{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5934065934065934,
  "eval_steps": 500,
  "global_step": 90,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8822625875473022,
      "learning_rate": 0.0,
      "loss": 2.9966,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.1069581508636475,
      "learning_rate": 4e-05,
      "loss": 2.9598,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.8758227229118347,
      "learning_rate": 8e-05,
      "loss": 2.5775,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.0401133298873901,
      "learning_rate": 0.00012,
      "loss": 2.6196,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.4041666984558105,
      "learning_rate": 0.00016,
      "loss": 3.1798,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.4210084676742554,
      "learning_rate": 0.0002,
      "loss": 2.0834,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.1845953464508057,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.3524,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.3485188484191895,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.616,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0533819198608398,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2391,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.1041414737701416,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0831,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.7204957604408264,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8896,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7176511287689209,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8995,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.7679543495178223,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.7737,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.8583915829658508,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.8345,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5992399454116821,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.7105,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5483726859092712,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7893,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.47341662645339966,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.8783,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4923449456691742,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.5529,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.382350355386734,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.6698,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.43962135910987854,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.6906,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.6100013256072998,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7102,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.4505807161331177,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.5965,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.420966774225235,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.8076,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.37792259454727173,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.4851,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.39667177200317383,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.7452,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.35318464040756226,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.7378,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.34349656105041504,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6639,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.37496012449264526,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.5393,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.42517000436782837,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.6226,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.365597128868103,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.5503,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4194570481777191,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.6564,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.400821328163147,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7257,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.4243015646934509,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.5831,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.4274579584598541,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.6801,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.30914393067359924,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.4985,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.36418190598487854,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.506,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.5366491079330444,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.6998,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.40732792019844055,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6035,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.41157761216163635,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.5741,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.49116623401641846,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.5644,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.43378788232803345,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.5459,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.43929198384284973,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.4644,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.40316739678382874,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.6401,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.41275328397750854,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.601,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2872825264930725,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.4375,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4530083239078522,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7684,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.31746530532836914,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.5948,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.35115814208984375,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6928,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.29176679253578186,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.5716,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.356320858001709,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.5595,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.33391836285591125,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.5823,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.35161083936691284,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.5482,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.31787368655204773,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.5471,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2908938527107239,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.5348,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.34024009108543396,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.4426,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.40695953369140625,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.5771,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.49275121092796326,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.544,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.4099092483520508,
      "learning_rate": 0.000176940133037694,
      "loss": 0.5028,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.31285232305526733,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.5137,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.414304256439209,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.4803,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4016311466693878,
      "learning_rate": 0.000175609756097561,
      "loss": 0.5934,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.30074217915534973,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.461,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3320770859718323,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.5756,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.37848159670829773,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.6247,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3719041347503662,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.5425,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.3609648644924164,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.484,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.32436180114746094,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.5081,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.33831897377967834,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.5861,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.26558148860931396,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6159,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.32884278893470764,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.5497,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.34436213970184326,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.4994,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3457243740558624,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6952,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.310139536857605,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.5439,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.417996346950531,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.5534,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35336464643478394,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.4557,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.3493141233921051,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5587,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.38658949732780457,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.64,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.4228934049606323,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.7367,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.38229817152023315,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.5983,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3111512362957001,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.601,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3454195261001587,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.4988,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3082880675792694,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.3354,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3996518552303314,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.5782,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3453790843486786,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.604,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3558626174926758,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.4868,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3380248248577118,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.6232,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.3425062298774719,
      "learning_rate": 0.000164079822616408,
      "loss": 0.6562,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.31318148970603943,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.4692,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3718196153640747,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7078,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34966057538986206,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.5526,
      "step": 90
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.992823349569331e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}