{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9607843137254903,
  "eval_steps": 500,
  "global_step": 9000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02178649237472767,
      "grad_norm": 1.4119257926940918,
      "learning_rate": 4.945533769063181e-05,
      "loss": 0.6917,
      "step": 100
    },
    {
      "epoch": 0.04357298474945534,
      "grad_norm": 1.3989609479904175,
      "learning_rate": 4.891067538126362e-05,
      "loss": 0.4496,
      "step": 200
    },
    {
      "epoch": 0.06535947712418301,
      "grad_norm": 1.8628056049346924,
      "learning_rate": 4.8366013071895424e-05,
      "loss": 0.4774,
      "step": 300
    },
    {
      "epoch": 0.08714596949891068,
      "grad_norm": 1.6151583194732666,
      "learning_rate": 4.7821350762527234e-05,
      "loss": 0.4805,
      "step": 400
    },
    {
      "epoch": 0.10893246187363835,
      "grad_norm": 0.3191039264202118,
      "learning_rate": 4.7276688453159044e-05,
      "loss": 0.4375,
      "step": 500
    },
    {
      "epoch": 0.13071895424836602,
      "grad_norm": 1.743823766708374,
      "learning_rate": 4.673202614379085e-05,
      "loss": 0.4678,
      "step": 600
    },
    {
      "epoch": 0.15250544662309368,
      "grad_norm": 1.9511303901672363,
      "learning_rate": 4.6187363834422656e-05,
      "loss": 0.5285,
      "step": 700
    },
    {
      "epoch": 0.17429193899782136,
      "grad_norm": 0.5090198516845703,
      "learning_rate": 4.564270152505447e-05,
      "loss": 0.4451,
      "step": 800
    },
    {
      "epoch": 0.19607843137254902,
      "grad_norm": 2.6404006481170654,
      "learning_rate": 4.5098039215686275e-05,
      "loss": 0.4524,
      "step": 900
    },
    {
      "epoch": 0.2178649237472767,
      "grad_norm": 2.596175193786621,
      "learning_rate": 4.4553376906318085e-05,
      "loss": 0.4284,
      "step": 1000
    },
    {
      "epoch": 0.23965141612200436,
      "grad_norm": 2.235574960708618,
      "learning_rate": 4.400871459694989e-05,
      "loss": 0.4234,
      "step": 1100
    },
    {
      "epoch": 0.26143790849673204,
      "grad_norm": 1.786952018737793,
      "learning_rate": 4.3464052287581704e-05,
      "loss": 0.4881,
      "step": 1200
    },
    {
      "epoch": 0.28322440087145967,
      "grad_norm": 1.1873655319213867,
      "learning_rate": 4.291938997821351e-05,
      "loss": 0.4714,
      "step": 1300
    },
    {
      "epoch": 0.30501089324618735,
      "grad_norm": 1.3493982553482056,
      "learning_rate": 4.2374727668845316e-05,
      "loss": 0.4329,
      "step": 1400
    },
    {
      "epoch": 0.32679738562091504,
      "grad_norm": 1.2561562061309814,
      "learning_rate": 4.1830065359477126e-05,
      "loss": 0.3972,
      "step": 1500
    },
    {
      "epoch": 0.3485838779956427,
      "grad_norm": 3.1698968410491943,
      "learning_rate": 4.1285403050108935e-05,
      "loss": 0.4276,
      "step": 1600
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 1.0001728534698486,
      "learning_rate": 4.074074074074074e-05,
      "loss": 0.5036,
      "step": 1700
    },
    {
      "epoch": 0.39215686274509803,
      "grad_norm": 2.307466745376587,
      "learning_rate": 4.0196078431372555e-05,
      "loss": 0.437,
      "step": 1800
    },
    {
      "epoch": 0.4139433551198257,
      "grad_norm": 1.7833284139633179,
      "learning_rate": 3.965141612200436e-05,
      "loss": 0.4415,
      "step": 1900
    },
    {
      "epoch": 0.4357298474945534,
      "grad_norm": 1.4704581499099731,
      "learning_rate": 3.910675381263617e-05,
      "loss": 0.4752,
      "step": 2000
    },
    {
      "epoch": 0.45751633986928103,
      "grad_norm": 1.4827431440353394,
      "learning_rate": 3.8562091503267977e-05,
      "loss": 0.4268,
      "step": 2100
    },
    {
      "epoch": 0.4793028322440087,
      "grad_norm": 0.10033423453569412,
      "learning_rate": 3.8017429193899786e-05,
      "loss": 0.4641,
      "step": 2200
    },
    {
