{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 75,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04145077720207254,
      "grad_norm": 7.120451927185059,
      "learning_rate": 0.0,
      "loss": 0.6092337369918823,
      "step": 1
    },
    {
      "epoch": 0.08290155440414508,
      "grad_norm": 7.659641742706299,
      "learning_rate": 1.25e-06,
      "loss": 0.6191706657409668,
      "step": 2
    },
    {
      "epoch": 0.12435233160621761,
      "grad_norm": 7.61025333404541,
      "learning_rate": 2.5e-06,
      "loss": 0.6386866569519043,
      "step": 3
    },
    {
      "epoch": 0.16580310880829016,
      "grad_norm": 6.137047290802002,
      "learning_rate": 3.7500000000000005e-06,
      "loss": 0.6147851943969727,
      "step": 4
    },
    {
      "epoch": 0.20725388601036268,
      "grad_norm": 4.532908916473389,
      "learning_rate": 5e-06,
      "loss": 0.5547504425048828,
      "step": 5
    },
    {
      "epoch": 0.24870466321243523,
      "grad_norm": 1.924709439277649,
      "learning_rate": 6.25e-06,
      "loss": 0.5066685676574707,
      "step": 6
    },
    {
      "epoch": 0.29015544041450775,
      "grad_norm": 2.2790632247924805,
      "learning_rate": 7.500000000000001e-06,
      "loss": 0.5300189256668091,
      "step": 7
    },
    {
      "epoch": 0.3316062176165803,
      "grad_norm": 2.3154819011688232,
      "learning_rate": 8.750000000000001e-06,
      "loss": 0.5313639640808105,
      "step": 8
    },
    {
      "epoch": 0.37305699481865284,
      "grad_norm": 2.5374321937561035,
      "learning_rate": 1e-05,
      "loss": 0.5247533321380615,
      "step": 9
    },
    {
      "epoch": 0.41450777202072536,
      "grad_norm": 2.257484197616577,
      "learning_rate": 9.994504457428557e-06,
      "loss": 0.5156197547912598,
      "step": 10
    },
    {
      "epoch": 0.45595854922279794,
      "grad_norm": 1.8503879308700562,
      "learning_rate": 9.978029910109491e-06,
      "loss": 0.5004717111587524,
      "step": 11
    },
    {
      "epoch": 0.49740932642487046,
      "grad_norm": 1.385116457939148,
      "learning_rate": 9.950612572673255e-06,
      "loss": 0.4922693967819214,
      "step": 12
    },
    {
      "epoch": 0.538860103626943,
      "grad_norm": 1.3758662939071655,
      "learning_rate": 9.91231271437788e-06,
      "loss": 0.4821719527244568,
      "step": 13
    },
    {
      "epoch": 0.5803108808290155,
      "grad_norm": 1.6386404037475586,
      "learning_rate": 9.863214526624065e-06,
      "loss": 0.49417412281036377,
      "step": 14
    },
    {
      "epoch": 0.6217616580310881,
      "grad_norm": 1.6066042184829712,
      "learning_rate": 9.803425937884202e-06,
      "loss": 0.5054992437362671,
      "step": 15
    },
    {
      "epoch": 0.6632124352331606,
      "grad_norm": 1.4308427572250366,
      "learning_rate": 9.733078376452172e-06,
      "loss": 0.45705559849739075,
      "step": 16
    },
    {
      "epoch": 0.7046632124352331,
      "grad_norm": 1.2889971733093262,
      "learning_rate": 9.652326481535434e-06,
      "loss": 0.45977818965911865,
      "step": 17
    },
    {
      "epoch": 0.7461139896373057,
      "grad_norm": 1.1706485748291016,
      "learning_rate": 9.561347763324484e-06,
      "loss": 0.45801055431365967,
      "step": 18
    },
    {
      "epoch": 0.7875647668393783,
      "grad_norm": 1.0704251527786255,
      "learning_rate": 9.460342212786933e-06,
      "loss": 0.4489409625530243,
