{
  "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": 1.3236569166183472,
      "learning_rate": 0.0,
      "loss": 2.4901,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 2.2663447856903076,
      "learning_rate": 4e-05,
      "loss": 3.0812,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6167106628417969,
      "learning_rate": 8e-05,
      "loss": 2.9177,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.5226534605026245,
      "learning_rate": 0.00012,
      "loss": 2.503,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.168428897857666,
      "learning_rate": 0.00016,
      "loss": 2.8535,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 1.97528076171875,
      "learning_rate": 0.0002,
      "loss": 1.7334,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.583857297897339,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.8924,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 1.9402282238006592,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.273,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.030725359916687,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.3303,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 1.3545081615447998,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.3464,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.9670407176017761,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.2525,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.7464919090270996,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.1564,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5867994427680969,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.0917,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6113730669021606,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.1594,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4500170052051544,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.0796,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.5538170337677002,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.1618,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.45620211958885193,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.1508,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4772197902202606,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.061,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.533805787563324,
      "learning_rate": 0.00019423503325942352,
      "loss": 1.1468,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.4162095785140991,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.9207,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.30745798349380493,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.8223,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.29989153146743774,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0635,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.4353378415107727,
      "learning_rate": 0.00019246119733924613,
      "loss": 1.1136,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.30720826983451843,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0796,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.30275797843933105,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.9368,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3034687042236328,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9616,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.3129018545150757,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9762,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.32465481758117676,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.025,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3805822730064392,
      "learning_rate": 0.00018980044345898005,
      "loss": 1.0966,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30361831188201904,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.1199,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3538556694984436,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.8606,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.4855636954307556,
      "learning_rate": 0.00018847006651884703,
      "loss": 1.3002,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.36801108717918396,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.1441,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3000083565711975,
      "learning_rate": 0.00018758314855875832,
      "loss": 1.0868,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.35833317041397095,
      "learning_rate": 0.00018713968957871397,
      "loss": 0.9805,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.26648440957069397,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.9186,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.29637497663497925,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0078,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3601683974266052,
      "learning_rate": 0.00018580931263858095,
      "loss": 1.0045,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3521329462528229,
      "learning_rate": 0.0001853658536585366,
      "loss": 1.0004,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.2667492628097534,
      "learning_rate": 0.00018492239467849224,
      "loss": 0.9271,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.33176255226135254,
      "learning_rate": 0.0001844789356984479,
      "loss": 1.0735,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.3940621018409729,
      "learning_rate": 0.00018403547671840356,
      "loss": 1.1447,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3026503324508667,
      "learning_rate": 0.0001835920177383592,
      "loss": 0.8857,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.2967509627342224,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0834,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2822628319263458,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9712,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.36211535334587097,
      "learning_rate": 0.00018226164079822616,
      "loss": 1.0312,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.3197602331638336,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9411,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.34601065516471863,
      "learning_rate": 0.00018137472283813748,
      "loss": 0.9466,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3059934973716736,
      "learning_rate": 0.00018093126385809312,
      "loss": 0.8534,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3049042820930481,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9564,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.3513273298740387,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0429,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.33669522404670715,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.9706,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3956065773963928,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.0505,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.31517383456230164,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.0469,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.36682212352752686,
      "learning_rate": 0.00017827050997782707,
      "loss": 0.9408,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.38366109132766724,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.1865,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.30710846185684204,
      "learning_rate": 0.00017738359201773839,
      "loss": 1.0216,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.29654064774513245,
      "learning_rate": 0.000176940133037694,
      "loss": 0.9368,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.43266645073890686,
      "learning_rate": 0.00017649667405764967,
      "loss": 0.9399,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.3399896025657654,
      "learning_rate": 0.00017605321507760532,
      "loss": 1.2272,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.35805898904800415,
      "learning_rate": 0.000175609756097561,
      "loss": 1.1291,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.3398084044456482,
      "learning_rate": 0.00017516629711751663,
      "loss": 1.062,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.3010111451148987,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.9908,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.3359769284725189,
      "learning_rate": 0.00017427937915742792,
      "loss": 1.094,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.35044530034065247,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.9933,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.4499974548816681,
      "learning_rate": 0.00017339246119733924,
      "loss": 1.0979,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2390085607767105,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.7452,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2939722239971161,
      "learning_rate": 0.00017250554323725056,
      "loss": 1.1464,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.4215264916419983,
      "learning_rate": 0.00017206208425720623,
      "loss": 1.0169,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.24245759844779968,
      "learning_rate": 0.00017161862527716187,
      "loss": 0.7183,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.33143526315689087,
      "learning_rate": 0.00017117516629711752,
      "loss": 1.1435,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3057692348957062,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7141,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.3185351490974426,
      "learning_rate": 0.00017028824833702883,
      "loss": 0.9677,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.3105548322200775,
      "learning_rate": 0.0001698447893569845,
      "loss": 1.0319,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.27544498443603516,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.8509,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.24930939078330994,
      "learning_rate": 0.00016895787139689582,
      "loss": 0.9795,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.326751172542572,
      "learning_rate": 0.00016851441241685144,
      "loss": 1.0334,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2782577574253082,
      "learning_rate": 0.0001680709534368071,
      "loss": 0.9029,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.29126885533332825,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.9306,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.25332754850387573,
      "learning_rate": 0.00016718403547671842,
      "loss": 0.9057,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.3294142782688141,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.7615,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.39348527789115906,
      "learning_rate": 0.00016629711751662974,
      "loss": 0.8525,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.3311331868171692,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0504,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.32208502292633057,
      "learning_rate": 0.00016541019955654103,
      "loss": 1.043,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.3057066798210144,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.9153,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3061386048793793,
      "learning_rate": 0.00016452328159645234,
      "loss": 0.8475,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.34367796778678894,
      "learning_rate": 0.000164079822616408,
      "loss": 1.1397,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.3496788442134857,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.9111,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.34243008494377136,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.9765,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.4083498418331146,
      "learning_rate": 0.00016274944567627495,
      "loss": 1.09,
      "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": 1.4353851159724032e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}