{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.967741935483871,
  "eval_steps": 500,
  "global_step": 108,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018433179723502304,
      "grad_norm": 0.16578913731865466,
      "learning_rate": 5.000000000000001e-07,
      "loss": 0.5087,
      "step": 1
    },
    {
      "epoch": 0.03686635944700461,
      "grad_norm": 0.1722925976557175,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 0.4998,
      "step": 2
    },
    {
      "epoch": 0.055299539170506916,
      "grad_norm": 0.162572172422981,
      "learning_rate": 1.5e-06,
      "loss": 0.5098,
      "step": 3
    },
    {
      "epoch": 0.07373271889400922,
      "grad_norm": 0.15599834075161614,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.5042,
      "step": 4
    },
    {
      "epoch": 0.09216589861751152,
      "grad_norm": 0.12177646639247991,
      "learning_rate": 2.5e-06,
      "loss": 0.5071,
      "step": 5
    },
    {
      "epoch": 0.11059907834101383,
      "grad_norm": 0.1237088515175474,
      "learning_rate": 3e-06,
      "loss": 0.5017,
      "step": 6
    },
    {
      "epoch": 0.12903225806451613,
      "grad_norm": 0.16630602309614123,
      "learning_rate": 3.5000000000000004e-06,
      "loss": 0.5048,
      "step": 7
    },
    {
      "epoch": 0.14746543778801843,
      "grad_norm": 0.27010444722015153,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.5101,
      "step": 8
    },
    {
      "epoch": 0.16589861751152074,
      "grad_norm": 0.29479730440390195,
      "learning_rate": 4.5e-06,
      "loss": 0.5076,
      "step": 9
    },
    {
      "epoch": 0.18433179723502305,
      "grad_norm": 0.1759601385954911,
      "learning_rate": 5e-06,
      "loss": 0.5081,
      "step": 10
    },
    {
      "epoch": 0.20276497695852536,
      "grad_norm": 0.16293907501833735,
      "learning_rate": 5.500000000000001e-06,
      "loss": 0.5058,
      "step": 11
    },
    {
      "epoch": 0.22119815668202766,
      "grad_norm": 0.2104524729834747,
      "learning_rate": 6e-06,
      "loss": 0.5041,
      "step": 12
    },
    {
      "epoch": 0.23963133640552994,
      "grad_norm": 0.3439111046909263,
      "learning_rate": 6.5000000000000004e-06,
      "loss": 0.5028,
      "step": 13
    },
    {
      "epoch": 0.25806451612903225,
      "grad_norm": 0.1896879332677983,
      "learning_rate": 7.000000000000001e-06,
      "loss": 0.5063,
      "step": 14
    },
    {
      "epoch": 0.2764976958525346,
      "grad_norm": 0.16556412873045434,
      "learning_rate": 7.5e-06,
      "loss": 0.5008,
      "step": 15
    },
    {
      "epoch": 0.29493087557603687,
      "grad_norm": 0.18454200495588122,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.5025,
      "step": 16
    },
    {
      "epoch": 0.31336405529953915,
      "grad_norm": 0.19016194104381942,
      "learning_rate": 8.500000000000002e-06,
      "loss": 0.506,
      "step": 17
    },
    {
      "epoch": 0.3317972350230415,
      "grad_norm": 0.1756522900201089,
      "learning_rate": 9e-06,
      "loss": 0.5065,
      "step": 18
    },
    {
      "epoch": 0.35023041474654376,
      "grad_norm": 0.20347747202770788,
      "learning_rate": 9.5e-06,
      "loss": 0.5018,
      "step": 19
    },
    {
      "epoch": 0.3686635944700461,
      "grad_norm": 0.17281128792073364,
      "learning_rate": 1e-05,
      "loss": 0.4985,
      "step": 20
    },
    {
      "epoch": 0.3870967741935484,
      "grad_norm": 0.16864344707112827,
      "learning_rate": 1.05e-05,
      "loss": 0.5001,
