{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "grad_norm": 4.447973251342773,
      "learning_rate": 4e-05,
      "loss": 2.7672,
      "step": 1
    },
    {
      "epoch": 0.1,
      "grad_norm": 4.150802135467529,
      "learning_rate": 8e-05,
      "loss": 2.6287,
      "step": 2
    },
    {
      "epoch": 0.15,
      "grad_norm": 3.937238931655884,
      "learning_rate": 0.00012,
      "loss": 2.5862,
      "step": 3
    },
    {
      "epoch": 0.2,
      "grad_norm": 3.001154899597168,
      "learning_rate": 0.00016,
      "loss": 2.1841,
      "step": 4
    },
    {
      "epoch": 0.25,
      "grad_norm": 2.4711031913757324,
      "learning_rate": 0.0002,
      "loss": 1.8194,
      "step": 5
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.8626506328582764,
      "learning_rate": 0.00019994532573409262,
      "loss": 1.5182,
      "step": 6
    },
    {
      "epoch": 0.35,
      "grad_norm": 1.5748854875564575,
      "learning_rate": 0.00019978136272187747,
      "loss": 1.2377,
      "step": 7
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.3064329624176025,
      "learning_rate": 0.00019950829025450114,
      "loss": 1.0241,
      "step": 8
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.1094794273376465,
      "learning_rate": 0.00019912640693269752,
      "loss": 0.963,
      "step": 9
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.3718185424804688,
      "learning_rate": 0.00019863613034027224,
      "loss": 0.919,
      "step": 10
    },
    {
      "epoch": 0.55,
      "grad_norm": 0.6297829151153564,
      "learning_rate": 0.00019803799658748094,
      "loss": 0.8479,
      "step": 11
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.5934209227561951,
      "learning_rate": 0.0001973326597248006,
      "loss": 0.8286,
      "step": 12
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.5935357809066772,
      "learning_rate": 0.00019652089102773488,
      "loss": 0.7957,
      "step": 13
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.4544467031955719,
      "learning_rate": 0.00019560357815343577,
      "loss": 0.7723,
      "step": 14
    },
    {
      "epoch": 0.75,
      "grad_norm": 0.3061223030090332,
      "learning_rate": 0.00019458172417006347,
      "loss": 0.7505,
      "step": 15
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.4051577150821686,
      "learning_rate": 0.0001934564464599461,
      "loss": 0.774,
      "step": 16
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.35342541337013245,
      "learning_rate": 0.00019222897549773848,
      "loss": 0.7647,
      "step": 17
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.2566414773464203,
      "learning_rate": 0.00019090065350491626,
      "loss": 0.7316,
      "step": 18
    },
    {
      "epoch": 0.95,
      "grad_norm": 0.27759572863578796,
      "learning_rate": 0.00018947293298207635,
      "loss": 0.74,
      "step": 19
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2516538202762604,
      "learning_rate": 0.0001879473751206489,
      "loss": 0.7862,
      "step": 20
    },
    {
      "epoch": 1.05,
      "grad_norm": 0.291866660118103,
      "learning_rate": 0.00018632564809575742,
      "loss": 0.6802,
      "step": 21
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.26497676968574524,
      "learning_rate": 0.00018460952524209355,
      "loss": 0.6779,
      "step": 22
    },
    {
      "epoch": 1.15,
      "grad_norm": 0.29328078031539917,
      "learning_rate": 0.00018280088311480201,
      "loss": 0.6612,
      "step": 23
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.24686995148658752,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.6859,
      "step": 24
    },
    {
      "epoch": 1.25,
      "grad_norm": 0.24599069356918335,
      "learning_rate": 0.00017891405093963938,
      "loss": 0.6753,
      "step": 25
    },
    {
      "epoch": 1.3,
      "grad_norm": 0.22834160923957825,
