{
  "best_metric": 0.536793053150177,
  "best_model_checkpoint": "output/eminem/checkpoint-1371",
  "epoch": 3.0,
  "global_step": 1371,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.3299239388716378e-07,
      "loss": 0.9607,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.216610996650382e-07,
      "loss": 0.966,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.920572031213835e-07,
      "loss": 0.9796,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 9.43857047145701e-07,
      "loss": 0.8739,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.3766395364652307e-06,
      "loss": 1.0099,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.88988664168433e-06,
      "loss": 0.9153,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.482984019353729e-06,
      "loss": 1.0177,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 3.1552217473210573e-06,
      "loss": 0.9735,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 3.905795174492246e-06,
      "loss": 0.8828,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.733805883976127e-06,
      "loss": 1.0567,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.638262768466535e-06,
      "loss": 0.9174,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 6.618083216572472e-06,
      "loss": 0.8727,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 7.6720944086741e-06,
      "loss": 0.9884,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 8.799034720759847e-06,
      "loss": 0.9629,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 9.997555234555936e-06,
      "loss": 0.927,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.1266221352147439e-05,
      "loss": 0.9882,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.260351451315264e-05,
      "loss": 1.1071,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.4007834012403411e-05,
      "loss": 0.9968,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.5477498915945732e-05,
      "loss": 0.8446,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7010750073074396e-05,
      "loss": 1.1172,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.8605752221991424e-05,
      "loss": 1.0285,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 2.026059618656475e-05,
      "loss": 1.1558,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 2.19733011615644e-05,
      "loss": 1.0706,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 2.3741817083633492e-05,
      "loss": 0.9304,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 2.5564027085162985e-05,
      "loss": 1.0108,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 2.7437750028125123e-05,
      "loss": 1.022,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 2.9360743114840418e-05,
      "loss": 0.9518,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 3.133070457254507e-05,
      "loss": 0.9963,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 3.334527640855787e-05,
      "loss": 0.9435,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 3.5402047232733056e-05,
      "loss": 0.955,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 3.749855514383242e-05,
      "loss": 0.9793,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 3.963229067635804e-05,
      "loss": 0.9688,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.180069980431374e-05,
      "loss": 0.9478,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.400118699831312e-05,
      "loss": 0.9073,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.62311183323573e-05,
      "loss": 0.8938,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.848782463657674e-05,
      "loss": 1.0837,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.076860469215926e-05,
      "loss": 0.964,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.307072846463586e-05,
      "loss": 0.9684,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.539144037166391e-05,
      "loss": 0.9341,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.772796258138569e-05,
      "loss": 0.8384,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 6.007749833742388e-05,
      "loss": 0.8859,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 6.243723530652334e-05,
      "loss": 0.9459,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 6.480434894484296e-05,
      "loss": 0.9548,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 6.717600587885728e-05,
      "loss": 0.9153,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.954936729683686e-05,
      "loss": 0.9542,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 7.192159234682828e-05,
      "loss": 0.9709,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 7.428984153708106e-05,
      "loss": 0.9535,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 7.665128013484648e-05,
      "loss": 0.9314,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 7.900308155947524e-05,
      "loss": 0.9481,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.134243076576675e-05,
      "loss": 1.0072,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.366652761350124e-05,
      "loss": 0.9006,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 8.597259021913684e-05,
      "loss": 1.1408,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.825785828564903e-05,
      "loss": 0.8856,
      "step": 265
    },
    {
      "epoch": 0.59,
      "learning_rate": 9.051959640653727e-05,
      "loss": 0.8189,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 9.275509734003362e-05,
      "loss": 0.9642,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 9.496168524960374e-05,
      "loss": 0.9964,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.713671890685066e-05,