      "step": 19
    },
    {
      "epoch": 0.8290155440414507,
      "grad_norm": 1.1201295852661133,
      "learning_rate": 9.349531862043952e-06,
      "loss": 0.45053625106811523,
      "step": 20
    },
    {
      "epoch": 0.8704663212435233,
      "grad_norm": 1.0289005041122437,
      "learning_rate": 9.229160296295488e-06,
      "loss": 0.43083542585372925,
      "step": 21
    },
    {
      "epoch": 0.9119170984455959,
      "grad_norm": 1.1308515071868896,
      "learning_rate": 9.099492118367123e-06,
      "loss": 0.4581252932548523,
      "step": 22
    },
    {
      "epoch": 0.9533678756476683,
      "grad_norm": 1.0535929203033447,
      "learning_rate": 8.960812367055646e-06,
      "loss": 0.44346559047698975,
      "step": 23
    },
    {
      "epoch": 0.9948186528497409,
      "grad_norm": 0.9610625505447388,
      "learning_rate": 8.81342589055191e-06,
      "loss": 0.44911324977874756,
      "step": 24
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.3097646236419678,
      "learning_rate": 8.657656676318346e-06,
      "loss": 0.4283459782600403,
      "step": 25
    },
    {
      "epoch": 1.0414507772020725,
      "grad_norm": 1.0472010374069214,
      "learning_rate": 8.49384713889421e-06,
      "loss": 0.37155479192733765,
      "step": 26
    },
    {
      "epoch": 1.0829015544041452,
      "grad_norm": 0.9855507612228394,
      "learning_rate": 8.32235736719411e-06,
      "loss": 0.3688446581363678,
      "step": 27
    },
    {
      "epoch": 1.1243523316062176,
      "grad_norm": 0.9636088609695435,
      "learning_rate": 8.143564332954426e-06,
      "loss": 0.37474608421325684,
      "step": 28
    },
    {
      "epoch": 1.16580310880829,
      "grad_norm": 0.9028092622756958,
      "learning_rate": 7.957861062067614e-06,
      "loss": 0.3555857241153717,
      "step": 29
    },
    {
      "epoch": 1.2072538860103628,
      "grad_norm": 0.9712267518043518,
      "learning_rate": 7.765655770625997e-06,
      "loss": 0.34159055352211,
      "step": 30
    },
    {
      "epoch": 1.2487046632124352,
      "grad_norm": 1.8104084730148315,
      "learning_rate": 7.56737096757421e-06,
      "loss": 0.3687860369682312,
      "step": 31
    },
    {
      "epoch": 1.2901554404145077,
      "grad_norm": 1.0975350141525269,
      "learning_rate": 7.363442525942827e-06,
      "loss": 0.35419169068336487,
      "step": 32
    },
    {
      "epoch": 1.3316062176165804,
      "grad_norm": 1.1601834297180176,
      "learning_rate": 7.1543187247048525e-06,
      "loss": 0.3395620882511139,
      "step": 33
    },
    {
      "epoch": 1.3730569948186528,
      "grad_norm": 1.1519272327423096,
      "learning_rate": 6.9404592633612486e-06,
      "loss": 0.3692774176597595,
      "step": 34
    },
    {
      "epoch": 1.4145077720207253,
      "grad_norm": 1.097473382949829,
      "learning_rate": 6.722334251421665e-06,
      "loss": 0.34006065130233765,
      "step": 35
    },
    {
      "epoch": 1.455958549222798,
      "grad_norm": 1.0180498361587524,
      "learning_rate": 6.500423175001705e-06,
      "loss": 0.3356683850288391,
      "step": 36
    },
    {
      "epoch": 1.4974093264248705,
      "grad_norm": 0.9087209701538086,
      "learning_rate": 6.275213842808383e-06,
      "loss": 0.34355655312538147,
      "step": 37
    },
    {
      "epoch": 1.5388601036269431,
      "grad_norm": 0.9768698811531067,
      "learning_rate": 6.047201313830724e-06,
      "loss": 0.343985915184021,
