{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 375,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "grad_norm": 4.780884742736816,
      "learning_rate": 4.9985889393594345e-05,
      "loss": 1.1252,
      "step": 5
    },
    {
      "epoch": 0.03,
      "grad_norm": 3.6875321865081787,
      "learning_rate": 4.992859235371958e-05,
      "loss": 0.9595,
      "step": 10
    },
    {
      "epoch": 0.04,
      "grad_norm": 3.3574156761169434,
      "learning_rate": 4.9827327946335875e-05,
      "loss": 0.5891,
      "step": 15
    },
    {
      "epoch": 0.05,
      "grad_norm": 1.8378690481185913,
      "learning_rate": 4.968227477476554e-05,
      "loss": 0.8209,
      "step": 20
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.445030927658081,
      "learning_rate": 4.949368867399567e-05,
      "loss": 0.6718,
      "step": 25
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.878016710281372,
      "learning_rate": 4.9261902259453614e-05,
      "loss": 0.4986,
      "step": 30
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.1748273372650146,
      "learning_rate": 4.898732434036244e-05,
      "loss": 0.5459,
      "step": 35
    },
    {
      "epoch": 0.11,
      "grad_norm": 2.1013641357421875,
      "learning_rate": 4.867043919871076e-05,
      "loss": 0.436,
      "step": 40
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.9981414675712585,
      "learning_rate": 4.8311805735108894e-05,
      "loss": 0.4354,
      "step": 45
    },
    {
      "epoch": 0.13,
      "grad_norm": 1.1620482206344604,
      "learning_rate": 4.791205648303775e-05,
      "loss": 0.3934,
      "step": 50
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.8525057435035706,
      "learning_rate": 4.747189649322894e-05,
      "loss": 0.3605,
      "step": 55
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8548981547355652,
      "learning_rate": 4.699210209014394e-05,
      "loss": 0.4358,
      "step": 60
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.0279943943023682,
      "learning_rate": 4.6473519502745476e-05,
      "loss": 0.2643,
      "step": 65
    },
    {
      "epoch": 0.19,
      "grad_norm": 1.06588613986969,
      "learning_rate": 4.591706337197597e-05,
      "loss": 0.2999,
      "step": 70
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.4997105598449707,
      "learning_rate": 4.532371513757564e-05,
      "loss": 0.3291,
      "step": 75
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.7532416582107544,
      "learning_rate": 4.469452130708543e-05,
      "loss": 0.3229,
      "step": 80
    },
    {
      "epoch": 0.23,
      "grad_norm": 1.3268669843673706,
      "learning_rate": 4.4030591610087624e-05,
      "loss": 0.2938,
      "step": 85
    },
    {
      "epoch": 0.24,
      "grad_norm": 2.0165152549743652,
      "learning_rate": 4.3333097040939764e-05,
      "loss": 0.2999,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 1.5449421405792236,
      "learning_rate": 4.260326779345393e-05,
      "loss": 0.3433,
      "step": 95
    },
    {
      "epoch": 0.27,
      "grad_norm": 1.3084044456481934,
      "learning_rate": 4.184239109116393e-05,
      "loss": 0.3539,
      "step": 100
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.125744342803955,
      "learning_rate": 4.105180891700746e-05,
      "loss": 0.3158,
      "step": 105
    },
    {
      "epoch": 0.29,
      "grad_norm": 1.8335057497024536,
      "learning_rate": 4.023291564642711e-05,
      "loss": 0.2642,
      "step": 110
    },
    {
      "epoch": 0.31,
      "grad_norm": 1.0940334796905518,
      "learning_rate": 3.938715558806525e-05,
      "loss": 0.3195,
      "step": 115
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.5591059923171997,
      "learning_rate": 3.851602043638994e-05,
      "loss": 0.3332,
      "step": 120
    },
    {
      "epoch": 0.33,
      "grad_norm": 1.333927035331726,
      "learning_rate": 3.7621046640744975e-05,
      "loss": 0.3035,
      "step": 125
    },
    {
      "epoch": 0.35,
      "grad_norm": 2.269136905670166,
      "learning_rate": 3.670381269546429e-05,