      "epoch": 0.5010893246187363,
      "grad_norm": 2.280324935913086,
      "learning_rate": 3.747276688453159e-05,
      "loss": 0.4393,
      "step": 2300
    },
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 0.7182455658912659,
      "learning_rate": 3.6928104575163405e-05,
      "loss": 0.4143,
      "step": 2400
    },
    {
      "epoch": 0.5446623093681917,
      "grad_norm": 6.931342124938965,
      "learning_rate": 3.638344226579521e-05,
      "loss": 0.4742,
      "step": 2500
    },
    {
      "epoch": 0.5664488017429193,
      "grad_norm": 1.6501855850219727,
      "learning_rate": 3.583877995642702e-05,
      "loss": 0.4183,
      "step": 2600
    },
    {
      "epoch": 0.5882352941176471,
      "grad_norm": 15.619595527648926,
      "learning_rate": 3.529411764705883e-05,
      "loss": 0.4591,
      "step": 2700
    },
    {
      "epoch": 0.6100217864923747,
      "grad_norm": 1.5793421268463135,
      "learning_rate": 3.474945533769064e-05,
      "loss": 0.4326,
      "step": 2800
    },
    {
      "epoch": 0.6318082788671024,
      "grad_norm": 1.2501574754714966,
      "learning_rate": 3.420479302832244e-05,
      "loss": 0.4019,
      "step": 2900
    },
    {
      "epoch": 0.6535947712418301,
      "grad_norm": 2.454075336456299,
      "learning_rate": 3.366013071895425e-05,
      "loss": 0.4306,
      "step": 3000
    },
    {
      "epoch": 0.6753812636165577,
      "grad_norm": 1.4100277423858643,
      "learning_rate": 3.311546840958606e-05,
      "loss": 0.4533,
      "step": 3100
    },
    {
      "epoch": 0.6971677559912854,
      "grad_norm": 1.2618755102157593,
      "learning_rate": 3.257080610021787e-05,
      "loss": 0.4523,
      "step": 3200
    },
    {
      "epoch": 0.7189542483660131,
      "grad_norm": 1.4713486433029175,
      "learning_rate": 3.202614379084967e-05,
      "loss": 0.4371,
      "step": 3300
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 1.1793227195739746,
      "learning_rate": 3.148148148148148e-05,
      "loss": 0.4465,
      "step": 3400
    },
    {
      "epoch": 0.7625272331154684,
      "grad_norm": 0.7598987221717834,
      "learning_rate": 3.093681917211329e-05,
      "loss": 0.4759,
      "step": 3500
    },
    {
      "epoch": 0.7843137254901961,
      "grad_norm": 1.8617286682128906,
      "learning_rate": 3.0392156862745097e-05,
      "loss": 0.4248,
      "step": 3600
    },
    {
      "epoch": 0.8061002178649237,
      "grad_norm": 0.8327335715293884,
      "learning_rate": 2.984749455337691e-05,
      "loss": 0.4257,
      "step": 3700
    },
    {
      "epoch": 0.8278867102396514,
      "grad_norm": 1.4007729291915894,
      "learning_rate": 2.9302832244008716e-05,
      "loss": 0.4066,
      "step": 3800
    },
    {
      "epoch": 0.8496732026143791,
      "grad_norm": 1.50600266456604,
      "learning_rate": 2.8758169934640522e-05,
      "loss": 0.4225,
      "step": 3900
    },
    {
      "epoch": 0.8714596949891068,
      "grad_norm": 1.622689127922058,
      "learning_rate": 2.8213507625272335e-05,
      "loss": 0.4262,
      "step": 4000
    },
    {
      "epoch": 0.8932461873638344,
      "grad_norm": 1.0574493408203125,
      "learning_rate": 2.766884531590414e-05,
      "loss": 0.4102,
      "step": 4100
    },
    {
      "epoch": 0.9150326797385621,
      "grad_norm": 0.6209813356399536,
      "learning_rate": 2.7124183006535947e-05,
      "loss": 0.4231,
      "step": 4200
    },
    {
      "epoch": 0.9368191721132898,
      "grad_norm": 0.6364914178848267,
      "learning_rate": 2.657952069716776e-05,
      "loss": 0.4556,
      "step": 4300
    },
    {
      "epoch": 0.9586056644880174,
      "grad_norm": 0.9522435665130615,
      "learning_rate": 2.6034858387799566e-05,
      "loss": 0.4344,
      "step": 4400
    },
    {
      "epoch": 0.9803921568627451,
      "grad_norm": 0.8629395365715027,
      "learning_rate": 2.5490196078431373e-05,
      "loss": 0.4111,
      "step": 4500
    },
    {