      "step": 21
    },
    {
      "epoch": 0.4055299539170507,
      "grad_norm": 0.180006594373567,
      "learning_rate": 1.1000000000000001e-05,
      "loss": 0.4957,
      "step": 22
    },
    {
      "epoch": 0.423963133640553,
      "grad_norm": 0.22019846104588628,
      "learning_rate": 1.1500000000000002e-05,
      "loss": 0.4994,
      "step": 23
    },
    {
      "epoch": 0.4423963133640553,
      "grad_norm": 0.29450471197920014,
      "learning_rate": 1.2e-05,
      "loss": 0.4975,
      "step": 24
    },
    {
      "epoch": 0.4608294930875576,
      "grad_norm": 0.3531458750461238,
      "learning_rate": 1.25e-05,
      "loss": 0.5024,
      "step": 25
    },
    {
      "epoch": 0.4792626728110599,
      "grad_norm": 0.2704221537114728,
      "learning_rate": 1.3000000000000001e-05,
      "loss": 0.5036,
      "step": 26
    },
    {
      "epoch": 0.4976958525345622,
      "grad_norm": 0.21807981567443038,
      "learning_rate": 1.3500000000000001e-05,
      "loss": 0.4963,
      "step": 27
    },
    {
      "epoch": 0.5161290322580645,
      "grad_norm": 0.2537511686453976,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.5014,
      "step": 28
    },
    {
      "epoch": 0.5345622119815668,
      "grad_norm": 0.27282609851480566,
      "learning_rate": 1.45e-05,
      "loss": 0.4952,
      "step": 29
    },
    {
      "epoch": 0.5529953917050692,
      "grad_norm": 0.1811493216272178,
      "learning_rate": 1.5e-05,
      "loss": 0.4945,
      "step": 30
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.2154826922529899,
      "learning_rate": 1.55e-05,
      "loss": 0.4927,
      "step": 31
    },
    {
      "epoch": 0.5898617511520737,
      "grad_norm": 0.27147274813275624,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.4955,
      "step": 32
    },
    {
      "epoch": 0.6082949308755761,
      "grad_norm": 0.3148285453024877,
      "learning_rate": 1.65e-05,
      "loss": 0.4944,
      "step": 33
    },
    {
      "epoch": 0.6267281105990783,
      "grad_norm": 0.34859491123867103,
      "learning_rate": 1.7000000000000003e-05,
      "loss": 0.4905,
      "step": 34
    },
    {
      "epoch": 0.6451612903225806,
      "grad_norm": 0.42577058166978227,
      "learning_rate": 1.75e-05,
      "loss": 0.4913,
      "step": 35
    },
    {
      "epoch": 0.663594470046083,
      "grad_norm": 0.4904668611850979,
      "learning_rate": 1.8e-05,
      "loss": 0.496,
      "step": 36
    },
    {
      "epoch": 0.6820276497695853,
      "grad_norm": 0.45085408352277095,
      "learning_rate": 1.85e-05,
      "loss": 0.497,
      "step": 37
    },
    {
      "epoch": 0.7004608294930875,
      "grad_norm": 0.3728335955961086,
      "learning_rate": 1.9e-05,
      "loss": 0.4924,
      "step": 38
    },
    {
      "epoch": 0.7188940092165899,
      "grad_norm": 0.31712845935435935,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.4971,
      "step": 39
    },
    {
      "epoch": 0.7373271889400922,
      "grad_norm": 0.35626608232389995,
      "learning_rate": 2e-05,
      "loss": 0.4937,
      "step": 40
    },
    {
      "epoch": 0.7557603686635944,
      "grad_norm": 0.36587367082049105,
      "learning_rate": 2.05e-05,
      "loss": 0.4879,
      "step": 41
    },
    {
      "epoch": 0.7741935483870968,
      "grad_norm": 0.34644598131926585,
      "learning_rate": 2.1e-05,
      "loss": 0.4978,
      "step": 42
    },
    {
      "epoch": 0.7926267281105991,
      "grad_norm": 0.3590839478187489,
      "learning_rate": 2.15e-05,
      "loss": 0.4933,