      "loss": 0.2444,
      "step": 130
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.834069013595581,
      "learning_rate": 3.5765936355830356e-05,
      "loss": 0.2488,
      "step": 135
    },
    {
      "epoch": 0.37,
      "grad_norm": 1.8295272588729858,
      "learning_rate": 3.480907178478654e-05,
      "loss": 0.3412,
      "step": 140
    },
    {
      "epoch": 0.39,
      "grad_norm": 1.2500354051589966,
      "learning_rate": 3.383490663543635e-05,
      "loss": 0.2906,
      "step": 145
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.8438131213188171,
      "learning_rate": 3.2845159074474806e-05,
      "loss": 0.3942,
      "step": 150
    },
    {
      "epoch": 0.41,
      "grad_norm": 1.1667203903198242,
      "learning_rate": 3.1841574751802076e-05,
      "loss": 0.3231,
      "step": 155
    },
    {
      "epoch": 0.43,
      "grad_norm": 1.511820912361145,
      "learning_rate": 3.082592372166412e-05,
      "loss": 0.3024,
      "step": 160
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.2225658893585205,
      "learning_rate": 2.9799997320750507e-05,
      "loss": 0.2341,
      "step": 165
    },
    {
      "epoch": 0.45,
      "grad_norm": 1.8434339761734009,
      "learning_rate": 2.87656050087558e-05,
      "loss": 0.2748,
      "step": 170
    },
    {
      "epoch": 0.47,
      "grad_norm": 1.3489751815795898,
      "learning_rate": 2.7724571176976732e-05,
      "loss": 0.334,
      "step": 175
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.535201907157898,
      "learning_rate": 2.667873193057407e-05,
      "loss": 0.2567,
      "step": 180
    },
    {
      "epoch": 0.49,
      "grad_norm": 1.008681058883667,
      "learning_rate": 2.562993185017431e-05,
      "loss": 0.2683,
      "step": 185
    },
    {
      "epoch": 0.51,
      "grad_norm": 1.9973254203796387,
      "learning_rate": 2.4580020738523e-05,
      "loss": 0.239,
      "step": 190
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.8730356693267822,
      "learning_rate": 2.353085035792756e-05,
      "loss": 0.3383,
      "step": 195
    },
    {
      "epoch": 0.53,
      "grad_norm": 2.763739824295044,
      "learning_rate": 2.2484271164243996e-05,
      "loss": 0.2523,
      "step": 200
    },
    {
      "epoch": 0.55,
      "grad_norm": 1.719117522239685,
      "learning_rate": 2.1442129043167874e-05,
      "loss": 0.3107,
      "step": 205
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.4132226705551147,
      "learning_rate": 2.0406262054585738e-05,
      "loss": 0.3588,
      "step": 210
    },
    {
      "epoch": 0.57,
      "grad_norm": 1.4880174398422241,
      "learning_rate": 1.937849719072931e-05,
      "loss": 0.2298,
      "step": 215
    },
    {
      "epoch": 0.59,
      "grad_norm": 1.2804921865463257,
      "learning_rate": 1.836064715384989e-05,
      "loss": 0.312,
      "step": 220
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.978888988494873,
      "learning_rate": 1.7354507159096647e-05,
      "loss": 0.2606,
      "step": 225
    },
    {
      "epoch": 0.61,
      "grad_norm": 2.160645008087158,
      "learning_rate": 1.6361851768237324e-05,
      "loss": 0.2912,
      "step": 230
    },
    {
      "epoch": 0.63,
      "grad_norm": 0.8796546459197998,
      "learning_rate": 1.5384431759806083e-05,
      "loss": 0.2589,
      "step": 235
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.5918033123016357,
      "learning_rate": 1.4423971041198556e-05,
      "loss": 0.3087,
      "step": 240
    },
    {
      "epoch": 0.65,
      "grad_norm": 1.169569969177246,
      "learning_rate": 1.3482163608160408e-05,
      "loss": 0.2531,
      "step": 245
    },
    {
      "epoch": 0.67,
      "grad_norm": 1.3483657836914062,
      "learning_rate": 1.2560670557032108e-05,
      "loss": 0.2408,
      "step": 250
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.515302300453186,
      "learning_rate": 1.1661117155019293e-05,
      "loss": 0.2372,
      "step": 255
    },
    {
      "epoch": 0.69,
      "grad_norm": 1.2919508218765259,
      "learning_rate": 1.0785089973656337e-05,
