{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.864864864864865,
  "eval_steps": 500,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 12.665340423583984,
      "learning_rate": 2e-05,
      "loss": 1.7136,
      "step": 1
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 16.679874420166016,
      "learning_rate": 4e-05,
      "loss": 1.8963,
      "step": 2
    },
    {
      "epoch": 0.32432432432432434,
      "grad_norm": 20.59364891052246,
      "learning_rate": 6e-05,
      "loss": 1.9249,
      "step": 3
    },
    {
      "epoch": 0.43243243243243246,
      "grad_norm": 14.520182609558105,
      "learning_rate": 8e-05,
      "loss": 1.9998,
      "step": 4
    },
    {
      "epoch": 0.5405405405405406,
      "grad_norm": 12.898869514465332,
      "learning_rate": 0.0001,
      "loss": 1.7198,
      "step": 5
    },
    {
      "epoch": 0.6486486486486487,
      "grad_norm": 8.388209342956543,
      "learning_rate": 0.00012,
      "loss": 1.4897,
      "step": 6
    },
    {
      "epoch": 0.7567567567567568,
      "grad_norm": 11.714303016662598,
      "learning_rate": 0.00014,
      "loss": 1.496,
      "step": 7
    },
    {
      "epoch": 0.8648648648648649,
      "grad_norm": 9.486503601074219,
      "learning_rate": 0.00016,
      "loss": 1.2274,
      "step": 8
    },
    {
      "epoch": 0.972972972972973,
      "grad_norm": 5.287358283996582,
      "learning_rate": 0.00018,
      "loss": 0.9407,
      "step": 9
    },
    {
      "epoch": 1.0810810810810811,
      "grad_norm": 8.37257194519043,
      "learning_rate": 0.0002,
      "loss": 1.345,
      "step": 10
    },
    {
      "epoch": 1.1891891891891893,
      "grad_norm": 4.060468673706055,
      "learning_rate": 0.0001999229036240723,
      "loss": 0.4743,
      "step": 11
    },
    {
      "epoch": 1.2972972972972974,
      "grad_norm": 5.808952808380127,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.3448,
      "step": 12
    },
    {
      "epoch": 1.4054054054054055,
      "grad_norm": 3.857832193374634,
      "learning_rate": 0.00019930684569549264,
      "loss": 0.2794,
      "step": 13
    },
    {
      "epoch": 1.5135135135135136,
      "grad_norm": 17.618928909301758,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.2564,
      "step": 14
    },
    {
      "epoch": 1.6216216216216215,
      "grad_norm": 3.731938362121582,
      "learning_rate": 0.00019807852804032305,
      "loss": 0.127,
      "step": 15
    },
    {
      "epoch": 1.7297297297297298,
      "grad_norm": 10.822015762329102,
      "learning_rate": 0.00019723699203976766,
      "loss": 0.1671,
      "step": 16
    },
    {
      "epoch": 1.8378378378378377,
      "grad_norm": 6.625267028808594,
      "learning_rate": 0.00019624552364536473,
      "loss": 0.165,
      "step": 17
    },
    {
      "epoch": 1.945945945945946,
      "grad_norm": 3.4650943279266357,
      "learning_rate": 0.00019510565162951537,
      "loss": 0.1427,
      "step": 18
    },
    {
      "epoch": 2.054054054054054,
      "grad_norm": 2.571530818939209,
      "learning_rate": 0.00019381913359224842,
      "loss": 0.2318,
      "step": 19
    },
    {
      "epoch": 2.1621621621621623,
      "grad_norm": 1.4535036087036133,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.0737,
      "step": 20
    },
    {
      "epoch": 2.27027027027027,
      "grad_norm": 3.276848077774048,
      "learning_rate": 0.00019081431738250814,
      "loss": 0.1144,
      "step": 21
    },
    {
      "epoch": 2.3783783783783785,
      "grad_norm": 1.9437713623046875,
      "learning_rate": 0.0001891006524188368,
      "loss": 0.1057,
      "step": 22
    },
    {
      "epoch": 2.4864864864864864,
      "grad_norm": 0.7327317595481873,
      "learning_rate": 0.00018724960070727972,
      "loss": 0.0499,
      "step": 23
    },
    {
      "epoch": 2.5945945945945947,