      "step": 38
    },
    {
      "epoch": 1.5803108808290154,
      "grad_norm": 0.9981656074523926,
      "learning_rate": 5.816886809092651e-06,
      "loss": 0.3492792844772339,
      "step": 39
    },
    {
      "epoch": 1.621761658031088,
      "grad_norm": 0.8749750256538391,
      "learning_rate": 5.584776609860414e-06,
      "loss": 0.33584338426589966,
      "step": 40
    },
    {
      "epoch": 1.6632124352331608,
      "grad_norm": 0.8628058433532715,
      "learning_rate": 5.351380944726465e-06,
      "loss": 0.34260594844818115,
      "step": 41
    },
    {
      "epoch": 1.704663212435233,
      "grad_norm": 0.9912312030792236,
      "learning_rate": 5.117212868016303e-06,
      "loss": 0.3369492292404175,
      "step": 42
    },
    {
      "epoch": 1.7461139896373057,
      "grad_norm": 1.0078606605529785,
      "learning_rate": 4.882787131983698e-06,
      "loss": 0.3325812816619873,
      "step": 43
    },
    {
      "epoch": 1.7875647668393784,
      "grad_norm": 0.9152034521102905,
      "learning_rate": 4.6486190552735375e-06,
      "loss": 0.34193870425224304,
      "step": 44
    },
    {
      "epoch": 1.8290155440414506,
      "grad_norm": 0.8891971111297607,
      "learning_rate": 4.415223390139588e-06,
      "loss": 0.3421243727207184,
      "step": 45
    },
    {
      "epoch": 1.8704663212435233,
      "grad_norm": 0.8489858508110046,
      "learning_rate": 4.183113190907349e-06,
      "loss": 0.3245125710964203,
      "step": 46
    },
    {
      "epoch": 1.911917098445596,
      "grad_norm": 0.8828305006027222,
      "learning_rate": 3.952798686169279e-06,
      "loss": 0.3218913674354553,
      "step": 47
    },
    {
      "epoch": 1.9533678756476682,
      "grad_norm": 0.8916757702827454,
      "learning_rate": 3.7247861571916183e-06,
      "loss": 0.33640530705451965,
      "step": 48
    },
    {
      "epoch": 1.994818652849741,
      "grad_norm": 0.9354485869407654,
      "learning_rate": 3.4995768249982975e-06,
      "loss": 0.3383684754371643,
      "step": 49
    },
    {
      "epoch": 2.0,
      "grad_norm": 2.479360818862915,
      "learning_rate": 3.2776657485783357e-06,
      "loss": 0.3096318542957306,
      "step": 50
    },
    {
      "epoch": 2.0414507772020727,
      "grad_norm": 0.9290817975997925,
      "learning_rate": 3.059540736638751e-06,
      "loss": 0.27142035961151123,
      "step": 51
    },
    {
      "epoch": 2.082901554404145,
      "grad_norm": 0.9304895997047424,
      "learning_rate": 2.8456812752951483e-06,
      "loss": 0.27613067626953125,
      "step": 52
    },
    {
      "epoch": 2.1243523316062176,
      "grad_norm": 0.9569095373153687,
      "learning_rate": 2.636557474057173e-06,
      "loss": 0.26246941089630127,
      "step": 53
    },
    {
      "epoch": 2.1658031088082903,
      "grad_norm": 0.9609872102737427,
      "learning_rate": 2.4326290324257896e-06,
      "loss": 0.26978862285614014,
      "step": 54
    },
    {
      "epoch": 2.2072538860103625,
      "grad_norm": 0.9280001521110535,
      "learning_rate": 2.234344229374003e-06,
      "loss": 0.2672296166419983,
      "step": 55
    },
    {
      "epoch": 2.2487046632124352,
      "grad_norm": 0.8706973195075989,
      "learning_rate": 2.042138937932388e-06,
      "loss": 0.2540016770362854,
      "step": 56
    },
    {
      "epoch": 2.290155440414508,
      "grad_norm": 0.8727967143058777,
      "learning_rate": 1.856435667045577e-06,