      "loss": 0.3127,
      "step": 260
    },
    {
      "epoch": 0.71,
      "grad_norm": 2.6820788383483887,
      "learning_rate": 9.934134090518593e-06,
      "loss": 0.3022,
      "step": 265
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.8853113055229187,
      "learning_rate": 9.109750364118924e-06,
      "loss": 0.2447,
      "step": 270
    },
    {
      "epoch": 0.73,
      "grad_norm": 0.7025986909866333,
      "learning_rate": 8.313392786794833e-06,
      "loss": 0.26,
      "step": 275
    },
    {
      "epoch": 0.75,
      "grad_norm": 1.3302998542785645,
      "learning_rate": 7.546465920254974e-06,
      "loss": 0.3202,
      "step": 280
    },
    {
      "epoch": 0.76,
      "grad_norm": 2.354292392730713,
      "learning_rate": 6.810322418308085e-06,
      "loss": 0.2997,
      "step": 285
    },
    {
      "epoch": 0.77,
      "grad_norm": 2.33747935295105,
      "learning_rate": 6.106260641143546e-06,
      "loss": 0.2958,
      "step": 290
    },
    {
      "epoch": 0.79,
      "grad_norm": 1.9870978593826294,
      "learning_rate": 5.435522365371376e-06,
      "loss": 0.2598,
      "step": 295
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.8262547254562378,
      "learning_rate": 4.799290593860525e-06,
      "loss": 0.2752,
      "step": 300
    },
    {
      "epoch": 0.81,
      "grad_norm": 1.7228032350540161,
      "learning_rate": 4.198687469238297e-06,
      "loss": 0.2258,
      "step": 305
    },
    {
      "epoch": 0.83,
      "grad_norm": 1.789536952972412,
      "learning_rate": 3.6347722947309843e-06,
      "loss": 0.2819,
      "step": 310
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.036774158477783,
      "learning_rate": 3.108539665836388e-06,
      "loss": 0.3051,
      "step": 315
    },
    {
      "epoch": 0.85,
      "grad_norm": 0.786209762096405,
      "learning_rate": 2.6209177161234445e-06,
      "loss": 0.3378,
      "step": 320
    },
    {
      "epoch": 0.87,
      "grad_norm": 0.6244500875473022,
      "learning_rate": 2.1727664802529216e-06,
      "loss": 0.2508,
      "step": 325
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.9054006338119507,
      "learning_rate": 1.7648763771063837e-06,
      "loss": 0.2559,
      "step": 330
    },
    {
      "epoch": 0.89,
      "grad_norm": 2.387683868408203,
      "learning_rate": 1.3979668156987425e-06,
      "loss": 0.2678,
      "step": 335
    },
    {
      "epoch": 0.91,
      "grad_norm": 1.6146109104156494,
      "learning_rate": 1.0726849263332256e-06,
      "loss": 0.1965,
      "step": 340
    },
    {
      "epoch": 0.92,
      "grad_norm": 3.5136632919311523,
      "learning_rate": 7.896044192366586e-07,
      "loss": 0.1523,
      "step": 345
    },
    {
      "epoch": 0.93,
      "grad_norm": 1.1758712530136108,
      "learning_rate": 5.492245726881201e-07,
      "loss": 0.2632,
      "step": 350
    },
    {
      "epoch": 0.95,
      "grad_norm": 1.7988349199295044,
      "learning_rate": 3.51969352425624e-07,
      "loss": 0.2846,
      "step": 355
    },
    {
      "epoch": 0.96,
      "grad_norm": 2.6087231636047363,
      "learning_rate": 1.981866638839952e-07,
      "loss": 0.3034,
      "step": 360
    },
    {
      "epoch": 0.97,
      "grad_norm": 2.0585777759552,
      "learning_rate": 8.814773858275004e-08,
      "loss": 0.2232,
      "step": 365
    },
    {
      "epoch": 0.99,
      "grad_norm": 2.155041217803955,
      "learning_rate": 2.2046655746280064e-08,
      "loss": 0.2931,
      "step": 370
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.2778571844100952,
      "learning_rate": 0.0,
      "loss": 0.2683,
      "step": 375
    },
    {
      "epoch": 1.0,
      "step": 375,
      "total_flos": 6.39535360058327e+16,
      "train_loss": 0.33599581162134806,
      "train_runtime": 7953.7418,
      "train_samples_per_second": 0.377,
      "train_steps_per_second": 0.047
    }
  ],
  "logging_steps": 5,
  "max_steps": 375,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "total_flos": 6.39535360058327e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}