{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6923076923076923,
  "eval_steps": 500,
  "global_step": 105,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.02959144115448,
      "learning_rate": 0.0,
      "loss": 3.3348,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0243064165115356,
      "learning_rate": 4e-05,
      "loss": 3.3843,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9533873796463013,
      "learning_rate": 8e-05,
      "loss": 3.1602,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.3778162002563477,
      "learning_rate": 0.00012,
      "loss": 3.8548,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.5720551013946533,
      "learning_rate": 0.00016,
      "loss": 3.334,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.0702953338623047,
      "learning_rate": 0.0002,
      "loss": 3.2436,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 1.883508563041687,
      "learning_rate": 0.00019955654101995565,
      "loss": 2.4118,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8991221189498901,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.7996,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.943290114402771,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.7992,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.1848249435424805,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3218,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8290153741836548,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.1483,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.782597541809082,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1466,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 1.070041537284851,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0435,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.7890101671218872,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1189,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.6797720789909363,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.9294,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.6561483144760132,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8717,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.6154541969299316,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.9475,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6936250925064087,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.1112,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4830031096935272,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.8719,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4977757930755615,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.8456,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.4251507520675659,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.7946,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.5000141263008118,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.9003,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5055630803108215,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.8483,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.5189692378044128,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.862,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.39381036162376404,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.73,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.4727248549461365,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9574,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.5471789836883545,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.8291,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.4908490777015686,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.7855,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.5352988243103027,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.8019,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.4222325384616852,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7782,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.5250545740127563,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.827,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.5112847685813904,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7717,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.45085787773132324,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.8548,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.5169785618782043,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8469,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.4831181466579437,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.7138,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.4298362731933594,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.6416,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.4677696228027344,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.8296,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.4513629376888275,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.6803,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.4796628952026367,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.7778,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.4168303906917572,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.748,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3913823962211609,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8508,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.46302542090415955,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.86,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.43823087215423584,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.7062,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.4874539375305176,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.7632,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.44593605399131775,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8815,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.4195469915866852,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7796,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.40345215797424316,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.6468,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.4226957857608795,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.6274,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.477471262216568,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.7629,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.39429357647895813,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.6709,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.4581214189529419,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.7036,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.4935621917247772,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.6878,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.45704221725463867,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7126,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.4570856988430023,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.7569,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.4568769037723541,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.7162,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.4904540181159973,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.7308,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.4313798248767853,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.635,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.5561969876289368,
      "learning_rate": 0.000176940133037694,
      "loss": 0.7838,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.44863128662109375,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.6366,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.4197455048561096,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.7589,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.4661950170993805,
      "learning_rate": 0.000175609756097561,
      "loss": 0.725,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.46837183833122253,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.64,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.5886682868003845,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.5071,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.5030215978622437,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.692,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.5501147508621216,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8112,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.4744016230106354,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.6571,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.4610467553138733,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.6737,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.495379239320755,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7577,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4832289516925812,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.6387,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.5150049924850464,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8346,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.4854123294353485,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.6864,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.45552781224250793,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.6789,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.4643484652042389,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.6516,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.4445684254169464,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.6762,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.5563467741012573,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7624,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.4668287932872772,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.5379,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.424448698759079,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.6594,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.47027847170829773,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.6288,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.4704686403274536,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.7025,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.5712776184082031,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.6923,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.5098185539245605,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.6952,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.5409852266311646,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.6023,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.6706210374832153,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.713,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.34992656111717224,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.7375,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.6524062156677246,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.739,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.5203568935394287,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.7482,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.6416592597961426,
      "learning_rate": 0.000164079822616408,
      "loss": 0.7033,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.4666348695755005,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.6811,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.6599462628364563,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.7908,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.551964521408081,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.6226,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.429592490196228,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.6602,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.5001062750816345,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.6884,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.4265173375606537,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.6613,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.4387926757335663,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.6829,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.5375656485557556,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.6584,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.511247992515564,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.6725,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.49439311027526855,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7958,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.521442174911499,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.6591,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.5001063942909241,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7915,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.741524338722229,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.6201,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.49745646119117737,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.915,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.5976807475090027,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.7476,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.47543030977249146,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.8067,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.5175777673721313,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.618,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.5875190496444702,
      "learning_rate": 0.00015609756097560978,
      "loss": 0.6178,
      "step": 105
    }
  ],
  "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": 4.217460027385651e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}