{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2967032967032967,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 1.092259407043457,
      "learning_rate": 0.0,
      "loss": 1.0581,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.0709208250045776,
      "learning_rate": 9.56e-05,
      "loss": 1.1072,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.958633303642273,
      "learning_rate": 0.0001912,
      "loss": 0.9974,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.1406344175338745,
      "learning_rate": 0.0002868,
      "loss": 1.0239,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.6300336122512817,
      "learning_rate": 0.0003824,
      "loss": 0.864,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.6665506958961487,
      "learning_rate": 0.000478,
      "loss": 0.9466,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5092409253120422,
      "learning_rate": 0.00047694013303769406,
      "loss": 0.9307,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.4416404068470001,
      "learning_rate": 0.00047588026607538804,
      "loss": 0.8977,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.2995733320713043,
      "learning_rate": 0.0004748203991130821,
      "loss": 0.8339,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3041072487831116,
      "learning_rate": 0.00047376053215077607,
      "loss": 0.8087,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.37241628766059875,
      "learning_rate": 0.00047270066518847006,
      "loss": 0.771,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.39393821358680725,
      "learning_rate": 0.0004716407982261641,
      "loss": 0.8849,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.3837544918060303,
      "learning_rate": 0.00047058093126385814,
      "loss": 0.8491,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.49497556686401367,
      "learning_rate": 0.0004695210643015521,
      "loss": 0.8303,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.5117122530937195,
      "learning_rate": 0.00046846119733924617,
      "loss": 0.8409,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.49063509702682495,
      "learning_rate": 0.00046740133037694015,
      "loss": 0.7597,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.45528849959373474,
      "learning_rate": 0.00046634146341463414,
      "loss": 0.7641,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.6419070959091187,
      "learning_rate": 0.0004652815964523282,
      "loss": 0.7994,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.4234957695007324,
      "learning_rate": 0.0004642217294900222,
      "loss": 0.8006,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3917295038700104,
      "learning_rate": 0.0004631618625277162,
      "loss": 0.672,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.42700546979904175,
      "learning_rate": 0.00046210199556541025,
      "loss": 0.79,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.31304818391799927,
      "learning_rate": 0.00046104212860310423,
      "loss": 0.8003,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.5040671229362488,
      "learning_rate": 0.0004599822616407982,
      "loss": 0.7685,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3319059908390045,
      "learning_rate": 0.00045892239467849226,
      "loss": 0.6304,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3119790554046631,
      "learning_rate": 0.0004578625277161863,
      "loss": 0.6764,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.5550832748413086,
      "learning_rate": 0.0004568026607538803,
      "loss": 0.7242,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.34620189666748047,
      "learning_rate": 0.00045574279379157433,
      "loss": 0.7264,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.37555280327796936,
      "learning_rate": 0.00045468292682926826,
      "loss": 0.7266,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.37990307807922363,
      "learning_rate": 0.0004536230598669623,
      "loss": 0.7272,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.41835644841194153,
      "learning_rate": 0.00045256319290465634,
      "loss": 0.6954,
      "step": 30
    },
    {
      "epoch": 0.2043956043956044,
      "grad_norm": 0.4351997673511505,
      "learning_rate": 0.00045150332594235033,
      "loss": 0.796,
      "step": 31
    },
    {
      "epoch": 0.210989010989011,
      "grad_norm": 0.408133864402771,
      "learning_rate": 0.00045044345898004437,
      "loss": 0.7393,
      "step": 32
    },
    {
      "epoch": 0.2175824175824176,
      "grad_norm": 0.3200816512107849,
      "learning_rate": 0.0004493835920177384,
      "loss": 0.7437,
      "step": 33
    },
    {
      "epoch": 0.22417582417582418,
      "grad_norm": 0.2987661063671112,
      "learning_rate": 0.00044832372505543234,
      "loss": 0.724,
      "step": 34
    },
    {
      "epoch": 0.23076923076923078,
      "grad_norm": 0.3201579451560974,
      "learning_rate": 0.0004472638580931264,
      "loss": 0.7287,
      "step": 35
    },
    {
      "epoch": 0.23736263736263735,
      "grad_norm": 0.30183011293411255,
      "learning_rate": 0.0004462039911308204,
      "loss": 0.7698,
      "step": 36
    },
    {
      "epoch": 0.24395604395604395,
      "grad_norm": 0.3419806659221649,
      "learning_rate": 0.0004451441241685144,
      "loss": 0.6937,
      "step": 37
    },
    {
      "epoch": 0.25054945054945055,
      "grad_norm": 0.3351280391216278,
      "learning_rate": 0.00044408425720620845,
      "loss": 0.6422,
      "step": 38
    },
    {
      "epoch": 0.2571428571428571,
      "grad_norm": 0.3343323767185211,
      "learning_rate": 0.0004430243902439025,
      "loss": 0.7491,
      "step": 39
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.31155410408973694,
      "learning_rate": 0.0004419645232815964,
      "loss": 0.754,
      "step": 40
    },
    {
      "epoch": 0.2703296703296703,
      "grad_norm": 0.30340951681137085,
      "learning_rate": 0.00044090465631929047,
      "loss": 0.7478,
      "step": 41
    },
    {
      "epoch": 0.27692307692307694,
      "grad_norm": 0.32625922560691833,
      "learning_rate": 0.0004398447893569845,
      "loss": 0.6869,
      "step": 42
    },
    {
      "epoch": 0.2835164835164835,
      "grad_norm": 0.3275451958179474,
      "learning_rate": 0.0004387849223946785,
      "loss": 0.7391,
      "step": 43
    },
    {
      "epoch": 0.29010989010989013,
      "grad_norm": 0.3605313003063202,
      "learning_rate": 0.00043772505543237253,
      "loss": 0.6923,
      "step": 44
    },
    {
      "epoch": 0.2967032967032967,
      "grad_norm": 0.25487375259399414,
      "learning_rate": 0.0004366651884700666,
      "loss": 0.6635,
      "step": 45
    }
  ],
  "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": 2.0533664324726784e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}