      "step": 43
    },
    {
      "epoch": 0.8110599078341014,
      "grad_norm": 0.4208361801021048,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.4945,
      "step": 44
    },
    {
      "epoch": 0.8294930875576036,
      "grad_norm": 0.4476283919996847,
      "learning_rate": 2.25e-05,
      "loss": 0.4892,
      "step": 45
    },
    {
      "epoch": 0.847926267281106,
      "grad_norm": 0.36958185599300014,
      "learning_rate": 2.3000000000000003e-05,
      "loss": 0.4949,
      "step": 46
    },
    {
      "epoch": 0.8663594470046083,
      "grad_norm": 0.2911820871345684,
      "learning_rate": 2.35e-05,
      "loss": 0.4909,
      "step": 47
    },
    {
      "epoch": 0.8847926267281107,
      "grad_norm": 0.30858968380534924,
      "learning_rate": 2.4e-05,
      "loss": 0.4885,
      "step": 48
    },
    {
      "epoch": 0.9032258064516129,
      "grad_norm": 0.29278185745501223,
      "learning_rate": 2.45e-05,
      "loss": 0.4924,
      "step": 49
    },
    {
      "epoch": 0.9216589861751152,
      "grad_norm": 0.2544353522559892,
      "learning_rate": 2.5e-05,
      "loss": 0.4875,
      "step": 50
    },
    {
      "epoch": 0.9400921658986175,
      "grad_norm": 0.2715960030565017,
      "learning_rate": 2.5500000000000003e-05,
      "loss": 0.4868,
      "step": 51
    },
    {
      "epoch": 0.9585253456221198,
      "grad_norm": 0.3073179286108365,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.4889,
      "step": 52
    },
    {
      "epoch": 0.9769585253456221,
      "grad_norm": 0.3371193687132362,
      "learning_rate": 2.6500000000000004e-05,
      "loss": 0.4898,
      "step": 53
    },
    {
      "epoch": 0.9953917050691244,
      "grad_norm": 0.33074577044400744,
      "learning_rate": 2.7000000000000002e-05,
      "loss": 0.4841,
      "step": 54
    },
    {
      "epoch": 1.0138248847926268,
      "grad_norm": 0.3297515468133034,
      "learning_rate": 2.7500000000000004e-05,
      "loss": 0.4884,
      "step": 55
    },
    {
      "epoch": 1.0092165898617511,
      "grad_norm": 0.4029640463193266,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.459,
      "step": 56
    },
    {
      "epoch": 1.0276497695852536,
      "grad_norm": 0.4940605439662155,
      "learning_rate": 2.8499999999999998e-05,
      "loss": 0.4237,
      "step": 57
    },
    {
      "epoch": 1.0460829493087558,
      "grad_norm": 0.6088906714727877,
      "learning_rate": 2.9e-05,
      "loss": 0.431,
      "step": 58
    },
    {
      "epoch": 1.064516129032258,
      "grad_norm": 0.7906992222694273,
      "learning_rate": 2.95e-05,
      "loss": 0.4386,
      "step": 59
    },
    {
      "epoch": 1.0829493087557605,
      "grad_norm": 0.8776764408330847,
      "learning_rate": 3e-05,
      "loss": 0.4377,
      "step": 60
    },
    {
      "epoch": 1.1013824884792627,
      "grad_norm": 0.8163334281126426,
      "learning_rate": 3.05e-05,
      "loss": 0.4356,
      "step": 61
    },
    {
      "epoch": 1.119815668202765,
      "grad_norm": 0.8591188461532855,
      "learning_rate": 3.1e-05,
      "loss": 0.4343,
      "step": 62
    },
    {
      "epoch": 1.1382488479262673,
      "grad_norm": 0.7423520884399006,
      "learning_rate": 3.15e-05,
      "loss": 0.4396,
      "step": 63
    },
    {
      "epoch": 1.1566820276497696,
      "grad_norm": 0.6559077625993845,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.4393,
      "step": 64
    },
    {
      "epoch": 1.1751152073732718,
      "grad_norm": 0.5192220132180586,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 0.4268,
