{
  "best_metric": 0.9721857309341431,
  "best_model_checkpoint": "output/queen/checkpoint-759",
  "epoch": 11.0,
  "global_step": 759,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.07,
      "learning_rate": 0.00013537785052914354,
      "loss": 3.396,
      "step": 5
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001300082017869573,
      "loss": 3.2987,
      "step": 10
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001213763104094255,
      "loss": 2.8576,
      "step": 15
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.000109940736055617,
      "loss": 2.9968,
      "step": 20
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.630898093421199e-05,
      "loss": 2.9324,
      "step": 25
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.120521692221673e-05,
      "loss": 2.9931,
      "step": 30
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.543181473690228e-05,
      "loss": 2.8919,
      "step": 35
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.982671888105512e-05,
      "loss": 2.7977,
      "step": 40
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.5218932770313667e-05,
      "loss": 2.9689,
      "step": 45
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.2384478845846175e-05,
      "loss": 2.756,
      "step": 50
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.200517324255647e-05,
      "loss": 2.8716,
      "step": 55
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.6324050628611986e-06,
      "loss": 2.9236,
      "step": 60
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.578444419609313e-07,
      "loss": 2.8184,
      "step": 65
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.78603196144104,
      "eval_runtime": 4.3884,
      "eval_samples_per_second": 21.192,
      "eval_steps_per_second": 2.734,
      "step": 68
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.926355061606279e-07,
      "loss": 2.8201,
      "step": 70
    },
    {
      "epoch": 1.1,
      "learning_rate": 3.55617957525975e-06,
      "loss": 2.7876,
      "step": 75
    },
    {
      "epoch": 1.18,
      "learning_rate": 1.0275104488948473e-05,
      "loss": 2.8738,
      "step": 80
    },
    {
      "epoch": 1.25,
      "learning_rate": 2.009247481060283e-05,
      "loss": 2.6439,
      "step": 85
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.2486753626613365e-05,
      "loss": 2.5993,
      "step": 90
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.679950861668151e-05,
      "loss": 2.7072,
      "step": 95
    },
    {
      "epoch": 1.47,
      "learning_rate": 6.227039054081748e-05,
      "loss": 2.7465,
      "step": 100
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.807752594969911e-05,
      "loss": 2.5926,
      "step": 105
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.338117830043867e-05,
      "loss": 2.7178,
      "step": 110
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.00010736835802938978,
      "loss": 2.7027,
      "step": 115
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011929601172133719,
      "loss": 2.4457,
      "step": 120
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.00012853049599834097,
      "loss": 2.6806,
      "step": 125
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00013458123912165538,
      "loss": 2.4508,
      "step": 130
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.00013712680207144277,
      "loss": 2.6492,
      "step": 135
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.3717236518859863,
      "eval_runtime": 4.3106,
      "eval_samples_per_second": 22.039,
      "eval_steps_per_second": 2.784,
      "step": 136
    },
    {
      "epoch": 2.0,
      "eval_loss": 2.222139835357666,
      "eval_runtime": 3.7161,
      "eval_samples_per_second": 23.412,
      "eval_steps_per_second": 2.96,
      "step": 138
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.00013691577939766304,
      "loss": 2.3223,
      "step": 140
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.00013374528334456193,
      "loss": 2.4227,
      "step": 145
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00012721317115188912,
