{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 438,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00228310502283105,
      "grad_norm": 6.537960529327393,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 1.8099,
      "step": 1
    },
    {
      "epoch": 0.01141552511415525,
      "grad_norm": 6.545882225036621,
      "learning_rate": 2.272727272727273e-05,
      "loss": 1.7378,
      "step": 5
    },
    {
      "epoch": 0.0228310502283105,
      "grad_norm": 4.1666693687438965,
      "learning_rate": 4.545454545454546e-05,
      "loss": 1.5963,
      "step": 10
    },
    {
      "epoch": 0.03424657534246575,
      "grad_norm": 2.742569923400879,
      "learning_rate": 6.818181818181818e-05,
      "loss": 1.36,
      "step": 15
    },
    {
      "epoch": 0.045662100456621,
      "grad_norm": 1.3173938989639282,
      "learning_rate": 9.090909090909092e-05,
      "loss": 1.2028,
      "step": 20
    },
    {
      "epoch": 0.05707762557077625,
      "grad_norm": 1.3680421113967896,
      "learning_rate": 0.00011363636363636365,
      "loss": 1.1031,
      "step": 25
    },
    {
      "epoch": 0.0684931506849315,
      "grad_norm": 1.06874418258667,
      "learning_rate": 0.00013636363636363637,
      "loss": 1.0291,
      "step": 30
    },
    {
      "epoch": 0.07990867579908675,
      "grad_norm": 0.7481689453125,
      "learning_rate": 0.0001590909090909091,
      "loss": 0.9542,
      "step": 35
    },
    {
      "epoch": 0.091324200913242,
      "grad_norm": 0.5238539576530457,
      "learning_rate": 0.00018181818181818183,
      "loss": 0.9042,
      "step": 40
    },
    {
      "epoch": 0.10273972602739725,
      "grad_norm": 0.6258371472358704,
      "learning_rate": 0.00019999682111362368,
      "loss": 0.8712,
      "step": 45
    },
    {
      "epoch": 0.1141552511415525,
      "grad_norm": 0.652073860168457,
      "learning_rate": 0.00019988558131018186,
      "loss": 0.8544,
      "step": 50
    },
    {
      "epoch": 0.12557077625570776,
      "grad_norm": 0.41882091760635376,
      "learning_rate": 0.0001996155992365444,
      "loss": 0.8341,
      "step": 55
    },
    {
      "epoch": 0.136986301369863,
      "grad_norm": 0.4048590064048767,
      "learning_rate": 0.00019918730395931649,
      "loss": 0.8206,
      "step": 60
    },
    {
      "epoch": 0.14840182648401826,
      "grad_norm": 0.41035646200180054,
      "learning_rate": 0.00019860137614295168,
      "loss": 0.8261,
      "step": 65
    },
    {
      "epoch": 0.1598173515981735,
      "grad_norm": 0.5227702856063843,
      "learning_rate": 0.00019785874696801202,
      "loss": 0.8022,
      "step": 70
    },
    {
      "epoch": 0.17123287671232876,
      "grad_norm": 0.744319498538971,
      "learning_rate": 0.0001969605966512975,
      "loss": 0.8126,
      "step": 75
    },
    {
      "epoch": 0.182648401826484,
      "grad_norm": 0.6107627749443054,
      "learning_rate": 0.00019590835257019714,
      "loss": 0.8135,
      "step": 80
    },
    {
      "epoch": 0.19406392694063926,
      "grad_norm": 0.5606933832168579,
      "learning_rate": 0.00019470368699424218,
      "loss": 0.791,
      "step": 85
    },
    {
      "epoch": 0.2054794520547945,
      "grad_norm": 0.481476753950119,
      "learning_rate": 0.00019334851442746664,
      "loss": 0.7933,
      "step": 90
    },
    {
      "epoch": 0.21689497716894976,
      "grad_norm": 0.42986494302749634,
      "learning_rate": 0.00019184498856579868,
      "loss": 0.7855,
      "step": 95
    },
    {
      "epoch": 0.228310502283105,
      "grad_norm": 0.8674535751342773,
      "learning_rate": 0.00019019549887431877,
      "loss": 0.788,
      "step": 100
    },
    {
      "epoch": 0.23972602739726026,
      "grad_norm": 0.5029703974723816,
      "learning_rate": 0.00018840266678982342,
      "loss": 0.7916,
      "step": 105
    },
    {
      "epoch": 0.2511415525114155,
      "grad_norm": 0.5123094916343689,
      "learning_rate": 0.00018646934155473022,