      "step": 65
    },
    {
      "epoch": 1.1935483870967742,
      "grad_norm": 0.4721316464238954,
      "learning_rate": 3.3e-05,
      "loss": 0.4299,
      "step": 66
    },
    {
      "epoch": 1.2119815668202765,
      "grad_norm": 0.37162261772983884,
      "learning_rate": 3.35e-05,
      "loss": 0.428,
      "step": 67
    },
    {
      "epoch": 1.230414746543779,
      "grad_norm": 0.390597086956948,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.4242,
      "step": 68
    },
    {
      "epoch": 1.2488479262672811,
      "grad_norm": 0.3667364763504883,
      "learning_rate": 3.45e-05,
      "loss": 0.4308,
      "step": 69
    },
    {
      "epoch": 1.2672811059907834,
      "grad_norm": 0.4413076637014959,
      "learning_rate": 3.5e-05,
      "loss": 0.4175,
      "step": 70
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.3828593150648835,
      "learning_rate": 3.55e-05,
      "loss": 0.4255,
      "step": 71
    },
    {
      "epoch": 1.304147465437788,
      "grad_norm": 0.3422241428662135,
      "learning_rate": 3.6e-05,
      "loss": 0.4206,
      "step": 72
    },
    {
      "epoch": 1.3225806451612903,
      "grad_norm": 0.419503312255047,
      "learning_rate": 3.65e-05,
      "loss": 0.4216,
      "step": 73
    },
    {
      "epoch": 1.3410138248847927,
      "grad_norm": 0.39398530533795917,
      "learning_rate": 3.7e-05,
      "loss": 0.4186,
      "step": 74
    },
    {
      "epoch": 1.359447004608295,
      "grad_norm": 0.31275590078306537,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 0.4192,
      "step": 75
    },
    {
      "epoch": 1.3778801843317972,
      "grad_norm": 0.283726761659876,
      "learning_rate": 3.8e-05,
      "loss": 0.4134,
      "step": 76
    },
    {
      "epoch": 1.3963133640552996,
      "grad_norm": 0.2795686696921213,
      "learning_rate": 3.85e-05,
      "loss": 0.4201,
      "step": 77
    },
    {
      "epoch": 1.4147465437788018,
      "grad_norm": 0.2573708572632348,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.4174,
      "step": 78
    },
    {
      "epoch": 1.4331797235023043,
      "grad_norm": 0.26179179902269994,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.4186,
      "step": 79
    },
    {
      "epoch": 1.4516129032258065,
      "grad_norm": 0.25383918207396766,
      "learning_rate": 4e-05,
      "loss": 0.4115,
      "step": 80
    },
    {
      "epoch": 1.4700460829493087,
      "grad_norm": 0.26752441715146946,
      "learning_rate": 4.05e-05,
      "loss": 0.4164,
      "step": 81
    },
    {
      "epoch": 1.488479262672811,
      "grad_norm": 0.3298159183943398,
      "learning_rate": 4.1e-05,
      "loss": 0.4199,
      "step": 82
    },
    {
      "epoch": 1.5069124423963134,
      "grad_norm": 0.38660808750412323,
      "learning_rate": 4.15e-05,
      "loss": 0.417,
      "step": 83
    },
    {
      "epoch": 1.5253456221198156,
      "grad_norm": 0.485211204279941,
      "learning_rate": 4.2e-05,
      "loss": 0.4193,
      "step": 84
    },
    {
      "epoch": 1.543778801843318,
      "grad_norm": 0.6255151017178746,
      "learning_rate": 4.25e-05,
      "loss": 0.4264,
      "step": 85
    },
    {
      "epoch": 1.5622119815668203,
      "grad_norm": 0.7700118743780004,
      "learning_rate": 4.3e-05,
      "loss": 0.4287,
      "step": 86
    },
    {
      "epoch": 1.5806451612903225,
      "grad_norm": 0.6615400048001224,
      "learning_rate": 4.35e-05,
      "loss": 0.4277,
      "step": 87
    },
    {