      "learning_rate": 0.00017684011108568592,
      "loss": 0.677,
      "step": 26
    },
    {
      "epoch": 1.35,
      "grad_norm": 0.24461103975772858,
      "learning_rate": 0.0001746821476984154,
      "loss": 0.6418,
      "step": 27
    },
    {
      "epoch": 1.4,
      "grad_norm": 0.21487152576446533,
      "learning_rate": 0.00017244252047910892,
      "loss": 0.6358,
      "step": 28
    },
    {
      "epoch": 1.45,
      "grad_norm": 0.21681031584739685,
      "learning_rate": 0.00017012367842724887,
      "loss": 0.6218,
      "step": 29
    },
    {
      "epoch": 1.5,
      "grad_norm": 0.2119208723306656,
      "learning_rate": 0.00016772815716257412,
      "loss": 0.5886,
      "step": 30
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.22078657150268555,
      "learning_rate": 0.00016525857615241687,
      "loss": 0.6381,
      "step": 31
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.22970253229141235,
      "learning_rate": 0.0001627176358473537,
      "loss": 0.6165,
      "step": 32
    },
    {
      "epoch": 1.65,
      "grad_norm": 0.2325950413942337,
      "learning_rate": 0.00016010811472830252,
      "loss": 0.6287,
      "step": 33
    },
    {
      "epoch": 1.7,
      "grad_norm": 0.21151460707187653,
      "learning_rate": 0.00015743286626829437,
      "loss": 0.567,
      "step": 34
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.22438429296016693,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.6076,
      "step": 35
    },
    {
      "epoch": 1.8,
      "grad_norm": 0.21426045894622803,
      "learning_rate": 0.00015189695737812152,
      "loss": 0.6024,
      "step": 36
    },
    {
      "epoch": 1.85,
      "grad_norm": 0.21215516328811646,
      "learning_rate": 0.00014904235038305083,
      "loss": 0.6146,
      "step": 37
    },
    {
      "epoch": 1.9,
      "grad_norm": 0.2205992490053177,
      "learning_rate": 0.0001461341162978688,
      "loss": 0.5927,
      "step": 38
    },
    {
      "epoch": 1.95,
      "grad_norm": 0.2277802973985672,
      "learning_rate": 0.00014317543523384928,
      "loss": 0.5872,
      "step": 39
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.22207193076610565,
      "learning_rate": 0.00014016954246529696,
      "loss": 0.6077,
      "step": 40
    },
    {
      "epoch": 2.05,
      "grad_norm": 0.2099306583404541,
      "learning_rate": 0.00013711972489182208,
      "loss": 0.571,
      "step": 41
    },
    {
      "epoch": 2.1,
      "grad_norm": 0.2039865106344223,
      "learning_rate": 0.00013402931744416433,
      "loss": 0.5606,
      "step": 42
    },
    {
      "epoch": 2.15,
      "grad_norm": 0.20860564708709717,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.5544,
      "step": 43
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.22982315719127655,
      "learning_rate": 0.00012774029087618446,
      "loss": 0.5526,
      "step": 44
    },
    {
      "epoch": 2.25,
      "grad_norm": 0.20864799618721008,
      "learning_rate": 0.00012454854871407994,
      "loss": 0.5237,
      "step": 45
    },
    {
      "epoch": 2.3,
      "grad_norm": 0.21810759603977203,
      "learning_rate": 0.0001213299630743747,
      "loss": 0.5299,
      "step": 46
    },
    {
      "epoch": 2.35,
      "grad_norm": 0.21522781252861023,
      "learning_rate": 0.000118088053433211,
      "loss": 0.5316,
      "step": 47
    },
    {
      "epoch": 2.4,
      "grad_norm": 0.20544247329235077,
      "learning_rate": 0.0001148263647711842,
      "loss": 0.5068,
      "step": 48
    },
    {
      "epoch": 2.45,
      "grad_norm": 0.2135314643383026,
      "learning_rate": 0.00011154846369695863,
      "loss": 0.5364,
      "step": 49
    },
    {
      "epoch": 2.5,
      "grad_norm": 0.21021024882793427,
      "learning_rate": 0.00010825793454723325,
      "loss": 0.5186,
      "step": 50
    },
    {
      "epoch": 2.55,
      "grad_norm": 0.2136543244123459,