      "loss": 1.0822,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 9.927759485299768e-05,
      "loss": 1.0476,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00010138175051516164,
      "loss": 1.182,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0001034466672736827,
      "loss": 1.0057,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00010546987347685174,
      "loss": 0.9401,
      "step": 305
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00010744894739940985,
      "loss": 1.1325,
      "step": 310
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001093815201412914,
      "loss": 1.0879,
      "step": 315
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00011126527846313655,
      "loss": 1.048,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0001130979675551757,
      "loss": 0.9551,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00011487739373618278,
      "loss": 0.9586,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.00011660142707925162,
      "loss": 0.9103,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00011826800396126513,
      "loss": 1.0702,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001198751295329933,
      "loss": 0.9897,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00012142088010688453,
      "loss": 0.9608,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00012290340545966183,
      "loss": 1.1265,
      "step": 355
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00012432093104699707,
      "loss": 1.0023,
      "step": 360
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00012567176012759186,
      "loss": 1.0231,
      "step": 365
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0001269542757941335,
      "loss": 1.1342,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00012816694290869156,
      "loss": 1.0269,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00012930830994023604,
      "loss": 1.1784,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001303770107020853,
      "loss": 1.1591,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00013137176598719403,
      "loss": 1.0692,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00013229138509933172,
      "loss": 0.9776,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00013313476727831364,
      "loss": 1.1472,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0001339009030175844,
      "loss": 1.1092,
      "step": 405
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013458887527256958,
      "loss": 1.0475,
      "step": 410
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013519786055835514,
      "loss": 1.0603,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0001357271299353754,
      "loss": 1.0979,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00013617604988193791,
      "loss": 1.1643,
      "step": 425
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013654408305253046,
      "loss": 1.1787,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00013683078892100969,
      "loss": 1.0679,
      "step": 435
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013703582430790026,
      "loss": 1.1034,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00013715894379117124,
      "loss": 1.2196,
      "step": 445
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0001372,
      "loss": 1.1973,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.8132181763648987,
      "eval_runtime": 8.3954,
      "eval_samples_per_second": 76.947,
      "eval_steps_per_second": 9.648,
      "step": 454
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00013715894379117126,
      "loss": 1.097,
      "step": 455
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001370358243079003,
      "loss": 1.0361,
      "step": 460
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00013683078892100974,
      "loss": 1.0419,
      "step": 465
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00013654408305253056,
      "loss": 0.9943,
      "step": 470
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00013617604988193802,
      "loss": 0.8492,
      "step": 475
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.0001357271299353755,
      "loss": 0.8659,
      "step": 480
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.00013519786055835527,
      "loss": 1.0681,
      "step": 485
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00013458887527256977,
      "loss": 0.8057,
      "step": 490
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0001339009030175846,
      "loss": 0.8735,
      "step": 495
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00013313476727831386,
      "loss": 1.0159,
      "step": 500
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00013229138509933196,
      "loss": 1.0634,
      "step": 505
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.0001313717659871943,
      "loss": 1.1331,
      "step": 510
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00013037701070208558,
      "loss": 1.0009,
      "step": 515
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00012930830994023633,
      "loss": 0.9342,
      "step": 520
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001281669429086919,
      "loss": 0.9788,
      "step": 525
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00012695427579413385,
      "loss": 0.9793,
      "step": 530
    },
    {
      "epoch": 1.18,
      "learning_rate": 0.0001256717601275922,
      "loss": 1.0848,
      "step": 535
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.00012432093104699745,
      "loss": 0.9297,
      "step": 540
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.00012290340545966224,