      "loss": 0.25238296389579773,
      "step": 57
    },
    {
      "epoch": 2.33160621761658,
      "grad_norm": 0.8466634750366211,
      "learning_rate": 1.677642632805892e-06,
      "loss": 0.2629680335521698,
      "step": 58
    },
    {
      "epoch": 2.373056994818653,
      "grad_norm": 0.8684727549552917,
      "learning_rate": 1.5061528611057917e-06,
      "loss": 0.2571195662021637,
      "step": 59
    },
    {
      "epoch": 2.4145077720207255,
      "grad_norm": 0.8672791123390198,
      "learning_rate": 1.3423433236816563e-06,
      "loss": 0.25775718688964844,
      "step": 60
    },
    {
      "epoch": 2.4559585492227978,
      "grad_norm": 0.8584659695625305,
      "learning_rate": 1.186574109448091e-06,
      "loss": 0.2611117959022522,
      "step": 61
    },
    {
      "epoch": 2.4974093264248705,
      "grad_norm": 0.8773574829101562,
      "learning_rate": 1.0391876329443534e-06,
      "loss": 0.2653461992740631,
      "step": 62
    },
    {
      "epoch": 2.538860103626943,
      "grad_norm": 0.8978050947189331,
      "learning_rate": 9.005078816328772e-07,
      "loss": 0.2551964223384857,
      "step": 63
    },
    {
      "epoch": 2.5803108808290154,
      "grad_norm": 0.8816140294075012,
      "learning_rate": 7.708397037045129e-07,
      "loss": 0.25102558732032776,
      "step": 64
    },
    {
      "epoch": 2.621761658031088,
      "grad_norm": 0.8575056791305542,
      "learning_rate": 6.50468137956049e-07,
      "loss": 0.2575952410697937,
      "step": 65
    },
    {
      "epoch": 2.6632124352331608,
      "grad_norm": 0.8623489737510681,
      "learning_rate": 5.396577872130676e-07,
      "loss": 0.258808970451355,
      "step": 66
    },
    {
      "epoch": 2.704663212435233,
      "grad_norm": 0.8812604546546936,
      "learning_rate": 4.386522366755169e-07,
      "loss": 0.24736732244491577,
      "step": 67
    },
    {
      "epoch": 2.7461139896373057,
      "grad_norm": 0.8553208708763123,
      "learning_rate": 3.4767351846456744e-07,
      "loss": 0.2533082365989685,
      "step": 68
    },
    {
      "epoch": 2.7875647668393784,
      "grad_norm": 0.8664875626564026,
      "learning_rate": 2.669216235478295e-07,
      "loss": 0.25305628776550293,
      "step": 69
    },
    {
      "epoch": 2.8290155440414506,
      "grad_norm": 0.8543892502784729,
      "learning_rate": 1.9657406211579966e-07,
      "loss": 0.2626458406448364,
      "step": 70
    },
    {
      "epoch": 2.8704663212435233,
      "grad_norm": 0.8664795756340027,
      "learning_rate": 1.3678547337593494e-07,
      "loss": 0.25443392992019653,
      "step": 71
    },
    {
      "epoch": 2.911917098445596,
      "grad_norm": 0.8772528767585754,
      "learning_rate": 8.768728562211948e-08,
      "loss": 0.26024767756462097,
      "step": 72
    },
    {
      "epoch": 2.9533678756476682,
      "grad_norm": 0.9000739455223083,
      "learning_rate": 4.9387427326745287e-08,
      "loss": 0.26604950428009033,
      "step": 73
    },
    {
      "epoch": 2.994818652849741,
      "grad_norm": 0.9007699489593506,
      "learning_rate": 2.1970089890509527e-08,
      "loss": 0.2610118091106415,
      "step": 74
    },
    {
      "epoch": 3.0,
      "grad_norm": 2.353334426879883,
      "learning_rate": 5.495542571443135e-09,
      "loss": 0.2638687193393707,
      "step": 75
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.5637762167102505e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}