      "grad_norm": 0.6805225610733032,
      "learning_rate": 0.00018526401643540922,
      "loss": 0.0393,
      "step": 24
    },
    {
      "epoch": 2.7027027027027026,
      "grad_norm": 1.9485719203948975,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.1071,
      "step": 25
    },
    {
      "epoch": 2.810810810810811,
      "grad_norm": 1.6188167333602905,
      "learning_rate": 0.00018090169943749476,
      "loss": 0.076,
      "step": 26
    },
    {
      "epoch": 2.918918918918919,
      "grad_norm": 0.5011986494064331,
      "learning_rate": 0.00017853169308807448,
      "loss": 0.0431,
      "step": 27
    },
    {
      "epoch": 3.027027027027027,
      "grad_norm": 3.750688314437866,
      "learning_rate": 0.0001760405965600031,
      "loss": 0.151,
      "step": 28
    },
    {
      "epoch": 3.135135135135135,
      "grad_norm": 1.4113177061080933,
      "learning_rate": 0.00017343225094356855,
      "loss": 0.0692,
      "step": 29
    },
    {
      "epoch": 3.2432432432432434,
      "grad_norm": 1.220698595046997,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.0671,
      "step": 30
    },
    {
      "epoch": 3.3513513513513513,
      "grad_norm": 0.5514506101608276,
      "learning_rate": 0.0001678800745532942,
      "loss": 0.0592,
      "step": 31
    },
    {
      "epoch": 3.4594594594594597,
      "grad_norm": 1.1301401853561401,
      "learning_rate": 0.00016494480483301836,
      "loss": 0.0709,
      "step": 32
    },
    {
      "epoch": 3.5675675675675675,
      "grad_norm": 2.738895893096924,
      "learning_rate": 0.00016190939493098344,
      "loss": 0.0752,
      "step": 33
    },
    {
      "epoch": 3.6756756756756754,
      "grad_norm": 1.05312180519104,
      "learning_rate": 0.00015877852522924732,
      "loss": 0.044,
      "step": 34
    },
    {
      "epoch": 3.7837837837837838,
      "grad_norm": 0.8468568325042725,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.053,
      "step": 35
    },
    {
      "epoch": 3.891891891891892,
      "grad_norm": 0.8362758159637451,
      "learning_rate": 0.0001522498564715949,
      "loss": 0.0694,
      "step": 36
    },
    {
      "epoch": 4.0,
      "grad_norm": 0.9148968458175659,
      "learning_rate": 0.00014886212414969553,
      "loss": 0.0675,
      "step": 37
    },
    {
      "epoch": 4.108108108108108,
      "grad_norm": 0.5609957575798035,
      "learning_rate": 0.00014539904997395468,
      "loss": 0.0585,
      "step": 38
    },
    {
      "epoch": 4.216216216216216,
      "grad_norm": 0.7747177481651306,
      "learning_rate": 0.0001418659737537428,
      "loss": 0.0389,
      "step": 39
    },
    {
      "epoch": 4.324324324324325,
      "grad_norm": 0.40356096625328064,
      "learning_rate": 0.000138268343236509,
      "loss": 0.0367,
      "step": 40
    },
    {
      "epoch": 4.4324324324324325,
      "grad_norm": 0.8019518256187439,
      "learning_rate": 0.0001346117057077493,
      "loss": 0.048,
      "step": 41
    },
    {
      "epoch": 4.54054054054054,
      "grad_norm": 0.746637761592865,
      "learning_rate": 0.00013090169943749476,
      "loss": 0.0484,
      "step": 42
    },
    {
      "epoch": 4.648648648648649,
      "grad_norm": 0.9343522191047668,
      "learning_rate": 0.00012714404498650743,
      "loss": 0.0457,
      "step": 43
    },
    {
      "epoch": 4.756756756756757,
      "grad_norm": 0.5715629458427429,
      "learning_rate": 0.00012334453638559057,
      "loss": 0.04,
      "step": 44
    },
    {
      "epoch": 4.864864864864865,
      "grad_norm": 0.2774278223514557,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.0369,
      "step": 45
    }
  ],
  "logging_steps": 1,
  "max_steps": 90,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.970590133387264e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}