{
  "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": 2.0722603797912598,
      "learning_rate": 0.0,
      "loss": 3.2131,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6677350997924805,
      "learning_rate": 4e-05,
      "loss": 2.5554,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6039100885391235,
      "learning_rate": 8e-05,
      "loss": 2.6951,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.6277270317077637,
      "learning_rate": 0.00012,
      "loss": 2.9003,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.0207111835479736,
      "learning_rate": 0.00016,
      "loss": 2.6989,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6012003421783447,
      "learning_rate": 0.0002,
      "loss": 2.2728,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.338730812072754,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7083,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.3853142261505127,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5367,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.1683852672576904,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2907,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9153192639350891,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.16,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4894245862960815,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.5419,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8791560530662537,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.323,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5337121486663818,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1458,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5149000883102417,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0808,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4778643846511841,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.088,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.47255033254623413,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0745,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.43144354224205017,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.2685,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.38666868209838867,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0754,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.38462671637535095,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9311,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.35871055722236633,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.95,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.43639278411865234,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9915,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3904358446598053,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0229,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3931411802768707,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.897,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3906334340572357,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0983,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3786067068576813,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0237,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.36092478036880493,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9729,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27863427996635437,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9565,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.30928313732147217,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0746,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3250511586666107,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9843,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30846866965293884,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0582,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.3773055672645569,
      "learning_rate": 0.00018891352549889136,
      "loss": 0.9213,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.3716050386428833,
      "learning_rate": 0.00018847006651884703,
      "loss": 0.9804,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3420291244983673,
      "learning_rate": 0.00018802660753880268,
      "loss": 1.0815,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2763300836086273,
      "learning_rate": 0.00018758314855875832,
      "loss": 0.902,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3937534689903259,
      "learning_rate": 0.00018713968957871397,
      "loss": 1.1645,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.27199873328208923,
      "learning_rate": 0.00018669623059866964,
      "loss": 0.8738,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.2848569452762604,
      "learning_rate": 0.00018625277161862528,
      "loss": 1.0149,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.31365159153938293,
      "learning_rate": 0.00018580931263858095,
      "loss": 0.9087,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.24746054410934448,
      "learning_rate": 0.0001853658536585366,
      "loss": 0.9948,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.23962347209453583,
      "learning_rate": 0.00018492239467849224,
      "loss": 1.1008,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.28994685411453247,
