{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.014713996689350745,
      "grad_norm": 1.3101017475128174,
      "learning_rate": 9.86764705882353e-05,
      "loss": 2.9497,
      "step": 10
    },
    {
      "epoch": 0.02942799337870149,
      "grad_norm": 1.7666537761688232,
      "learning_rate": 9.720588235294117e-05,
      "loss": 2.5707,
      "step": 20
    },
    {
      "epoch": 0.044141990068052236,
      "grad_norm": 1.4447238445281982,
      "learning_rate": 9.573529411764707e-05,
      "loss": 2.281,
      "step": 30
    },
    {
      "epoch": 0.05885598675740298,
      "grad_norm": 1.039144515991211,
      "learning_rate": 9.426470588235294e-05,
      "loss": 2.3904,
      "step": 40
    },
    {
      "epoch": 0.07356998344675372,
      "grad_norm": 1.2274360656738281,
      "learning_rate": 9.279411764705884e-05,
      "loss": 2.5839,
      "step": 50
    },
    {
      "epoch": 0.08828398013610447,
      "grad_norm": 1.1105211973190308,
      "learning_rate": 9.13235294117647e-05,
      "loss": 2.2987,
      "step": 60
    },
    {
      "epoch": 0.10299797682545521,
      "grad_norm": 1.2184361219406128,
      "learning_rate": 8.98529411764706e-05,
      "loss": 2.5504,
      "step": 70
    },
    {
      "epoch": 0.11771197351480596,
      "grad_norm": 1.1057401895523071,
      "learning_rate": 8.838235294117647e-05,
      "loss": 2.4922,
      "step": 80
    },
    {
      "epoch": 0.1324259702041567,
      "grad_norm": 1.1191836595535278,
      "learning_rate": 8.691176470588237e-05,
      "loss": 2.6277,
      "step": 90
    },
    {
      "epoch": 0.14713996689350745,
      "grad_norm": 1.2518597841262817,
      "learning_rate": 8.544117647058823e-05,
      "loss": 2.1856,
      "step": 100
    },
    {
      "epoch": 0.1618539635828582,
      "grad_norm": 1.2593870162963867,
      "learning_rate": 8.397058823529412e-05,
      "loss": 2.39,
      "step": 110
    },
    {
      "epoch": 0.17656796027220895,
      "grad_norm": 1.5582458972930908,
      "learning_rate": 8.25e-05,
      "loss": 2.2159,
      "step": 120
    },
    {
      "epoch": 0.1912819569615597,
      "grad_norm": 1.1720651388168335,
      "learning_rate": 8.102941176470588e-05,
      "loss": 2.5332,
      "step": 130
    },
    {
      "epoch": 0.20599595365091042,
      "grad_norm": 1.3537250757217407,
      "learning_rate": 7.955882352941176e-05,
      "loss": 2.549,
      "step": 140
    },
    {
      "epoch": 0.22070995034026117,
      "grad_norm": 1.440487265586853,
      "learning_rate": 7.808823529411765e-05,
      "loss": 2.6141,
      "step": 150
    },
    {
      "epoch": 0.23542394702961192,
      "grad_norm": 1.2468889951705933,
      "learning_rate": 7.661764705882354e-05,
      "loss": 2.1802,
      "step": 160
    },
    {
      "epoch": 0.25013794371896264,
      "grad_norm": 1.6108534336090088,
      "learning_rate": 7.514705882352941e-05,
      "loss": 2.0655,
      "step": 170
    },
    {
      "epoch": 0.2648519404083134,
      "grad_norm": 1.454962968826294,
      "learning_rate": 7.367647058823531e-05,
      "loss": 2.3067,
      "step": 180
    },
    {
      "epoch": 0.27956593709766414,
      "grad_norm": 1.4071511030197144,
      "learning_rate": 7.220588235294118e-05,
      "loss": 2.378,
      "step": 190
    },
    {
      "epoch": 0.2942799337870149,
      "grad_norm": 1.7635990381240845,
      "learning_rate": 7.073529411764707e-05,
      "loss": 2.6275,
      "step": 200
    },
    {
      "epoch": 0.30899393047636564,
      "grad_norm": 1.4291043281555176,
      "learning_rate": 6.926470588235294e-05,
      "loss": 1.8871,
      "step": 210
    },
    {
      "epoch": 0.3237079271657164,
      "grad_norm": 1.5699518918991089,
      "learning_rate": 6.779411764705882e-05,
      "loss": 2.3781,
      "step": 220
    },
    {
      "epoch": 0.33842192385506714,
      "grad_norm": 1.5319325923919678,
      "learning_rate": 6.632352941176471e-05,
      "loss": 2.1488,