      "loss": 2.3956,
      "step": 150
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00011765651179294606,
      "loss": 2.3273,
      "step": 155
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.0001055684464238085,
      "loss": 2.4048,
      "step": 160
    },
    {
      "epoch": 2.39,
      "learning_rate": 9.157274139492967e-05,
      "loss": 2.4168,
      "step": 165
    },
    {
      "epoch": 2.46,
      "learning_rate": 7.639160076306266e-05,
      "loss": 2.4496,
      "step": 170
    },
    {
      "epoch": 2.54,
      "learning_rate": 6.0808399236937385e-05,
      "loss": 2.0669,
      "step": 175
    },
    {
      "epoch": 2.61,
      "learning_rate": 4.5627258605070364e-05,
      "loss": 2.2692,
      "step": 180
    },
    {
      "epoch": 2.68,
      "learning_rate": 3.1631553576191535e-05,
      "loss": 2.1242,
      "step": 185
    },
    {
      "epoch": 2.75,
      "learning_rate": 1.954348820705391e-05,
      "loss": 2.3064,
      "step": 190
    },
    {
      "epoch": 2.83,
      "learning_rate": 9.986828848110892e-06,
      "loss": 2.146,
      "step": 195
    },
    {
      "epoch": 2.9,
      "learning_rate": 3.454716655438096e-06,
      "loss": 2.3787,
      "step": 200
    },
    {
      "epoch": 2.97,
      "learning_rate": 2.8422060233695394e-07,
      "loss": 2.2533,
      "step": 205
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.043508768081665,
      "eval_runtime": 3.8679,
      "eval_samples_per_second": 22.493,
      "eval_steps_per_second": 2.844,
      "step": 207
    },
    {
      "epoch": 3.04,
      "learning_rate": 6.389441019077102e-07,
      "loss": 2.1995,
      "step": 210
    },
    {
      "epoch": 3.12,
      "learning_rate": 4.500582770777967e-06,
      "loss": 2.2239,
      "step": 215
    },
    {
      "epoch": 3.19,
      "learning_rate": 1.166986896886688e-05,
      "loss": 2.1124,
      "step": 220
    },
    {
      "epoch": 3.26,
      "learning_rate": 2.177685437520025e-05,
      "loss": 2.2442,
      "step": 225
    },
    {
      "epoch": 3.33,
      "learning_rate": 3.4300000000000014e-05,
      "loss": 2.0765,
      "step": 230
    },
    {
      "epoch": 3.41,
      "learning_rate": 4.859308855339902e-05,
      "loss": 2.042,
      "step": 235
    },
    {
      "epoch": 3.48,
      "learning_rate": 6.391857044318346e-05,
      "loss": 2.0462,
      "step": 240
    },
    {
      "epoch": 3.55,
      "learning_rate": 7.948562268689874e-05,
      "loss": 1.9776,
      "step": 245
    },
    {
      "epoch": 3.62,
      "learning_rate": 9.449095682862937e-05,
      "loss": 2.1824,
      "step": 250
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.0001081602700970798,
      "loss": 1.996,
      "step": 255
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.00011978820084915117,
      "loss": 2.1329,
      "step": 260
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.00012877472652481797,
      "loss": 2.1854,
      "step": 265
    },
    {
      "epoch": 3.91,
      "learning_rate": 0.00013465612591205902,
      "loss": 1.8201,
      "step": 270
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.00013712890801216552,
      "loss": 1.8969,
      "step": 275
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.9531660079956055,
      "eval_runtime": 3.8382,
      "eval_samples_per_second": 22.667,
      "eval_steps_per_second": 2.866,
      "step": 276
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.0001360654727320747,
      "loss": 1.817,
      "step": 280
    },
    {
      "epoch": 4.13,
      "learning_rate": 0.0001315206952832741,
      "loss": 1.6319,
      "step": 285
    },
    {
      "epoch": 4.2,
      "learning_rate": 0.00012372909452021153,
      "loss": 1.7738,
      "step": 290
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.00011309273133714503,
      "loss": 1.7757,
      "step": 295
    },
    {
      "epoch": 4.35,
      "learning_rate": 0.0001001604615883571,
      "loss": 1.9699,
      "step": 300
    },
    {
      "epoch": 4.42,
      "learning_rate": 8.5599614119113e-05,
      "loss": 1.9681,
      "step": 305
    },
    {
      "epoch": 4.49,