      "learning_rate": 0.0001844789356984479,
      "loss": 0.915,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.30804207921028137,
      "learning_rate": 0.00018403547671840356,
      "loss": 0.8168,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.397780179977417,
      "learning_rate": 0.0001835920177383592,
      "loss": 1.0102,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.28575780987739563,
      "learning_rate": 0.00018314855875831487,
      "loss": 1.0709,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.2701430022716522,
      "learning_rate": 0.00018270509977827052,
      "loss": 0.9748,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.34878647327423096,
      "learning_rate": 0.00018226164079822616,
      "loss": 0.9461,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.29195308685302734,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9907,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.32355818152427673,
      "learning_rate": 0.00018137472283813748,
      "loss": 1.0469,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.3442789614200592,
      "learning_rate": 0.00018093126385809312,
      "loss": 1.017,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.3519359827041626,
      "learning_rate": 0.0001804878048780488,
      "loss": 0.9013,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.26735949516296387,
      "learning_rate": 0.00018004434589800444,
      "loss": 1.0039,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.27275341749191284,
      "learning_rate": 0.00017960088691796008,
      "loss": 0.8377,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.3131617307662964,
      "learning_rate": 0.00017915742793791575,
      "loss": 1.079,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.3103640675544739,
      "learning_rate": 0.0001787139689578714,
      "loss": 1.1037,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3662891089916229,
      "learning_rate": 0.00017827050997782707,
      "loss": 1.2238,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.31076231598854065,
      "learning_rate": 0.00017782705099778271,
      "loss": 1.0621,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.364701509475708,
      "learning_rate": 0.00017738359201773839,
      "loss": 0.8895,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3279484212398529,
      "learning_rate": 0.000176940133037694,
      "loss": 0.8092,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.4195176959037781,
      "learning_rate": 0.00017649667405764967,
      "loss": 1.0942,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.35336142778396606,
      "learning_rate": 0.00017605321507760532,
      "loss": 0.9458,
      "step": 60
    },
    {
      "epoch": 0.4021978021978022,
      "grad_norm": 0.2668030560016632,
      "learning_rate": 0.000175609756097561,
      "loss": 0.7203,
      "step": 61
    },
    {
      "epoch": 0.4087912087912088,
      "grad_norm": 0.2878060042858124,
      "learning_rate": 0.00017516629711751663,
      "loss": 0.8954,
      "step": 62
    },
    {
      "epoch": 0.4153846153846154,
      "grad_norm": 0.28040236234664917,
      "learning_rate": 0.0001747228381374723,
      "loss": 0.847,
      "step": 63
    },
    {
      "epoch": 0.421978021978022,
      "grad_norm": 0.38638436794281006,
      "learning_rate": 0.00017427937915742792,
      "loss": 0.9154,
      "step": 64
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 0.3532263934612274,
      "learning_rate": 0.0001738359201773836,
      "loss": 0.967,
      "step": 65
    },
    {
      "epoch": 0.4351648351648352,
      "grad_norm": 0.24510745704174042,
      "learning_rate": 0.00017339246119733924,
      "loss": 0.9775,
      "step": 66
    },
    {
      "epoch": 0.44175824175824174,
      "grad_norm": 0.2761436402797699,
      "learning_rate": 0.0001729490022172949,
      "loss": 0.9424,
      "step": 67
    },
    {
      "epoch": 0.44835164835164837,
      "grad_norm": 0.2630966901779175,
      "learning_rate": 0.00017250554323725056,
      "loss": 0.9213,
      "step": 68
    },
    {
      "epoch": 0.45494505494505494,
      "grad_norm": 0.2421293705701828,
      "learning_rate": 0.00017206208425720623,
      "loss": 0.903,
      "step": 69
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.3474556505680084,
      "learning_rate": 0.00017161862527716187,
      "loss": 1.0754,
      "step": 70
    },
    {
      "epoch": 0.46813186813186813,
      "grad_norm": 0.25004228949546814,
      "learning_rate": 0.00017117516629711752,
      "loss": 0.9385,
      "step": 71
    },
    {
      "epoch": 0.4747252747252747,
      "grad_norm": 0.3480256199836731,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.8971,
      "step": 72
    },
    {
      "epoch": 0.48131868131868133,
      "grad_norm": 0.35953742265701294,
      "learning_rate": 0.00017028824833702883,
      "loss": 1.0076,
      "step": 73
    },
    {
      "epoch": 0.4879120879120879,
      "grad_norm": 0.2506542503833771,
      "learning_rate": 0.0001698447893569845,
      "loss": 0.771,
      "step": 74
    },
    {
      "epoch": 0.4945054945054945,
      "grad_norm": 0.29169702529907227,
      "learning_rate": 0.00016940133037694015,