      "learning_rate": 0.00010495837546732224,
      "loss": 0.5339,
      "step": 51
    },
    {
      "epoch": 2.6,
      "grad_norm": 0.23084285855293274,
      "learning_rate": 0.00010165339447663587,
      "loss": 0.5378,
      "step": 52
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.20442883670330048,
      "learning_rate": 9.834660552336415e-05,
      "loss": 0.5268,
      "step": 53
    },
    {
      "epoch": 2.7,
      "grad_norm": 0.22932833433151245,
      "learning_rate": 9.504162453267777e-05,
      "loss": 0.5174,
      "step": 54
    },
    {
      "epoch": 2.75,
      "grad_norm": 0.22436076402664185,
      "learning_rate": 9.174206545276677e-05,
      "loss": 0.5377,
      "step": 55
    },
    {
      "epoch": 2.8,
      "grad_norm": 0.2104436308145523,
      "learning_rate": 8.845153630304139e-05,
      "loss": 0.4974,
      "step": 56
    },
    {
      "epoch": 2.85,
      "grad_norm": 0.2314048409461975,
      "learning_rate": 8.517363522881579e-05,
      "loss": 0.5499,
      "step": 57
    },
    {
      "epoch": 2.9,
      "grad_norm": 0.22638021409511566,
      "learning_rate": 8.191194656678904e-05,
      "loss": 0.5341,
      "step": 58
    },
    {
      "epoch": 2.95,
      "grad_norm": 0.21407343447208405,
      "learning_rate": 7.867003692562534e-05,
      "loss": 0.5386,
      "step": 59
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.224117249250412,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.5139,
      "step": 60
    },
    {
      "epoch": 3.05,
      "grad_norm": 0.20954056084156036,
      "learning_rate": 7.225970912381556e-05,
      "loss": 0.5009,
      "step": 61
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.21707436442375183,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.5039,
      "step": 62
    },
    {
      "epoch": 3.15,
      "grad_norm": 0.21246309578418732,
      "learning_rate": 6.59706825558357e-05,
      "loss": 0.4932,
      "step": 63
    },
    {
      "epoch": 3.2,
      "grad_norm": 0.22075852751731873,
      "learning_rate": 6.28802751081779e-05,
      "loss": 0.4946,
      "step": 64
    },
    {
      "epoch": 3.25,
      "grad_norm": 0.2115776240825653,
      "learning_rate": 5.983045753470308e-05,
      "loss": 0.4816,
      "step": 65
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.2231447845697403,
      "learning_rate": 5.6824564766150726e-05,
      "loss": 0.4471,
      "step": 66
    },
    {
      "epoch": 3.35,
      "grad_norm": 0.2261902540922165,
      "learning_rate": 5.386588370213124e-05,
      "loss": 0.4758,
      "step": 67
    },
    {
      "epoch": 3.4,
      "grad_norm": 0.23066717386245728,
      "learning_rate": 5.095764961694922e-05,
      "loss": 0.4946,
      "step": 68
    },
    {
      "epoch": 3.45,
      "grad_norm": 0.23373715579509735,
      "learning_rate": 4.810304262187852e-05,
      "loss": 0.4551,
      "step": 69
    },
    {
      "epoch": 3.5,
      "grad_norm": 0.22016406059265137,
      "learning_rate": 4.530518418775733e-05,
      "loss": 0.4678,
      "step": 70
    },
    {
      "epoch": 3.55,
      "grad_norm": 0.22911153733730316,
      "learning_rate": 4.256713373170564e-05,
      "loss": 0.4621,
      "step": 71
    },
    {
      "epoch": 3.6,
      "grad_norm": 0.2464921772480011,
      "learning_rate": 3.9891885271697496e-05,
      "loss": 0.4524,
      "step": 72
    },
    {
      "epoch": 3.65,
      "grad_norm": 0.22986730933189392,
      "learning_rate": 3.7282364152646297e-05,
      "loss": 0.4619,
      "step": 73
    },
    {
      "epoch": 3.7,
      "grad_norm": 0.2360897809267044,
      "learning_rate": 3.4741423847583134e-05,
      "loss": 0.4873,
      "step": 74
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.23576760292053223,
      "learning_rate": 3.227184283742591e-05,
      "loss": 0.4566,
      "step": 75
    },
    {
      "epoch": 3.8,
      "grad_norm": 0.23615522682666779,