      "epoch": 1.0021786492374727,
      "grad_norm": 1.2452311515808105,
      "learning_rate": 2.4945533769063182e-05,
      "loss": 0.3741,
      "step": 4600
    },
    {
      "epoch": 1.0239651416122004,
      "grad_norm": 0.6457747220993042,
      "learning_rate": 2.4400871459694992e-05,
      "loss": 0.3617,
      "step": 4700
    },
    {
      "epoch": 1.0457516339869282,
      "grad_norm": 3.9131181240081787,
      "learning_rate": 2.38562091503268e-05,
      "loss": 0.3263,
      "step": 4800
    },
    {
      "epoch": 1.0675381263616557,
      "grad_norm": 1.347782015800476,
      "learning_rate": 2.3311546840958608e-05,
      "loss": 0.3248,
      "step": 4900
    },
    {
      "epoch": 1.0893246187363834,
      "grad_norm": 15.944000244140625,
      "learning_rate": 2.2766884531590417e-05,
      "loss": 0.3329,
      "step": 5000
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.9070430994033813,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 0.3405,
      "step": 5100
    },
    {
      "epoch": 1.132897603485839,
      "grad_norm": 1.5099300146102905,
      "learning_rate": 2.1677559912854033e-05,
      "loss": 0.3405,
      "step": 5200
    },
    {
      "epoch": 1.1546840958605664,
      "grad_norm": 1.4810432195663452,
      "learning_rate": 2.113289760348584e-05,
      "loss": 0.3575,
      "step": 5300
    },
    {
      "epoch": 1.1764705882352942,
      "grad_norm": 1.5918389558792114,
      "learning_rate": 2.058823529411765e-05,
      "loss": 0.3284,
      "step": 5400
    },
    {
      "epoch": 1.1982570806100217,
      "grad_norm": 1.1542829275131226,
      "learning_rate": 2.0043572984749455e-05,
      "loss": 0.3328,
      "step": 5500
    },
    {
      "epoch": 1.2200435729847494,
      "grad_norm": 2.9146111011505127,
      "learning_rate": 1.9498910675381264e-05,
      "loss": 0.3358,
      "step": 5600
    },
    {
      "epoch": 1.2418300653594772,
      "grad_norm": 1.1495596170425415,
      "learning_rate": 1.895424836601307e-05,
      "loss": 0.3581,
      "step": 5700
    },
    {
      "epoch": 1.263616557734205,
      "grad_norm": 1.925133228302002,
      "learning_rate": 1.840958605664488e-05,
      "loss": 0.338,
      "step": 5800
    },
    {
      "epoch": 1.2854030501089324,
      "grad_norm": 0.6670601963996887,
      "learning_rate": 1.786492374727669e-05,
      "loss": 0.3166,
      "step": 5900
    },
    {
      "epoch": 1.3071895424836601,
      "grad_norm": 1.3753750324249268,
      "learning_rate": 1.7320261437908496e-05,
      "loss": 0.3322,
      "step": 6000
    },
    {
      "epoch": 1.3289760348583877,
      "grad_norm": 0.8356995582580566,
      "learning_rate": 1.6775599128540306e-05,
      "loss": 0.3465,
      "step": 6100
    },
    {
      "epoch": 1.3507625272331154,
      "grad_norm": 0.6578918695449829,
      "learning_rate": 1.6230936819172112e-05,
      "loss": 0.3449,
      "step": 6200
    },
    {
      "epoch": 1.3725490196078431,
      "grad_norm": 0.8830516338348389,
      "learning_rate": 1.568627450980392e-05,
      "loss": 0.3152,
      "step": 6300
    },
    {
      "epoch": 1.3943355119825709,
      "grad_norm": 2.0208992958068848,
      "learning_rate": 1.5141612200435731e-05,
      "loss": 0.3237,
      "step": 6400
    },
    {
      "epoch": 1.4161220043572984,
      "grad_norm": 0.7672997117042542,
      "learning_rate": 1.4596949891067537e-05,
      "loss": 0.3317,
      "step": 6500
    },
    {
      "epoch": 1.4379084967320261,
      "grad_norm": 1.3644828796386719,
      "learning_rate": 1.4052287581699347e-05,
      "loss": 0.3341,
      "step": 6600
    },
    {
      "epoch": 1.4596949891067539,
      "grad_norm": 1.7263342142105103,
      "learning_rate": 1.3507625272331156e-05,
      "loss": 0.2875,
      "step": 6700
    },
    {
      "epoch": 1.4814814814814814,
      "grad_norm": 0.5791486501693726,
      "learning_rate": 1.2962962962962962e-05,
      "loss": 0.3583,
      "step": 6800
    },
    {
