm": 0.13480301201343536,
      "learning_rate": 9.670329670329671e-05,
      "loss": 0.1042,
      "step": 208
    },
    {
      "epoch": 1.1027308192457737,
      "grad_norm": 0.10744661092758179,
      "learning_rate": 9.450549450549451e-05,
      "loss": 0.0883,
      "step": 212
    },
    {
      "epoch": 1.1235370611183355,
      "grad_norm": 0.1190573051571846,
      "learning_rate": 9.230769230769232e-05,
      "loss": 0.0989,
      "step": 216
    },
    {
      "epoch": 1.1443433029908974,
      "grad_norm": 0.10405765473842621,
      "learning_rate": 9.010989010989012e-05,
      "loss": 0.0851,
      "step": 220
    },
    {
      "epoch": 1.165149544863459,
      "grad_norm": 0.11977458000183105,
      "learning_rate": 8.791208791208791e-05,
      "loss": 0.0891,
      "step": 224
    },
    {
      "epoch": 1.1859557867360209,
      "grad_norm": 0.12529583275318146,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.0961,
      "step": 228
    },
    {
      "epoch": 1.2067620286085825,
      "grad_norm": 0.11154180020093918,
      "learning_rate": 8.351648351648353e-05,
      "loss": 0.0854,
      "step": 232
    },
    {
      "epoch": 1.2275682704811444,
      "grad_norm": 0.14236748218536377,
      "learning_rate": 8.131868131868132e-05,
      "loss": 0.102,
      "step": 236
    },
    {
      "epoch": 1.2483745123537062,
      "grad_norm": 0.10751450061798096,
      "learning_rate": 7.912087912087912e-05,
      "loss": 0.099,
      "step": 240
    },
    {
      "epoch": 1.2691807542262679,
      "grad_norm": 0.1208043098449707,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.0929,
      "step": 244
    },
    {
      "epoch": 1.2899869960988297,
      "grad_norm": 0.11843656748533249,
      "learning_rate": 7.472527472527473e-05,
      "loss": 0.0975,
      "step": 248
    },
    {
      "epoch": 1.3107932379713914,
      "grad_norm": 0.13307110965251923,
      "learning_rate": 7.252747252747253e-05,
      "loss": 0.0929,
      "step": 252
    },
    {
      "epoch": 1.3315994798439532,
      "grad_norm": 0.14217737317085266,
      "learning_rate": 7.032967032967034e-05,
      "loss": 0.0897,
      "step": 256
    },
    {
      "epoch": 1.352405721716515,
      "grad_norm": 0.2811494469642639,
      "learning_rate": 6.813186813186814e-05,
      "loss": 0.0868,
      "step": 260
    },
    {
      "epoch": 1.3732119635890767,
      "grad_norm": 0.13263148069381714,
      "learning_rate": 6.593406593406594e-05,
      "loss": 0.0995,
      "step": 264
    },
    {
      "epoch": 1.3940182054616386,
      "grad_norm": 0.13853707909584045,
      "learning_rate": 6.373626373626373e-05,
      "loss": 0.0925,
      "step": 268
    },
    {
      "epoch": 1.4148244473342002,
      "grad_norm": 0.18387623131275177,
      "learning_rate": 6.153846153846155e-05,
      "loss": 0.095,
      "step": 272
    },
    {
      "epoch": 1.435630689206762,
      "grad_norm": 0.13655337691307068,
      "learning_rate": 5.9340659340659345e-05,
      "loss": 0.0962,
      "step": 276
    },
    {
      "epoch": 1.456436931079324,
      "grad_norm": 0.12651769816875458,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.0893,
      "step": 280
    },
    {
      "epoch": 1.4772431729518856,
      "grad_norm": 0.12896397709846497,
      "learning_rate": 5.494505494505495e-05,
      "loss": 0.0941,
      "step": 284
    },
    {
      "epoch": 1.4980494148244472,
      "grad_norm": 0.12387780100107193,
      "learning_rate": 5.274725274725275e-05,
      "loss": 0.0914,
      "step": 288
    },
    {
      "epoch": 1.518855656697009,
      "grad_norm": 0.13148820400238037,
      "learning_rate": 5.054945054945055e-05,
      "loss": 0.0879,
      "step": 292
    },
    {
      "epoch": 1.539661898569571,
      "grad_norm": 0.14551299810409546,
      "learning_rate": 4.8351648351648355e-05,
      "loss": 0.0892,
      "step": 296
    },
    {
      "epoch": 1.5604681404421328,