      "learning_rate": 7.016155537292879e-05,
      "loss": 1.9245,
      "step": 310
    },
    {
      "epoch": 4.57,
      "learning_rate": 5.464291750458938e-05,
      "loss": 1.7497,
      "step": 315
    },
    {
      "epoch": 4.64,
      "learning_rate": 3.98444906994169e-05,
      "loss": 1.7975,
      "step": 320
    },
    {
      "epoch": 4.71,
      "learning_rate": 2.6529900930537204e-05,
      "loss": 1.6675,
      "step": 325
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.5386205457676833e-05,
      "loss": 1.9876,
      "step": 330
    },
    {
      "epoch": 4.86,
      "learning_rate": 6.988439412050469e-06,
      "loss": 1.691,
      "step": 335
    },
    {
      "epoch": 4.93,
      "learning_rate": 1.7699429285993718e-06,
      "loss": 1.8689,
      "step": 340
    },
    {
      "epoch": 5.0,
      "learning_rate": 0.0,
      "loss": 1.9327,
      "step": 345
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.8510653972625732,
      "eval_runtime": 3.8275,
      "eval_samples_per_second": 22.73,
      "eval_steps_per_second": 2.874,
      "step": 345
    },
    {
      "epoch": 5.07,
      "learning_rate": 1.7699429285993566e-06,
      "loss": 1.5991,
      "step": 350
    },
    {
      "epoch": 5.14,
      "learning_rate": 6.988439412050431e-06,
      "loss": 1.6155,
      "step": 355
    },
    {
      "epoch": 5.22,
      "learning_rate": 1.538620545767678e-05,
      "loss": 1.6707,
      "step": 360
    },
    {
      "epoch": 5.29,
      "learning_rate": 2.6529900930537035e-05,
      "loss": 1.7262,
      "step": 365
    },
    {
      "epoch": 5.36,
      "learning_rate": 3.984449069941682e-05,
      "loss": 1.7087,
      "step": 370
    },
    {
      "epoch": 5.43,
      "learning_rate": 5.4642917504589295e-05,
      "loss": 1.7766,
      "step": 375
    },
    {
      "epoch": 5.51,
      "learning_rate": 7.016155537292883e-05,
      "loss": 1.5992,
      "step": 380
    },
    {
      "epoch": 5.58,
      "learning_rate": 8.559961411911291e-05,
      "loss": 1.6561,
      "step": 385
    },
    {
      "epoch": 5.65,
      "learning_rate": 0.00010016046158835702,
      "loss": 1.6108,
      "step": 390
    },
    {
      "epoch": 5.72,
      "learning_rate": 0.00011309273133714504,
      "loss": 1.6236,
      "step": 395
    },
    {
      "epoch": 5.8,
      "learning_rate": 0.0001237290945202115,
      "loss": 1.6319,
      "step": 400
    },
    {
      "epoch": 5.87,
      "learning_rate": 0.00013152069528327408,
      "loss": 1.4268,
      "step": 405
    },
    {
      "epoch": 5.94,
      "learning_rate": 0.00013606547273207472,
      "loss": 1.7278,
      "step": 410
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.8254233598709106,
      "eval_runtime": 3.854,
      "eval_samples_per_second": 22.574,
      "eval_steps_per_second": 2.854,
      "step": 414
    },
    {
      "epoch": 6.01,
      "learning_rate": 0.00013712890801216552,
      "loss": 1.8762,
      "step": 415
    },
    {
      "epoch": 6.09,
      "learning_rate": 0.00013465612591205902,
      "loss": 1.4495,
      "step": 420
    },
    {
      "epoch": 6.16,
      "learning_rate": 0.00012877472652481797,
      "loss": 1.5224,
      "step": 425
    },
    {
      "epoch": 6.23,
      "learning_rate": 0.00011978820084915123,
      "loss": 1.5038,
      "step": 430
    },
    {
      "epoch": 6.3,
      "learning_rate": 0.00010816027009708009,
      "loss": 1.4097,
      "step": 435
    },
    {
      "epoch": 6.38,
      "learning_rate": 9.449095682862935e-05,
      "loss": 1.3203,
      "step": 440
    },
    {
      "epoch": 6.45,
      "learning_rate": 7.948562268689883e-05,
      "loss": 1.3634,
      "step": 445
    },
    {
      "epoch": 6.52,
      "learning_rate": 6.39185704431838e-05,
      "loss": 1.4181,
      "step": 450
    },
    {
      "epoch": 6.59,
      "learning_rate": 4.859308855339899e-05,
      "loss": 1.5025,
      "step": 455
    },
    {
      "epoch": 6.67,
      "learning_rate": 3.429999999999998e-05,
      "loss": 1.5881,
      "step": 460
    },
    {
      "epoch": 6.74,
      "learning_rate": 2.1776854375200487e-05,
