{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.3956043956043956,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.195170283317566,
      "learning_rate": 0.0,
      "loss": 1.0821,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0331945419311523,
      "learning_rate": 9.56e-05,
      "loss": 1.0763,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.1415084600448608,
      "learning_rate": 0.0001912,
      "loss": 1.0495,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.063579797744751,
      "learning_rate": 0.0002868,
      "loss": 0.956,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6625626087188721,
      "learning_rate": 0.0003824,
      "loss": 0.8477,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6782878637313843,
      "learning_rate": 0.000478,
      "loss": 1.0343,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.6161335110664368,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9727,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.41984498500823975,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8698,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.3116914927959442,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8446,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.29025012254714966,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.7877,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.39959046244621277,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.8688,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.5689778923988342,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8847,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.40798476338386536,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.7254,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.6968982219696045,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.8179,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5194700360298157,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.7156,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.43927809596061707,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.8273,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3979283571243286,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7288,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.4314859211444855,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7677,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.3548160791397095,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.6472,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.38769328594207764,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.6578,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.3017254173755646,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.7163,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.33315712213516235,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.6951,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3334329426288605,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7464,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.301981121301651,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.667,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3768517076969147,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.6719,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.3810518980026245,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7687,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.4689561128616333,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7114,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.3895481824874878,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7328,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.44972071051597595,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.708,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.39502742886543274,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.7672,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.5479147434234619,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.7583,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.33382317423820496,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7369,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.49583446979522705,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.8174,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.3855836093425751,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.7935,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.45332643389701843,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7593,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.3067397475242615,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.6878,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3372962474822998,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.7705,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.40445494651794434,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.7849,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3279916048049927,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.715,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.31464719772338867,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.7322,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.27914178371429443,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.6922,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.27055102586746216,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.7071,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.30358147621154785,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7257,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3098717927932739,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6871,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.32566770911216736,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.7264,
      "step": 45
    },
    {
      "epoch": 0.3032967032967033,
      "grad_norm": 0.3617362082004547,
      "learning_rate": 0.0004356053215077605,
      "loss": 0.6902,
      "step": 46
    },
    {
      "epoch": 0.3098901098901099,
      "grad_norm": 0.43403375148773193,
      "learning_rate": 0.00043454545454545455,
      "loss": 0.7037,
      "step": 47
    },
    {
      "epoch": 0.31648351648351647,
      "grad_norm": 0.33475279808044434,
      "learning_rate": 0.0004334855875831486,
      "loss": 0.7261,
      "step": 48
    },
    {
      "epoch": 0.3230769230769231,
      "grad_norm": 0.34020453691482544,
      "learning_rate": 0.0004324257206208426,
      "loss": 0.6361,
      "step": 49
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.29145631194114685,
      "learning_rate": 0.0004313658536585366,
      "loss": 0.6797,
      "step": 50
    },
    {
      "epoch": 0.3362637362637363,
      "grad_norm": 0.35258740186691284,
      "learning_rate": 0.00043030598669623066,
      "loss": 0.6811,
      "step": 51
    },
    {
      "epoch": 0.34285714285714286,
      "grad_norm": 0.31551578640937805,
      "learning_rate": 0.0004292461197339246,
      "loss": 0.6662,
      "step": 52
    },
    {
      "epoch": 0.34945054945054943,
      "grad_norm": 0.40033137798309326,
      "learning_rate": 0.00042818625277161863,
      "loss": 0.7066,
      "step": 53
    },
    {
      "epoch": 0.35604395604395606,
      "grad_norm": 0.34928882122039795,
      "learning_rate": 0.00042712638580931267,
      "loss": 0.6704,
      "step": 54
    },
    {
      "epoch": 0.3626373626373626,
      "grad_norm": 0.3890458345413208,
      "learning_rate": 0.00042606651884700666,
      "loss": 0.7074,
      "step": 55
    },
    {
      "epoch": 0.36923076923076925,
      "grad_norm": 0.34585464000701904,
      "learning_rate": 0.0004250066518847007,
      "loss": 0.7147,
      "step": 56
    },
    {
      "epoch": 0.3758241758241758,
      "grad_norm": 0.2896708548069,
      "learning_rate": 0.00042394678492239474,
      "loss": 0.7679,
      "step": 57
    },
    {
      "epoch": 0.3824175824175824,
      "grad_norm": 0.3353179395198822,
      "learning_rate": 0.00042288691796008867,
      "loss": 0.6415,
      "step": 58
    },
    {
      "epoch": 0.389010989010989,
      "grad_norm": 0.32367175817489624,
      "learning_rate": 0.0004218270509977827,
      "loss": 0.7697,
      "step": 59
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.32652848958969116,
      "learning_rate": 0.00042076718403547675,
      "loss": 0.6835,
      "step": 60
    }
  ],
  "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": 2.755917642343219e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}