      "step": 230
    },
    {
      "epoch": 0.3531359205444179,
      "grad_norm": 1.505298376083374,
      "learning_rate": 6.485294117647059e-05,
      "loss": 2.6991,
      "step": 240
    },
    {
      "epoch": 0.36784991723376864,
      "grad_norm": 2.733734607696533,
      "learning_rate": 6.338235294117647e-05,
      "loss": 2.1978,
      "step": 250
    },
    {
      "epoch": 0.3825639139231194,
      "grad_norm": 1.6058900356292725,
      "learning_rate": 6.191176470588235e-05,
      "loss": 2.1871,
      "step": 260
    },
    {
      "epoch": 0.3972779106124701,
      "grad_norm": 2.072322130203247,
      "learning_rate": 6.044117647058824e-05,
      "loss": 2.5621,
      "step": 270
    },
    {
      "epoch": 0.41199190730182084,
      "grad_norm": 1.765065312385559,
      "learning_rate": 5.897058823529412e-05,
      "loss": 2.1595,
      "step": 280
    },
    {
      "epoch": 0.4267059039911716,
      "grad_norm": 1.5139451026916504,
      "learning_rate": 5.7499999999999995e-05,
      "loss": 2.2917,
      "step": 290
    },
    {
      "epoch": 0.44141990068052234,
      "grad_norm": 1.7041040658950806,
      "learning_rate": 5.6029411764705884e-05,
      "loss": 2.4275,
      "step": 300
    },
    {
      "epoch": 0.4561338973698731,
      "grad_norm": 1.5826152563095093,
      "learning_rate": 5.455882352941176e-05,
      "loss": 2.5011,
      "step": 310
    },
    {
      "epoch": 0.47084789405922384,
      "grad_norm": 1.692821979522705,
      "learning_rate": 5.308823529411765e-05,
      "loss": 2.3798,
      "step": 320
    },
    {
      "epoch": 0.4855618907485746,
      "grad_norm": 1.8263252973556519,
      "learning_rate": 5.161764705882354e-05,
      "loss": 2.6645,
      "step": 330
    },
    {
      "epoch": 0.5002758874379253,
      "grad_norm": 1.7093111276626587,
      "learning_rate": 5.0147058823529414e-05,
      "loss": 2.4835,
      "step": 340
    },
    {
      "epoch": 0.5149898841272761,
      "grad_norm": 1.7787758111953735,
      "learning_rate": 4.86764705882353e-05,
      "loss": 2.3779,
      "step": 350
    },
    {
      "epoch": 0.5297038808166268,
      "grad_norm": 1.7382874488830566,
      "learning_rate": 4.720588235294118e-05,
      "loss": 2.3799,
      "step": 360
    },
    {
      "epoch": 0.5444178775059776,
      "grad_norm": 1.797096848487854,
      "learning_rate": 4.573529411764706e-05,
      "loss": 2.2148,
      "step": 370
    },
    {
      "epoch": 0.5591318741953283,
      "grad_norm": 1.781445860862732,
      "learning_rate": 4.4264705882352944e-05,
      "loss": 2.0308,
      "step": 380
    },
    {
      "epoch": 0.5738458708846791,
      "grad_norm": 2.1444976329803467,
      "learning_rate": 4.2794117647058827e-05,
      "loss": 2.2169,
      "step": 390
    },
    {
      "epoch": 0.5885598675740298,
      "grad_norm": 1.8745927810668945,
      "learning_rate": 4.13235294117647e-05,
      "loss": 1.9554,
      "step": 400
    },
    {
      "epoch": 0.6032738642633806,
      "grad_norm": 1.5899605751037598,
      "learning_rate": 3.985294117647059e-05,
      "loss": 2.4028,
      "step": 410
    },
    {
      "epoch": 0.6179878609527313,
      "grad_norm": 1.9187322854995728,
      "learning_rate": 3.8382352941176474e-05,
      "loss": 2.2514,
      "step": 420
    },
    {
      "epoch": 0.632701857642082,
      "grad_norm": 1.5589262247085571,
      "learning_rate": 3.6911764705882356e-05,
      "loss": 2.343,
      "step": 430
    },
    {
      "epoch": 0.6474158543314328,
      "grad_norm": 1.5984998941421509,
      "learning_rate": 3.544117647058824e-05,
      "loss": 1.9433,
      "step": 440
    },
    {
      "epoch": 0.6621298510207835,
      "grad_norm": 1.9034677743911743,
      "learning_rate": 3.397058823529412e-05,
      "loss": 2.2025,
      "step": 450
    },
    {
      "epoch": 0.6768438477101343,
      "grad_norm": 1.7389880418777466,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 2.3835,