      "loss": 1.5042,
      "step": 465
    },
    {
      "epoch": 6.81,
      "learning_rate": 1.1669868968866859e-05,
      "loss": 1.4229,
      "step": 470
    },
    {
      "epoch": 6.88,
      "learning_rate": 4.500582770777952e-06,
      "loss": 1.5551,
      "step": 475
    },
    {
      "epoch": 6.96,
      "learning_rate": 6.389441019077407e-07,
      "loss": 1.6253,
      "step": 480
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.787222146987915,
      "eval_runtime": 3.8357,
      "eval_samples_per_second": 22.681,
      "eval_steps_per_second": 2.868,
      "step": 483
    },
    {
      "epoch": 7.03,
      "learning_rate": 2.8422060233696156e-07,
      "loss": 1.5683,
      "step": 485
    },
    {
      "epoch": 7.1,
      "learning_rate": 3.4547166554380356e-06,
      "loss": 1.1749,
      "step": 490
    },
    {
      "epoch": 7.17,
      "learning_rate": 9.986828848110785e-06,
      "loss": 1.2655,
      "step": 495
    },
    {
      "epoch": 7.25,
      "learning_rate": 1.9543488207053935e-05,
      "loss": 1.3456,
      "step": 500
    },
    {
      "epoch": 7.32,
      "learning_rate": 3.163155357619136e-05,
      "loss": 1.2074,
      "step": 505
    },
    {
      "epoch": 7.39,
      "learning_rate": 4.5627258605070174e-05,
      "loss": 1.3068,
      "step": 510
    },
    {
      "epoch": 7.46,
      "learning_rate": 6.080839923693748e-05,
      "loss": 1.1119,
      "step": 515
    },
    {
      "epoch": 7.54,
      "learning_rate": 7.639160076306239e-05,
      "loss": 1.3026,
      "step": 520
    },
    {
      "epoch": 7.61,
      "learning_rate": 9.15727413949297e-05,
      "loss": 1.4164,
      "step": 525
    },
    {
      "epoch": 7.68,
      "learning_rate": 0.00010556844642380854,
      "loss": 1.6188,
      "step": 530
    },
    {
      "epoch": 7.75,
      "learning_rate": 0.00011765651179294598,
      "loss": 1.438,
      "step": 535
    },
    {
      "epoch": 7.83,
      "learning_rate": 0.00012721317115188917,
      "loss": 1.267,
      "step": 540
    },
    {
      "epoch": 7.9,
      "learning_rate": 0.00013374528334456193,
      "loss": 1.2976,
      "step": 545
    },
    {
      "epoch": 7.97,
      "learning_rate": 0.00013691577939766304,
      "loss": 1.4411,
      "step": 550
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.795061707496643,
      "eval_runtime": 3.8467,
      "eval_samples_per_second": 22.617,
      "eval_steps_per_second": 2.86,
      "step": 552
    },
    {
      "epoch": 8.04,
      "learning_rate": 0.0001365610558980923,
      "loss": 1.266,
      "step": 555
    },
    {
      "epoch": 8.12,
      "learning_rate": 0.000132699417229222,
      "loss": 1.2792,
      "step": 560
    },
    {
      "epoch": 8.19,
      "learning_rate": 0.0001255301310311332,
      "loss": 1.2561,
      "step": 565
    },
    {
      "epoch": 8.26,
      "learning_rate": 0.00011542314562479977,
      "loss": 1.2462,
      "step": 570
    },
    {
      "epoch": 8.33,
      "learning_rate": 0.00010289999999999993,
      "loss": 1.2013,
      "step": 575
    },
    {
      "epoch": 8.41,
      "learning_rate": 8.860691144660113e-05,
      "loss": 1.2052,
      "step": 580
    },
    {
      "epoch": 8.48,
      "learning_rate": 7.328142955681657e-05,
      "loss": 1.3885,
      "step": 585
    },
    {
      "epoch": 8.55,
      "learning_rate": 5.771437731310106e-05,
      "loss": 1.0822,
      "step": 590
    },
    {
      "epoch": 8.62,
      "learning_rate": 4.270904317137078e-05,
      "loss": 1.3064,
      "step": 595
    },
    {
      "epoch": 8.7,
      "learning_rate": 2.9039729902920224e-05,
      "loss": 1.2009,
      "step": 600
    },
    {
      "epoch": 8.77,
      "learning_rate": 1.7411799150848703e-05,
      "loss": 1.2057,
      "step": 605
    },
    {
      "epoch": 8.84,
      "learning_rate": 8.425273475182102e-06,
      "loss": 1.1498,
      "step": 610
    },
    {
      "epoch": 8.91,
      "learning_rate": 2.5438740879410024e-06,
      "loss": 1.0197,
      "step": 615
    },
    {
      "epoch": 8.99,
      "learning_rate": 7.109198783448199e-08,
      "loss": 1.1622,
      "step": 620
