{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.4945054945054945,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.9395878314971924,
      "learning_rate": 0.0,
      "loss": 3.0255,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.0909342765808105,
      "learning_rate": 4e-05,
      "loss": 3.2722,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 2.2211079597473145,
      "learning_rate": 8e-05,
      "loss": 3.0812,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.576534390449524,
      "learning_rate": 0.00012,
      "loss": 2.3772,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.288299560546875,
      "learning_rate": 0.00016,
      "loss": 2.7816,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.0976123809814453,
      "learning_rate": 0.0002,
      "loss": 1.8456,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.893791437149048,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.9392,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.5747392177581787,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.2524,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.9431101083755493,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2513,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.4205081462860107,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.5582,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.0894768238067627,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2454,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5371621251106262,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1853,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5113345384597778,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0215,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5522609353065491,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0844,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5567106604576111,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.28,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5977707505226135,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.3916,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.4428749680519104,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0281,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.39748522639274597,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.9917,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4602974057197571,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9289,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.46893274784088135,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0148,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3629504144191742,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0688,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3591447174549103,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1489,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.38264843821525574,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0042,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30332762002944946,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0645,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.36956873536109924,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8483,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.35823047161102295,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9212,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.31688058376312256,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.8109,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.34314897656440735,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.9747,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.39364388585090637,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0013,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30356618762016296,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.9765,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.34586668014526367,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.0919,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.32317039370536804,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.0067,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.44286298751831055,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9623,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3818933367729187,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0142,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.33253738284111023,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8074,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3408537805080414,
      "learning_rate": 0.00018669623059866964,
      "loss": 1.0326,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.40733590722084045,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0927,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.36787742376327515,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0677,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3505491614341736,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9553,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3779163062572479,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.921,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.3095817565917969,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.8463,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3786693513393402,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0101,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.2848946750164032,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1081,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2794632613658905,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8742,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.33480748534202576,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9947,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.37888801097869873,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9493,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.39233142137527466,
      "learning_rate": 0.00018181818181818183,
      "loss": 1.0789,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.2909736931324005,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0518,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.2732703983783722,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9017,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.30006876587867737,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.8561,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.34367501735687256,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0616,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.2993384003639221,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.7779,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3281186819076538,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.7872,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2709483206272125,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9384,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3327484428882599,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9123,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.32308903336524963,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0042,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2704257369041443,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.9699,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.28141987323760986,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8826,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.35217514634132385,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0742,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3242128789424896,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.8373,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.29047495126724243,
      "learning_rate": 0.000175609756097561,
      "loss": 0.885,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.30491581559181213,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0813,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.34017154574394226,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0067,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.2905332148075104,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8561,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3342151343822479,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9917,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.35391831398010254,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.1116,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.34148970246315,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9165,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.35057196021080017,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9318,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.3118966221809387,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9556,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.29268085956573486,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.8563,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.3315921127796173,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.1628,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.35345011949539185,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.944,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.2805996835231781,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8882,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.385016530752182,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.799,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.35097435116767883,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9332,
      "step": 75
    }
  ],
  "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": 1.2185620173078528e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}