      "loss": 0.7698,
      "step": 110
    },
    {
      "epoch": 0.2625570776255708,
      "grad_norm": 0.6292619109153748,
      "learning_rate": 0.00018439859568894463,
      "loss": 0.7729,
      "step": 115
    },
    {
      "epoch": 0.273972602739726,
      "grad_norm": 0.48256051540374756,
      "learning_rate": 0.00018219372010688515,
      "loss": 0.7645,
      "step": 120
    },
    {
      "epoch": 0.2853881278538813,
      "grad_norm": 0.5615462064743042,
      "learning_rate": 0.00017985821888742685,
      "loss": 0.7683,
      "step": 125
    },
    {
      "epoch": 0.2968036529680365,
      "grad_norm": 0.44299066066741943,
      "learning_rate": 0.00017739580370507532,
      "loss": 0.7643,
      "step": 130
    },
    {
      "epoch": 0.3082191780821918,
      "grad_norm": 0.6133469343185425,
      "learning_rate": 0.00017481038793122088,
      "loss": 0.7703,
      "step": 135
    },
    {
      "epoch": 0.319634703196347,
      "grad_norm": 0.4634026885032654,
      "learning_rate": 0.0001721060804148482,
      "loss": 0.7747,
      "step": 140
    },
    {
      "epoch": 0.3310502283105023,
      "grad_norm": 0.5451490879058838,
      "learning_rate": 0.00016928717895258437,
      "loss": 0.7724,
      "step": 145
    },
    {
      "epoch": 0.3424657534246575,
      "grad_norm": 0.6281952261924744,
      "learning_rate": 0.0001663581634584641,
      "loss": 0.7638,
      "step": 150
    },
    {
      "epoch": 0.3538812785388128,
      "grad_norm": 0.5821138620376587,
      "learning_rate": 0.00016332368884426626,
      "loss": 0.7558,
      "step": 155
    },
    {
      "epoch": 0.365296803652968,
      "grad_norm": 0.6641839146614075,
      "learning_rate": 0.0001601885776217367,
      "loss": 0.7647,
      "step": 160
    },
    {
      "epoch": 0.3767123287671233,
      "grad_norm": 0.5730116963386536,
      "learning_rate": 0.00015695781223845441,
      "loss": 0.7655,
      "step": 165
    },
    {
      "epoch": 0.3881278538812785,
      "grad_norm": 0.5685128569602966,
      "learning_rate": 0.0001536365271595212,
      "loss": 0.7609,
      "step": 170
    },
    {
      "epoch": 0.3995433789954338,
      "grad_norm": 0.47333163022994995,
      "learning_rate": 0.00015023000070765884,
      "loss": 0.7609,
      "step": 175
    },
    {
      "epoch": 0.410958904109589,
      "grad_norm": 0.8263501524925232,
      "learning_rate": 0.0001467436466746814,
      "loss": 0.7536,
      "step": 180
    },
    {
      "epoch": 0.4223744292237443,
      "grad_norm": 0.6865557432174683,
      "learning_rate": 0.00014318300571767513,
      "loss": 0.7568,
      "step": 185
    },
    {
      "epoch": 0.4337899543378995,
      "grad_norm": 0.45099779963493347,
      "learning_rate": 0.0001395537365535585,
      "loss": 0.7536,
      "step": 190
    },
    {
      "epoch": 0.4452054794520548,
      "grad_norm": 0.44106268882751465,
      "learning_rate": 0.00013586160696601665,
      "loss": 0.7592,
      "step": 195
    },
    {
      "epoch": 0.45662100456621,
      "grad_norm": 0.44125545024871826,
      "learning_rate": 0.00013211248463910262,
      "loss": 0.7513,
      "step": 200
    },
    {
      "epoch": 0.4680365296803653,
      "grad_norm": 0.45518410205841064,
      "learning_rate": 0.00012831232783207277,
      "loss": 0.7404,
      "step": 205
    },
    {
      "epoch": 0.4794520547945205,
      "grad_norm": 0.4644870162010193,
      "learning_rate": 0.00012446717591027624,
      "loss": 0.7452,
      "step": 210
    },
    {
      "epoch": 0.4908675799086758,
      "grad_norm": 0.5244945883750916,
      "learning_rate": 0.00012058313974714746,
      "loss": 0.7494,
      "step": 215
    },
    {
      "epoch": 0.502283105022831,
      "grad_norm": 0.4744689464569092,
      "learning_rate": 0.00011666639201255506,
      "loss": 0.7382,
      "step": 220
    },
    {
      "epoch": 0.5136986301369864,
      "grad_norm": 0.4412366449832916,