    },
    {
      "epoch": 9.0,
      "eval_loss": 1.775342345237732,
      "eval_runtime": 3.8327,
      "eval_samples_per_second": 22.699,
      "eval_steps_per_second": 2.87,
      "step": 621
    },
    {
      "epoch": 9.19,
      "learning_rate": 1.2005173242556402e-05,
      "loss": 1.3691,
      "step": 625
    },
    {
      "epoch": 9.26,
      "learning_rate": 2.2384478845846314e-05,
      "loss": 1.5005,
      "step": 630
    },
    {
      "epoch": 9.34,
      "learning_rate": 3.5218932770313436e-05,
      "loss": 1.4065,
      "step": 635
    },
    {
      "epoch": 9.41,
      "learning_rate": 4.982671888105515e-05,
      "loss": 1.3225,
      "step": 640
    },
    {
      "epoch": 9.49,
      "learning_rate": 6.543181473690211e-05,
      "loss": 1.0367,
      "step": 645
    },
    {
      "epoch": 9.56,
      "learning_rate": 8.120521692221662e-05,
      "loss": 1.1784,
      "step": 650
    },
    {
      "epoch": 9.63,
      "learning_rate": 9.630898093421192e-05,
      "loss": 1.2778,
      "step": 655
    },
    {
      "epoch": 9.71,
      "learning_rate": 0.00010994073605561679,
      "loss": 1.3754,
      "step": 660
    },
    {
      "epoch": 9.78,
      "learning_rate": 0.00012137631040942535,
      "loss": 1.1983,
      "step": 665
    },
    {
      "epoch": 9.85,
      "learning_rate": 0.00013000820178695732,
      "loss": 1.3077,
      "step": 670
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.0001353778505291435,
      "loss": 1.4969,
      "step": 675
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001372,
      "loss": 1.3263,
      "step": 680
    },
    {
      "epoch": 10.0,
      "eval_loss": 1.0593422651290894,
      "eval_runtime": 1.2161,
      "eval_samples_per_second": 75.649,
      "eval_steps_per_second": 9.867,
      "step": 680
    },
    {
      "epoch": 9.93,
      "learning_rate": 0.00013543005707140072,
      "loss": 1.2301,
      "step": 685
    },
    {
      "epoch": 10.0,
      "learning_rate": 0.0001372,
      "loss": 1.2039,
      "step": 690
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.9929937720298767,
      "eval_runtime": 1.7672,
      "eval_samples_per_second": 48.098,
      "eval_steps_per_second": 6.224,
      "step": 690
    },
    {
      "epoch": 10.07,
      "learning_rate": 0.00013543005707140074,
      "loss": 1.1894,
      "step": 695
    },
    {
      "epoch": 10.14,
      "learning_rate": 0.0001302115605879495,
      "loss": 1.2106,
      "step": 700
    },
    {
      "epoch": 10.22,
      "learning_rate": 0.00012181379454232323,
      "loss": 1.144,
      "step": 705
    },
    {
      "epoch": 10.29,
      "learning_rate": 0.00011067009906946301,
      "loss": 1.3006,
      "step": 710
    },
    {
      "epoch": 10.36,
      "learning_rate": 9.735550930058323e-05,
      "loss": 1.2147,
      "step": 715
    },
    {
      "epoch": 10.43,
      "learning_rate": 8.255708249541075e-05,
      "loss": 1.1931,
      "step": 720
    },
    {
      "epoch": 10.51,
      "learning_rate": 6.703844462707122e-05,
      "loss": 1.2735,
      "step": 725
    },
    {
      "epoch": 10.58,
      "learning_rate": 5.160038588088712e-05,
      "loss": 1.1695,
      "step": 730
    },
    {
      "epoch": 10.65,
      "learning_rate": 3.703953841164302e-05,
      "loss": 1.2219,
      "step": 735
    },
    {
      "epoch": 10.72,
      "learning_rate": 2.4107268662854985e-05,
      "loss": 1.1271,
      "step": 740
    },
    {
      "epoch": 10.8,
      "learning_rate": 1.3470905479788523e-05,
      "loss": 1.2963,
      "step": 745
    },
    {
      "epoch": 10.87,
      "learning_rate": 5.679304716725944e-06,
      "loss": 1.0029,
      "step": 750
    },
    {
      "epoch": 10.94,
      "learning_rate": 1.1345272679252971e-06,
      "loss": 1.2789,
      "step": 755
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.9721857309341431,
      "eval_runtime": 1.8495,
      "eval_samples_per_second": 45.957,
      "eval_steps_per_second": 5.947,
      "step": 759
    }
  ],
  "max_steps": 759,
  "num_train_epochs": 11,
  "total_flos": 785966432256000.0,
  "trial_name": null,
  "trial_params": null
}