      "loss": 0.7205,
      "step": 75
    },
    {
      "epoch": 0.5010989010989011,
      "grad_norm": 0.26952701807022095,
      "learning_rate": 0.00016895787139689582,
      "loss": 1.0331,
      "step": 76
    },
    {
      "epoch": 0.5076923076923077,
      "grad_norm": 0.3254987895488739,
      "learning_rate": 0.00016851441241685144,
      "loss": 0.9197,
      "step": 77
    },
    {
      "epoch": 0.5142857142857142,
      "grad_norm": 0.2873916029930115,
      "learning_rate": 0.0001680709534368071,
      "loss": 1.0837,
      "step": 78
    },
    {
      "epoch": 0.5208791208791209,
      "grad_norm": 0.3419133424758911,
      "learning_rate": 0.00016762749445676275,
      "loss": 0.8816,
      "step": 79
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.29397767782211304,
      "learning_rate": 0.00016718403547671842,
      "loss": 1.0683,
      "step": 80
    },
    {
      "epoch": 0.5340659340659341,
      "grad_norm": 0.2623101472854614,
      "learning_rate": 0.00016674057649667407,
      "loss": 0.8472,
      "step": 81
    },
    {
      "epoch": 0.5406593406593406,
      "grad_norm": 0.44186830520629883,
      "learning_rate": 0.00016629711751662974,
      "loss": 1.2116,
      "step": 82
    },
    {
      "epoch": 0.5472527472527473,
      "grad_norm": 0.4125562906265259,
      "learning_rate": 0.00016585365853658536,
      "loss": 1.0062,
      "step": 83
    },
    {
      "epoch": 0.5538461538461539,
      "grad_norm": 0.3349130153656006,
      "learning_rate": 0.00016541019955654103,
      "loss": 0.8995,
      "step": 84
    },
    {
      "epoch": 0.5604395604395604,
      "grad_norm": 0.34971699118614197,
      "learning_rate": 0.00016496674057649667,
      "loss": 0.8694,
      "step": 85
    },
    {
      "epoch": 0.567032967032967,
      "grad_norm": 0.3700663447380066,
      "learning_rate": 0.00016452328159645234,
      "loss": 1.0927,
      "step": 86
    },
    {
      "epoch": 0.5736263736263736,
      "grad_norm": 0.28516340255737305,
      "learning_rate": 0.000164079822616408,
      "loss": 0.8334,
      "step": 87
    },
    {
      "epoch": 0.5802197802197803,
      "grad_norm": 0.27797970175743103,
      "learning_rate": 0.00016363636363636366,
      "loss": 0.8108,
      "step": 88
    },
    {
      "epoch": 0.5868131868131868,
      "grad_norm": 0.3791492283344269,
      "learning_rate": 0.0001631929046563193,
      "loss": 0.8473,
      "step": 89
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.34083792567253113,
      "learning_rate": 0.00016274944567627495,
      "loss": 0.9353,
      "step": 90
    },
    {
      "epoch": 0.6,
      "grad_norm": 0.28273823857307434,
      "learning_rate": 0.0001623059866962306,
      "loss": 0.8956,
      "step": 91
    },
    {
      "epoch": 0.6065934065934065,
      "grad_norm": 0.3167821764945984,
      "learning_rate": 0.00016186252771618626,
      "loss": 0.8953,
      "step": 92
    },
    {
      "epoch": 0.6131868131868132,
      "grad_norm": 0.26616188883781433,
      "learning_rate": 0.0001614190687361419,
      "loss": 0.8261,
      "step": 93
    },
    {
      "epoch": 0.6197802197802198,
      "grad_norm": 0.237916499376297,
      "learning_rate": 0.00016097560975609758,
      "loss": 0.8914,
      "step": 94
    },
    {
      "epoch": 0.6263736263736264,
      "grad_norm": 0.32362309098243713,
      "learning_rate": 0.00016053215077605322,
      "loss": 0.9295,
      "step": 95
    },
    {
      "epoch": 0.6329670329670329,
      "grad_norm": 0.2910405099391937,
      "learning_rate": 0.00016008869179600887,
      "loss": 1.047,
      "step": 96
    },
    {
      "epoch": 0.6395604395604395,
      "grad_norm": 0.279320627450943,
      "learning_rate": 0.00015964523281596454,
      "loss": 0.9465,
      "step": 97
    },
    {
      "epoch": 0.6461538461538462,
      "grad_norm": 0.36068761348724365,
      "learning_rate": 0.00015920177383592018,
      "loss": 1.0782,
      "step": 98
    },
    {
      "epoch": 0.6527472527472528,
      "grad_norm": 0.38116326928138733,
      "learning_rate": 0.00015875831485587586,
      "loss": 0.8893,
      "step": 99
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.28538259863853455,
      "learning_rate": 0.0001583148558758315,
      "loss": 0.8015,
      "step": 100
    },
    {
      "epoch": 0.6659340659340659,
      "grad_norm": 0.3541967272758484,
      "learning_rate": 0.00015787139689578714,
      "loss": 0.8434,
      "step": 101
    },
    {
      "epoch": 0.6725274725274726,
      "grad_norm": 0.34469982981681824,
      "learning_rate": 0.0001574279379157428,
      "loss": 0.8324,
      "step": 102
    },
    {
      "epoch": 0.6791208791208792,
      "grad_norm": 0.4213978946208954,
      "learning_rate": 0.00015698447893569846,
      "loss": 0.9444,
      "step": 103
    },
    {
      "epoch": 0.6857142857142857,
      "grad_norm": 0.3815469741821289,
      "learning_rate": 0.0001565410199556541,
      "loss": 0.8776,
      "step": 104
    },
    {
      "epoch": 0.6923076923076923,
      "grad_norm": 0.35397177934646606,
      "learning_rate": 0.00015609756097560978,
      "loss": 1.1552,
      "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": 1.7283982606860288e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}