      "epoch": 1.5990783410138247,
      "grad_norm": 0.4437937981053966,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.4232,
      "step": 88
    },
    {
      "epoch": 1.6175115207373272,
      "grad_norm": 0.567061608533075,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.4258,
      "step": 89
    },
    {
      "epoch": 1.6359447004608296,
      "grad_norm": 0.4918052804723442,
      "learning_rate": 4.5e-05,
      "loss": 0.4228,
      "step": 90
    },
    {
      "epoch": 1.6543778801843319,
      "grad_norm": 0.496826066236439,
      "learning_rate": 4.55e-05,
      "loss": 0.4229,
      "step": 91
    },
    {
      "epoch": 1.672811059907834,
      "grad_norm": 0.4731592011924632,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.4215,
      "step": 92
    },
    {
      "epoch": 1.6912442396313363,
      "grad_norm": 0.36878471669976337,
      "learning_rate": 4.6500000000000005e-05,
      "loss": 0.4193,
      "step": 93
    },
    {
      "epoch": 1.7096774193548387,
      "grad_norm": 0.42898764923079724,
      "learning_rate": 4.7e-05,
      "loss": 0.416,
      "step": 94
    },
    {
      "epoch": 1.728110599078341,
      "grad_norm": 0.3959738727253371,
      "learning_rate": 4.75e-05,
      "loss": 0.4186,
      "step": 95
    },
    {
      "epoch": 1.7465437788018434,
      "grad_norm": 0.3284621544244543,
      "learning_rate": 4.8e-05,
      "loss": 0.4159,
      "step": 96
    },
    {
      "epoch": 1.7649769585253456,
      "grad_norm": 0.3687303178188624,
      "learning_rate": 4.85e-05,
      "loss": 0.4177,
      "step": 97
    },
    {
      "epoch": 1.7834101382488479,
      "grad_norm": 0.36139089440724775,
      "learning_rate": 4.9e-05,
      "loss": 0.4198,
      "step": 98
    },
    {
      "epoch": 1.80184331797235,
      "grad_norm": 0.4663478454832621,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.4264,
      "step": 99
    },
    {
      "epoch": 1.8202764976958525,
      "grad_norm": 0.5056372967287713,
      "learning_rate": 5e-05,
      "loss": 0.4217,
      "step": 100
    },
    {
      "epoch": 1.838709677419355,
      "grad_norm": 0.5324522359135441,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 0.4216,
      "step": 101
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.4621746495598758,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.4225,
      "step": 102
    },
    {
      "epoch": 1.8755760368663594,
      "grad_norm": 0.3415822814753156,
      "learning_rate": 3.456708580912725e-05,
      "loss": 0.4187,
      "step": 103
    },
    {
      "epoch": 1.8940092165898617,
      "grad_norm": 0.30176145892972905,
      "learning_rate": 2.5e-05,
      "loss": 0.4175,
      "step": 104
    },
    {
      "epoch": 1.912442396313364,
      "grad_norm": 0.2511920801182371,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 0.4164,
      "step": 105
    },
    {
      "epoch": 1.9308755760368663,
      "grad_norm": 0.21487586752475282,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.4144,
      "step": 106
    },
    {
      "epoch": 1.9493087557603688,
      "grad_norm": 0.1707899105775025,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.4152,
      "step": 107
    },
    {
      "epoch": 1.967741935483871,
      "grad_norm": 0.16592415069318403,
      "learning_rate": 0.0,
      "loss": 0.4088,
      "step": 108
    }
  ],
  "logging_steps": 1,
  "max_steps": 108,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 6,
  "total_flos": 1.1787401428992e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}