      "grad_norm": 0.14105795323848724,
      "learning_rate": 4.615384615384616e-05,
      "loss": 0.0957,
      "step": 300
    },
    {
      "epoch": 1.5812743823146944,
      "grad_norm": 0.16130925714969635,
      "learning_rate": 4.3956043956043955e-05,
      "loss": 0.0822,
      "step": 304
    },
    {
      "epoch": 1.602080624187256,
      "grad_norm": 0.13052895665168762,
      "learning_rate": 4.1758241758241765e-05,
      "loss": 0.083,
      "step": 308
    },
    {
      "epoch": 1.622886866059818,
      "grad_norm": 0.14026325941085815,
      "learning_rate": 3.956043956043956e-05,
      "loss": 0.0854,
      "step": 312
    },
    {
      "epoch": 1.6436931079323798,
      "grad_norm": 0.12488283216953278,
      "learning_rate": 3.7362637362637365e-05,
      "loss": 0.085,
      "step": 316
    },
    {
      "epoch": 1.6644993498049416,
      "grad_norm": 0.13594555854797363,
      "learning_rate": 3.516483516483517e-05,
      "loss": 0.0889,
      "step": 320
    },
    {
      "epoch": 1.6853055916775033,
      "grad_norm": 0.1322001814842224,
      "learning_rate": 3.296703296703297e-05,
      "loss": 0.0863,
      "step": 324
    },
    {
      "epoch": 1.706111833550065,
      "grad_norm": 0.1550651490688324,
      "learning_rate": 3.0769230769230774e-05,
      "loss": 0.0888,
      "step": 328
    },
    {
      "epoch": 1.7269180754226268,
      "grad_norm": 0.13711196184158325,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.0883,
      "step": 332
    },
    {
      "epoch": 1.7477243172951886,
      "grad_norm": 0.14158359169960022,
      "learning_rate": 2.6373626373626374e-05,
      "loss": 0.0872,
      "step": 336
    },
    {
      "epoch": 1.7685305591677505,
      "grad_norm": 0.14009161293506622,
      "learning_rate": 2.4175824175824177e-05,
      "loss": 0.0876,
      "step": 340
    },
    {
      "epoch": 1.7893368010403121,
      "grad_norm": 0.1278422623872757,
      "learning_rate": 2.1978021978021977e-05,
      "loss": 0.0948,
      "step": 344
    },
    {
      "epoch": 1.8101430429128738,
      "grad_norm": 0.16997836530208588,
      "learning_rate": 1.978021978021978e-05,
      "loss": 0.0881,
      "step": 348
    },
    {
      "epoch": 1.8309492847854356,
      "grad_norm": 0.17075221240520477,
      "learning_rate": 1.7582417582417584e-05,
      "loss": 0.0838,
      "step": 352
    },
    {
      "epoch": 1.8517555266579975,
      "grad_norm": 0.13163046538829803,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 0.0868,
      "step": 356
    },
    {
      "epoch": 1.8725617685305593,
      "grad_norm": 0.12678372859954834,
      "learning_rate": 1.3186813186813187e-05,
      "loss": 0.0894,
      "step": 360
    },
    {
      "epoch": 1.893368010403121,
      "grad_norm": 0.15091709792613983,
      "learning_rate": 1.0989010989010989e-05,
      "loss": 0.092,
      "step": 364
    },
    {
      "epoch": 1.9141742522756826,
      "grad_norm": 0.13614249229431152,
      "learning_rate": 8.791208791208792e-06,
      "loss": 0.0829,
      "step": 368
    },
    {
      "epoch": 1.9349804941482445,
      "grad_norm": 0.13656853139400482,
      "learning_rate": 6.5934065934065935e-06,
      "loss": 0.0892,
      "step": 372
    },
    {
      "epoch": 1.9557867360208063,
      "grad_norm": 0.140973761677742,
      "learning_rate": 4.395604395604396e-06,
      "loss": 0.0848,
      "step": 376
    },
    {
      "epoch": 1.976592977893368,
      "grad_norm": 0.1271371990442276,
      "learning_rate": 2.197802197802198e-06,
      "loss": 0.0757,
      "step": 380
    },
    {
      "epoch": 1.9973992197659298,
      "grad_norm": 0.17182095348834991,
      "learning_rate": 0.0,
      "loss": 0.0872,
      "step": 384
    }
  ],
  "logging_steps": 4,
  "max_steps": 384,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.091116577734861e+18,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}