{
  "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": 1.324825406074524,
      "learning_rate": 0.0,
      "loss": 2.251,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.359919548034668,
      "learning_rate": 4e-05,
      "loss": 2.3496,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1708112955093384,
      "learning_rate": 8e-05,
      "loss": 2.0811,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.3121654987335205,
      "learning_rate": 0.00012,
      "loss": 2.5163,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.736699104309082,
      "learning_rate": 0.00016,
      "loss": 2.2536,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.6031162738800049,
      "learning_rate": 0.0002,
      "loss": 1.9244,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.7248623371124268,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.981,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.186155080795288,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.4323,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.0301684141159058,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.1934,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.7665079236030579,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.0643,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9783205986022949,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.3316,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.6272598505020142,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1988,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.3676067292690277,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.9774,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.39943814277648926,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.9461,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.36930710077285767,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0264,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.2694442868232727,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.9453,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.29302021861076355,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.0611,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.31116580963134766,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.839,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.29176589846611023,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9196,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3165068030357361,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9196,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3522554636001587,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0832,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.34008151292800903,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.9705,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.2566126883029938,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.9122,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.29866355657577515,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.8918,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.2955140471458435,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.1007,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.33036312460899353,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9752,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.2844546139240265,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9755,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3072405457496643,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0727,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.27163660526275635,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9208,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3229711353778839,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0546,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.23488745093345642,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8587,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.21555615961551666,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.7837,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.23712514340877533,
      "learning_rate": 0.00018802660753880268,
      "loss": 0.9478,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2658460736274719,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.034,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.2315426766872406,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.0614,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.2795284688472748,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.936,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.23665310442447662,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0365,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.29602324962615967,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.031,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.22743946313858032,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.8417,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3170803189277649,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.0181,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.30657052993774414,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0949,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.2403457909822464,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0674,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30654340982437134,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.2225,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2646230161190033,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8863,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.19537745416164398,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.8136,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.2946692407131195,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.7739,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.25506192445755005,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.917,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.25431299209594727,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.8607,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.25379678606987,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.9536,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3052731156349182,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9212,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.29013338685035706,
      "learning_rate": 0.00018004434589800444,
      "loss": 0.9172,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.26132503151893616,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9132,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.25556033849716187,
      "learning_rate": 0.00017915742793791575,
      "loss": 0.8975,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.24604447185993195,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9775,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3651309311389923,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.0722,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.29941031336784363,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0118,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.22141927480697632,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.7191,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.24013017117977142,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8956,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.22057652473449707,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.7262,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.2441413700580597,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0653,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.29345762729644775,
      "learning_rate": 0.000175609756097561,
      "loss": 1.045,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2953290045261383,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.0812,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.2912586033344269,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0766,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.23332780599594116,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.8158,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.2499706894159317,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.8437,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.27131178975105286,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0566,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.24329422414302826,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9095,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.22750143706798553,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.7947,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2624737620353699,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9386,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2711818516254425,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.9837,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.27666857838630676,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.8833,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3417559266090393,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9458,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.22324572503566742,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.8771,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2463648021221161,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.9063,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.26554247736930847,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7789,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.2468937337398529,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.8174,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.25815922021865845,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9862,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.31987327337265015,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9373,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.2607921361923218,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.868,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.256076455116272,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.964,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.30199241638183594,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.9589,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.25212472677230835,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.7611,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.28898489475250244,
      "learning_rate": 0.00016585365853658536,
      "loss": 0.8258,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.2534230947494507,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.9872,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34786713123321533,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8787,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.246382936835289,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9206,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.24042193591594696,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8852,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.2742517590522766,
      "learning_rate": 0.00016363636363636366,
      "loss": 1.0141,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.35837244987487793,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8341,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34418734908103943,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.983,
      "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": 1.6969868980568064e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}