      "epoch": 1.5032679738562091,
      "grad_norm": 1.689420223236084,
      "learning_rate": 1.2418300653594772e-05,
      "loss": 0.3011,
      "step": 6900
    },
    {
      "epoch": 1.5250544662309369,
      "grad_norm": 0.42838066816329956,
      "learning_rate": 1.187363834422658e-05,
      "loss": 0.3153,
      "step": 7000
    },
    {
      "epoch": 1.5468409586056646,
      "grad_norm": 1.6973720788955688,
      "learning_rate": 1.1328976034858388e-05,
      "loss": 0.3253,
      "step": 7100
    },
    {
      "epoch": 1.5686274509803921,
      "grad_norm": 1.9545549154281616,
      "learning_rate": 1.0784313725490197e-05,
      "loss": 0.3348,
      "step": 7200
    },
    {
      "epoch": 1.5904139433551199,
      "grad_norm": 1.2370498180389404,
      "learning_rate": 1.0239651416122005e-05,
      "loss": 0.3207,
      "step": 7300
    },
    {
      "epoch": 1.6122004357298474,
      "grad_norm": 1.108176589012146,
      "learning_rate": 9.694989106753813e-06,
      "loss": 0.3145,
      "step": 7400
    },
    {
      "epoch": 1.6339869281045751,
      "grad_norm": 1.849331259727478,
      "learning_rate": 9.150326797385621e-06,
      "loss": 0.2982,
      "step": 7500
    },
    {
      "epoch": 1.6557734204793029,
      "grad_norm": 1.2936469316482544,
      "learning_rate": 8.60566448801743e-06,
      "loss": 0.3161,
      "step": 7600
    },
    {
      "epoch": 1.6775599128540306,
      "grad_norm": 1.2373560667037964,
      "learning_rate": 8.061002178649239e-06,
      "loss": 0.3335,
      "step": 7700
    },
    {
      "epoch": 1.6993464052287581,
      "grad_norm": 0.7337093949317932,
      "learning_rate": 7.5163398692810456e-06,
      "loss": 0.3027,
      "step": 7800
    },
    {
      "epoch": 1.7211328976034859,
      "grad_norm": 0.2871895134449005,
      "learning_rate": 6.971677559912855e-06,
      "loss": 0.3048,
      "step": 7900
    },
    {
      "epoch": 1.7429193899782134,
      "grad_norm": 1.113721489906311,
      "learning_rate": 6.427015250544663e-06,
      "loss": 0.3076,
      "step": 8000
    },
    {
      "epoch": 1.7647058823529411,
      "grad_norm": 1.1479638814926147,
      "learning_rate": 5.882352941176471e-06,
      "loss": 0.3513,
      "step": 8100
    },
    {
      "epoch": 1.7864923747276689,
      "grad_norm": 0.8669132590293884,
      "learning_rate": 5.33769063180828e-06,
      "loss": 0.3347,
      "step": 8200
    },
    {
      "epoch": 1.8082788671023966,
      "grad_norm": 1.534184455871582,
      "learning_rate": 4.7930283224400875e-06,
      "loss": 0.336,
      "step": 8300
    },
    {
      "epoch": 1.8300653594771243,
      "grad_norm": 1.0394097566604614,
      "learning_rate": 4.2483660130718954e-06,
      "loss": 0.3152,
      "step": 8400
    },
    {
      "epoch": 1.8518518518518519,
      "grad_norm": 0.9366344809532166,
      "learning_rate": 3.7037037037037037e-06,
      "loss": 0.3272,
      "step": 8500
    },
    {
      "epoch": 1.8736383442265794,
      "grad_norm": 1.5486916303634644,
      "learning_rate": 3.159041394335512e-06,
      "loss": 0.3223,
      "step": 8600
    },
    {
      "epoch": 1.8954248366013071,
      "grad_norm": 2.589451551437378,
      "learning_rate": 2.6143790849673204e-06,
      "loss": 0.3189,
      "step": 8700
    },
    {
      "epoch": 1.9172113289760349,
      "grad_norm": 0.5650085806846619,
      "learning_rate": 2.0697167755991287e-06,
      "loss": 0.3132,
      "step": 8800
    },
    {
      "epoch": 1.9389978213507626,
      "grad_norm": 0.18872463703155518,
      "learning_rate": 1.525054466230937e-06,
      "loss": 0.3219,
      "step": 8900
    },
    {
      "epoch": 1.9607843137254903,
      "grad_norm": 1.094841718673706,
      "learning_rate": 9.80392156862745e-07,
      "loss": 0.3015,
      "step": 9000
    }
  ],
  "logging_steps": 100,
  "max_steps": 9180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.825775061368832e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}