      "learning_rate": 0.00011272315736294108,
      "loss": 0.7398,
      "step": 225
    },
    {
      "epoch": 0.5251141552511416,
      "grad_norm": 0.45072141289711,
      "learning_rate": 0.0001087597025488413,
      "loss": 0.7492,
      "step": 230
    },
    {
      "epoch": 0.5365296803652968,
      "grad_norm": 0.5198200941085815,
      "learning_rate": 0.00010478232645550782,
      "loss": 0.7505,
      "step": 235
    },
    {
      "epoch": 0.547945205479452,
      "grad_norm": 0.463403582572937,
      "learning_rate": 0.00010079735009246167,
      "loss": 0.7434,
      "step": 240
    },
    {
      "epoch": 0.5593607305936074,
      "grad_norm": 0.5372945070266724,
      "learning_rate": 9.681110654788482e-05,
      "loss": 0.7443,
      "step": 245
    },
    {
      "epoch": 0.5707762557077626,
      "grad_norm": 0.5424056649208069,
      "learning_rate": 9.282993092381625e-05,
      "loss": 0.7252,
      "step": 250
    },
    {
      "epoch": 0.5821917808219178,
      "grad_norm": 0.4267898201942444,
      "learning_rate": 8.886015026814736e-05,
      "loss": 0.7374,
      "step": 255
    },
    {
      "epoch": 0.593607305936073,
      "grad_norm": 0.4452318251132965,
      "learning_rate": 8.490807351941753e-05,
      "loss": 0.7374,
      "step": 260
    },
    {
      "epoch": 0.6050228310502284,
      "grad_norm": 0.5267938375473022,
      "learning_rate": 8.097998148038985e-05,
      "loss": 0.7369,
      "step": 265
    },
    {
      "epoch": 0.6164383561643836,
      "grad_norm": 0.49687665700912476,
      "learning_rate": 7.708211683634112e-05,
      "loss": 0.7324,
      "step": 270
    },
    {
      "epoch": 0.6278538812785388,
      "grad_norm": 0.4589200019836426,
      "learning_rate": 7.322067423393002e-05,
      "loss": 0.727,
      "step": 275
    },
    {
      "epoch": 0.639269406392694,
      "grad_norm": 0.6677468419075012,
      "learning_rate": 6.940179043641005e-05,
      "loss": 0.7265,
      "step": 280
    },
    {
      "epoch": 0.6506849315068494,
      "grad_norm": 0.4672200679779053,
      "learning_rate": 6.563153457083315e-05,
      "loss": 0.7358,
      "step": 285
    },
    {
      "epoch": 0.6621004566210046,
      "grad_norm": 0.48395875096321106,
      "learning_rate": 6.191589848274368e-05,
      "loss": 0.732,
      "step": 290
    },
    {
      "epoch": 0.6735159817351598,
      "grad_norm": 0.4542995095252991,
      "learning_rate": 5.82607872136913e-05,
      "loss": 0.7365,
      "step": 295
    },
    {
      "epoch": 0.684931506849315,
      "grad_norm": 0.46610426902770996,
      "learning_rate": 5.467200961669619e-05,
      "loss": 0.7272,
      "step": 300
    },
    {
      "epoch": 0.6963470319634704,
      "grad_norm": 0.47753971815109253,
      "learning_rate": 5.115526912458113e-05,
      "loss": 0.7256,
      "step": 305
    },
    {
      "epoch": 0.7077625570776256,
      "grad_norm": 0.5854398012161255,
      "learning_rate": 4.7716154685841944e-05,
      "loss": 0.7407,
      "step": 310
    },
    {
      "epoch": 0.7191780821917808,
      "grad_norm": 0.4733522832393646,
      "learning_rate": 4.4360131882460555e-05,
      "loss": 0.746,
      "step": 315
    },
    {
      "epoch": 0.730593607305936,
      "grad_norm": 0.49361252784729004,
      "learning_rate": 4.109253424377772e-05,
      "loss": 0.7349,
      "step": 320
    },
    {
      "epoch": 0.7420091324200914,
      "grad_norm": 0.5429126620292664,
      "learning_rate": 3.791855477022903e-05,
      "loss": 0.7281,
      "step": 325
    },
    {
      "epoch": 0.7534246575342466,
      "grad_norm": 0.48451346158981323,
      "learning_rate": 3.4843237680415156e-05,
      "loss": 0.728,
      "step": 330
    },
    {
      "epoch": 0.7648401826484018,
      "grad_norm": 0.4551585018634796,
      "learning_rate": 3.1871470394622404e-05,
      "loss": 0.715,
      "step": 335
    },
    {
      "epoch": 0.776255707762557,
      "grad_norm": 0.5019502639770508,