      "learning_rate": 2.9876321572751144e-05,
      "loss": 0.479,
      "step": 76
    },
    {
      "epoch": 3.85,
      "grad_norm": 0.2297057807445526,
      "learning_rate": 2.7557479520891104e-05,
      "loss": 0.4453,
      "step": 77
    },
    {
      "epoch": 3.9,
      "grad_norm": 0.23760643601417542,
      "learning_rate": 2.5317852301584643e-05,
      "loss": 0.4603,
      "step": 78
    },
    {
      "epoch": 3.95,
      "grad_norm": 0.23733963072299957,
      "learning_rate": 2.315988891431412e-05,
      "loss": 0.4904,
      "step": 79
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.23631036281585693,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.4378,
      "step": 80
    },
    {
      "epoch": 4.05,
      "grad_norm": 0.21698763966560364,
      "learning_rate": 1.9098300562505266e-05,
      "loss": 0.4746,
      "step": 81
    },
    {
      "epoch": 4.1,
      "grad_norm": 0.22145631909370422,
      "learning_rate": 1.7199116885197995e-05,
      "loss": 0.4326,
      "step": 82
    },
    {
      "epoch": 4.15,
      "grad_norm": 0.2206316590309143,
      "learning_rate": 1.5390474757906446e-05,
      "loss": 0.4661,
      "step": 83
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.22402209043502808,
      "learning_rate": 1.3674351904242611e-05,
      "loss": 0.4242,
      "step": 84
    },
    {
      "epoch": 4.25,
      "grad_norm": 0.2289542257785797,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.4374,
      "step": 85
    },
    {
      "epoch": 4.3,
      "grad_norm": 0.22736269235610962,
      "learning_rate": 1.0527067017923654e-05,
      "loss": 0.4555,
      "step": 86
    },
    {
      "epoch": 4.35,
      "grad_norm": 0.23473459482192993,
      "learning_rate": 9.09934649508375e-06,
      "loss": 0.457,
      "step": 87
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.23741869628429413,
      "learning_rate": 7.771024502261526e-06,
      "loss": 0.4488,
      "step": 88
    },
    {
      "epoch": 4.45,
      "grad_norm": 0.2166988104581833,
      "learning_rate": 6.543553540053926e-06,
      "loss": 0.4071,
      "step": 89
    },
    {
      "epoch": 4.5,
      "grad_norm": 0.2260877788066864,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.4167,
      "step": 90
    },
    {
      "epoch": 4.55,
      "grad_norm": 0.2313169240951538,
      "learning_rate": 4.3964218465642355e-06,
      "loss": 0.4316,
      "step": 91
    },
    {
      "epoch": 4.6,
      "grad_norm": 0.23149524629116058,
      "learning_rate": 3.4791089722651436e-06,
      "loss": 0.4373,
      "step": 92
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.2258220762014389,
      "learning_rate": 2.667340275199426e-06,
      "loss": 0.4298,
      "step": 93
    },
    {
      "epoch": 4.7,
      "grad_norm": 0.23423810303211212,
      "learning_rate": 1.9620034125190644e-06,
      "loss": 0.4717,
      "step": 94
    },
    {
      "epoch": 4.75,
      "grad_norm": 0.22674737870693207,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.4406,
      "step": 95
    },
    {
      "epoch": 4.8,
      "grad_norm": 0.22755774855613708,
      "learning_rate": 8.735930673024806e-07,
      "loss": 0.4683,
      "step": 96
    },
    {
      "epoch": 4.85,
      "grad_norm": 0.232791468501091,
      "learning_rate": 4.917097454988584e-07,
      "loss": 0.4585,
      "step": 97
    },
    {
      "epoch": 4.9,
      "grad_norm": 0.24561770260334015,
      "learning_rate": 2.1863727812254653e-07,
      "loss": 0.4532,
      "step": 98
    },
    {
      "epoch": 4.95,
      "grad_norm": 0.22012515366077423,
      "learning_rate": 5.467426590739511e-08,
      "loss": 0.4229,
      "step": 99
    },
    {
      "epoch": 5.0,
      "grad_norm": 0.21987777948379517,
      "learning_rate": 0.0,
      "loss": 0.4361,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 1.2238732695148954e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}