{
  "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": 1.3645844459533691,
      "learning_rate": 0.0,
      "loss": 2.5037,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.660995602607727,
      "learning_rate": 4e-05,
      "loss": 2.6031,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6392755508422852,
      "learning_rate": 8e-05,
      "loss": 2.9118,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.710063099861145,
      "learning_rate": 0.00012,
      "loss": 2.7714,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 1.6210428476333618,
      "learning_rate": 0.00016,
      "loss": 2.1514,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.3645424842834473,
      "learning_rate": 0.0002,
      "loss": 2.5283,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.700213670730591,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7241,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.8606327772140503,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.2173,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.842186450958252,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3338,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.0317293405532837,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.5118,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.8248395919799805,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.0751,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5275245308876038,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.0938,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.45801183581352234,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1561,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5454519987106323,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.2234,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.46795782446861267,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.126,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5097053050994873,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.8651,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.39326727390289307,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.102,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4550538659095764,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.2287,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.36811986565589905,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9848,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.36873698234558105,
      "learning_rate": 0.00019379157427937917,
      "loss": 1.0985,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.40543392300605774,
      "learning_rate": 0.00019334811529933484,
      "loss": 1.0776,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3196291923522949,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.1498,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.31376779079437256,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.0388,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.2825721502304077,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0112,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.41585949063301086,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.8182,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.30083444714546204,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.8058,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3621577322483063,
      "learning_rate": 0.00019068736141906876,
      "loss": 1.2748,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2544698119163513,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.8783,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3715449869632721,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.1229,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.39372724294662476,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1051,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3777405917644501,
      "learning_rate": 0.00018891352549889136,
      "loss": 1.2908,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.40752673149108887,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.8454,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3653320074081421,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0931,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.31746864318847656,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.8643,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3374824821949005,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.8283,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.26290443539619446,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9068,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.24013353884220123,
      "learning_rate": 0.00018625277161862528,
      "loss": 0.9357,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.26812735199928284,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.8113,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.2499343603849411,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.843,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.28877875208854675,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9069,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.33010339736938477,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.1674,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.31647464632987976,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.0174,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.31002527475357056,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.1348,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3115866482257843,
      "learning_rate": 0.00018314855875831487,
      "loss": 0.8801,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.304898202419281,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.7553,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.28940340876579285,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9455,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3560061752796173,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9425,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.3070710003376007,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9398,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.36494898796081543,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.0877,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.28735437989234924,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9873,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3916163146495819,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0092,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.33982348442077637,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9233,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.34739887714385986,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.201,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.2715175151824951,
      "learning_rate": 0.0001787139689578714,
      "loss": 0.9341,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.27719396352767944,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.1086,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.3649531900882721,
      "learning_rate": 0.00017782705099778271,
      "loss": 0.9422,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.27733761072158813,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0024,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3377635180950165,
      "learning_rate": 0.000176940133037694,
      "loss": 1.0302,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.3234331011772156,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.8961,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.4501403272151947,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.0076,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.3447868824005127,
      "learning_rate": 0.000175609756097561,
      "loss": 0.9882,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.25949928164482117,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8351,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.30628013610839844,
      "learning_rate": 0.0001747228381374723,
      "loss": 1.0555,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.417680561542511,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.261,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.32843342423439026,
      "learning_rate": 0.0001738359201773836,
      "loss": 1.1574,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.37481415271759033,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.1188,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.27844470739364624,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9118,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.3192802667617798,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9093,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2857853174209595,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.9354,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.2837400436401367,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.895,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.45861223340034485,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.0971,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.31916752457618713,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.9987,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.32653743028640747,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.9662,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2894360423088074,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.0653,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.3567565679550171,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.9241,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.256074994802475,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.7865,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.33665013313293457,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.041,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2950928807258606,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9518,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.264356791973114,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8075,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.3302100896835327,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.8485,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.2833380401134491,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.7926,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.3453841507434845,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.971,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.2654123604297638,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.1499,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.31106314063072205,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.0009,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.367225706577301,
      "learning_rate": 0.00016496674057649667,
      "loss": 1.0477,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3222266435623169,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.9234,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.29851892590522766,
      "learning_rate": 0.000164079822616408,
      "loss": 0.935,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.22740495204925537,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8715,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.34969761967658997,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9699,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.264044851064682,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.8414,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.3013779819011688,
      "learning_rate": 0.0001623059866962306,
      "loss": 1.0331,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.2941848933696747,
      "learning_rate": 0.00016186252771618626,
      "loss": 1.1354,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.2865702211856842,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.9942,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.3316570520401001,
      "learning_rate": 0.00016097560975609758,
      "loss": 1.0279,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.36422255635261536,
      "learning_rate": 0.00016053215077605322,
      "loss": 1.0983,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.35495316982269287,
      "learning_rate": 0.00016008869179600887,
      "loss": 0.9114,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.3313552141189575,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.7726,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.3033399283885956,
      "learning_rate": 0.00015920177383592018,
      "loss": 0.9066,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.2781226933002472,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.7253,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.27466264367103577,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.7809,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.2644181251525879,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8201,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.28048309683799744,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8246,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.33915644884109497,
      "learning_rate": 0.00015698447893569846,
      "loss": 1.0543,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.2994322180747986,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.988,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.3395415246486664,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.1211,
      "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": 1.77402390933504e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}