      "step": 460
    },
    {
      "epoch": 0.691557844399485,
      "grad_norm": 1.8547667264938354,
      "learning_rate": 3.1029411764705886e-05,
      "loss": 2.2641,
      "step": 470
    },
    {
      "epoch": 0.7062718410888358,
      "grad_norm": 1.6838593482971191,
      "learning_rate": 2.9558823529411766e-05,
      "loss": 1.8679,
      "step": 480
    },
    {
      "epoch": 0.7209858377781865,
      "grad_norm": 2.003615617752075,
      "learning_rate": 2.8088235294117648e-05,
      "loss": 2.2402,
      "step": 490
    },
    {
      "epoch": 0.7356998344675373,
      "grad_norm": 1.7946232557296753,
      "learning_rate": 2.661764705882353e-05,
      "loss": 1.9735,
      "step": 500
    },
    {
      "epoch": 0.750413831156888,
      "grad_norm": 1.9260705709457397,
      "learning_rate": 2.5147058823529413e-05,
      "loss": 2.3836,
      "step": 510
    },
    {
      "epoch": 0.7651278278462388,
      "grad_norm": 1.3813334703445435,
      "learning_rate": 2.3676470588235295e-05,
      "loss": 2.4856,
      "step": 520
    },
    {
      "epoch": 0.7798418245355895,
      "grad_norm": 1.6835263967514038,
      "learning_rate": 2.2205882352941178e-05,
      "loss": 2.3702,
      "step": 530
    },
    {
      "epoch": 0.7945558212249402,
      "grad_norm": 2.234776496887207,
      "learning_rate": 2.073529411764706e-05,
      "loss": 2.6312,
      "step": 540
    },
    {
      "epoch": 0.809269817914291,
      "grad_norm": 1.4896553754806519,
      "learning_rate": 1.9264705882352943e-05,
      "loss": 2.2481,
      "step": 550
    },
    {
      "epoch": 0.8239838146036417,
      "grad_norm": 1.92662513256073,
      "learning_rate": 1.7794117647058825e-05,
      "loss": 1.9659,
      "step": 560
    },
    {
      "epoch": 0.8386978112929925,
      "grad_norm": 1.4436355829238892,
      "learning_rate": 1.6323529411764708e-05,
      "loss": 2.3563,
      "step": 570
    },
    {
      "epoch": 0.8534118079823432,
      "grad_norm": 1.8207820653915405,
      "learning_rate": 1.4852941176470589e-05,
      "loss": 2.0522,
      "step": 580
    },
    {
      "epoch": 0.868125804671694,
      "grad_norm": 1.8331910371780396,
      "learning_rate": 1.3382352941176471e-05,
      "loss": 2.4762,
      "step": 590
    },
    {
      "epoch": 0.8828398013610447,
      "grad_norm": 1.7300273180007935,
      "learning_rate": 1.1911764705882354e-05,
      "loss": 2.4929,
      "step": 600
    },
    {
      "epoch": 0.8975537980503955,
      "grad_norm": 1.7423087358474731,
      "learning_rate": 1.0441176470588236e-05,
      "loss": 2.065,
      "step": 610
    },
    {
      "epoch": 0.9122677947397462,
      "grad_norm": 1.853888988494873,
      "learning_rate": 8.970588235294119e-06,
      "loss": 2.3043,
      "step": 620
    },
    {
      "epoch": 0.926981791429097,
      "grad_norm": 1.6552138328552246,
      "learning_rate": 7.5e-06,
      "loss": 2.6556,
      "step": 630
    },
    {
      "epoch": 0.9416957881184477,
      "grad_norm": 1.6745601892471313,
      "learning_rate": 6.029411764705883e-06,
      "loss": 2.3833,
      "step": 640
    },
    {
      "epoch": 0.9564097848077984,
      "grad_norm": 1.6154053211212158,
      "learning_rate": 4.558823529411764e-06,
      "loss": 2.4859,
      "step": 650
    },
    {
      "epoch": 0.9711237814971492,
      "grad_norm": 1.7248449325561523,
      "learning_rate": 3.0882352941176472e-06,
      "loss": 2.4022,
      "step": 660
    },
    {
      "epoch": 0.9858377781864999,
      "grad_norm": 1.7172226905822754,
      "learning_rate": 1.6176470588235297e-06,
      "loss": 2.5658,
      "step": 670
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.6853206157684326,
      "learning_rate": 1.4705882352941178e-07,
      "loss": 2.1013,
      "step": 680
    }
  ],
  "logging_steps": 10,
  "max_steps": 680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 5.941123206453658e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}