      "learning_rate": 2.9007975767533714e-05,
      "loss": 0.7269,
      "step": 340
    },
    {
      "epoch": 0.7876712328767124,
      "grad_norm": 0.43697601556777954,
      "learning_rate": 2.625730458247362e-05,
      "loss": 0.735,
      "step": 345
    },
    {
      "epoch": 0.7990867579908676,
      "grad_norm": 0.4500909149646759,
      "learning_rate": 2.3623828319116748e-05,
      "loss": 0.7368,
      "step": 350
    },
    {
      "epoch": 0.8105022831050228,
      "grad_norm": 0.455743670463562,
      "learning_rate": 2.1111732206152424e-05,
      "loss": 0.7385,
      "step": 355
    },
    {
      "epoch": 0.821917808219178,
      "grad_norm": 0.4662931561470032,
      "learning_rate": 1.8725008569947365e-05,
      "loss": 0.7389,
      "step": 360
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.45579805970191956,
      "learning_rate": 1.6467450489776582e-05,
      "loss": 0.7271,
      "step": 365
    },
    {
      "epoch": 0.8447488584474886,
      "grad_norm": 0.4291900098323822,
      "learning_rate": 1.4342645769705977e-05,
      "loss": 0.7224,
      "step": 370
    },
    {
      "epoch": 0.8561643835616438,
      "grad_norm": 0.43814659118652344,
      "learning_rate": 1.2353971236706564e-05,
      "loss": 0.736,
      "step": 375
    },
    {
      "epoch": 0.867579908675799,
      "grad_norm": 0.45001426339149475,
      "learning_rate": 1.0504587374062391e-05,
      "loss": 0.7174,
      "step": 380
    },
    {
      "epoch": 0.8789954337899544,
      "grad_norm": 0.5118018388748169,
      "learning_rate": 8.797433298600622e-06,
      "loss": 0.7214,
      "step": 385
    },
    {
      "epoch": 0.8904109589041096,
      "grad_norm": 0.4473750591278076,
      "learning_rate": 7.235222089726279e-06,
      "loss": 0.7279,
      "step": 390
    },
    {
      "epoch": 0.9018264840182648,
      "grad_norm": 0.44456323981285095,
      "learning_rate": 5.82043647768502e-06,
      "loss": 0.736,
      "step": 395
    },
    {
      "epoch": 0.91324200913242,
      "grad_norm": 0.4372852146625519,
      "learning_rate": 4.555324897906132e-06,
      "loss": 0.7248,
      "step": 400
    },
    {
      "epoch": 0.9246575342465754,
      "grad_norm": 0.44558244943618774,
      "learning_rate": 3.441897917696679e-06,
      "loss": 0.7276,
      "step": 405
    },
    {
      "epoch": 0.9360730593607306,
      "grad_norm": 0.4511885941028595,
      "learning_rate": 2.4819250409651607e-06,
      "loss": 0.7269,
      "step": 410
    },
    {
      "epoch": 0.9474885844748858,
      "grad_norm": 0.4582946002483368,
      "learning_rate": 1.6769318960533464e-06,
      "loss": 0.729,
      "step": 415
    },
    {
      "epoch": 0.958904109589041,
      "grad_norm": 0.43736863136291504,
      "learning_rate": 1.0281978111449375e-06,
      "loss": 0.7401,
      "step": 420
    },
    {
      "epoch": 0.9703196347031964,
      "grad_norm": 0.4510857164859772,
      "learning_rate": 5.367537811046485e-07,
      "loss": 0.7356,
      "step": 425
    },
    {
      "epoch": 0.9817351598173516,
      "grad_norm": 0.4327021539211273,
      "learning_rate": 2.0338082897886079e-07,
      "loss": 0.7222,
      "step": 430
    },
    {
      "epoch": 0.9931506849315068,
      "grad_norm": 0.44210952520370483,
      "learning_rate": 2.8608764761639538e-08,
      "loss": 0.7244,
      "step": 435
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.8283706903457642,
      "eval_runtime": 0.9325,
      "eval_samples_per_second": 12.868,
      "eval_steps_per_second": 1.072,
      "step": 438
    },
    {
      "epoch": 1.0,
      "step": 438,
      "total_flos": 6.128949620228751e+17,
      "train_loss": 0.7978243280763495,
      "train_runtime": 3115.8127,
      "train_samples_per_second": 4.494,
      "train_steps_per_second": 0.141
    }
  ],
  "logging_steps": 5,
  "max_steps": 438,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.128949620228751e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}