      "loss": 1.1117,
      "step": 545
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00012142088010688494,
      "loss": 1.1474,
      "step": 550
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.00011987512953299372,
      "loss": 0.9244,
      "step": 555
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.00011826800396126557,
      "loss": 1.1159,
      "step": 560
    },
    {
      "epoch": 1.24,
      "learning_rate": 0.00011660142707925208,
      "loss": 1.0104,
      "step": 565
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.00011487739373618326,
      "loss": 1.0571,
      "step": 570
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.00011309796755517619,
      "loss": 1.1123,
      "step": 575
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00011126527846313704,
      "loss": 0.8683,
      "step": 580
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.00010938152014129192,
      "loss": 0.9522,
      "step": 585
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.00010744894739941038,
      "loss": 0.9323,
      "step": 590
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.00010546987347685228,
      "loss": 0.8976,
      "step": 595
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00010344666727368325,
      "loss": 0.8812,
      "step": 600
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.00010138175051516221,
      "loss": 0.9468,
      "step": 605
    },
    {
      "epoch": 1.34,
      "learning_rate": 9.927759485299826e-05,
      "loss": 0.9565,
      "step": 610
    },
    {
      "epoch": 1.35,
      "learning_rate": 9.713671890685124e-05,
      "loss": 1.0534,
      "step": 615
    },
    {
      "epoch": 1.37,
      "learning_rate": 9.496168524960432e-05,
      "loss": 1.1313,
      "step": 620
    },
    {
      "epoch": 1.38,
      "learning_rate": 9.275509734003423e-05,
      "loss": 1.1094,
      "step": 625
    },
    {
      "epoch": 1.39,
      "learning_rate": 9.051959640653786e-05,
      "loss": 1.0261,
      "step": 630
    },
    {
      "epoch": 1.4,
      "learning_rate": 8.825785828564964e-05,
      "loss": 1.0947,
      "step": 635
    },
    {
      "epoch": 1.41,
      "learning_rate": 8.597259021913746e-05,
      "loss": 1.014,
      "step": 640
    },
    {
      "epoch": 1.42,
      "learning_rate": 8.366652761350186e-05,
      "loss": 0.9513,
      "step": 645
    },
    {
      "epoch": 1.43,
      "learning_rate": 8.134243076576737e-05,
      "loss": 1.0445,
      "step": 650
    },
    {
      "epoch": 1.44,
      "learning_rate": 7.900308155947589e-05,
      "loss": 0.9315,
      "step": 655
    },
    {
      "epoch": 1.45,
      "learning_rate": 7.665128013484713e-05,
      "loss": 1.0082,
      "step": 660
    },
    {
      "epoch": 1.46,
      "learning_rate": 7.42898415370817e-05,
      "loss": 1.0051,
      "step": 665
    },
    {
      "epoch": 1.48,
      "learning_rate": 7.192159234682893e-05,
      "loss": 1.0477,
      "step": 670
    },
    {
      "epoch": 1.49,
      "learning_rate": 6.95493672968375e-05,
      "loss": 1.0178,
      "step": 675
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.717600587885793e-05,
      "loss": 0.9478,
      "step": 680
    },
    {
      "epoch": 1.51,
      "learning_rate": 6.48043489448436e-05,
      "loss": 1.0712,
      "step": 685
    },
    {
      "epoch": 1.52,
      "learning_rate": 6.243723530652398e-05,
      "loss": 1.0546,
      "step": 690
    },
    {
      "epoch": 1.53,
      "learning_rate": 6.0077498337424516e-05,
      "loss": 0.9993,
      "step": 695
    },
    {
      "epoch": 1.54,
      "learning_rate": 5.772796258138633e-05,
      "loss": 1.0692,
      "step": 700
    },
    {
      "epoch": 1.55,
      "learning_rate": 5.5391440371664534e-05,
      "loss": 0.784,
      "step": 705
    },
    {
      "epoch": 1.56,
      "learning_rate": 5.307072846463648e-05,
      "loss": 1.0026,
      "step": 710
    },
    {
      "epoch": 1.57,
      "learning_rate": 5.0768604692159876e-05,
      "loss": 1.0188,
      "step": 715
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.848782463657735e-05,
      "loss": 1.1097,
      "step": 720
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.623111833235789e-05,
      "loss": 0.8797,
      "step": 725
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.400118699831371e-05,
      "loss": 0.9968,
      "step": 730
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.180069980431433e-05,
      "loss": 0.9446,
      "step": 735
    },
    {
      "epoch": 1.63,
      "learning_rate": 3.9632290676358616e-05,
      "loss": 0.9644,
      "step": 740
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.749855514383298e-05,
      "loss": 0.9931,
      "step": 745
    },
    {
      "epoch": 1.65,
      "learning_rate": 3.540204723273361e-05,
      "loss": 0.846,
      "step": 750
    },
    {
      "epoch": 1.66,
      "learning_rate": 3.3345276408558416e-05,
      "loss": 0.8853,
      "step": 755
    },
    {
      "epoch": 1.67,
      "learning_rate": 3.1330704572545604e-05,
      "loss": 1.0022,
      "step": 760
    },
    {
      "epoch": 1.69,
      "learning_rate": 2.9360743114840946e-05,
      "loss": 0.9714,
      "step": 765
    },
    {
      "epoch": 1.7,
      "learning_rate": 2.743775002812563e-05,
      "loss": 0.9134,
      "step": 770
    },
    {
      "epoch": 1.71,
      "learning_rate": 2.556402708516349e-05,
      "loss": 1.0328,
      "step": 775
    },
    {
      "epoch": 1.72,
      "learning_rate": 2.374181708363397e-05,
      "loss": 0.9452,
      "step": 780
    },
    {
      "epoch": 1.73,
      "learning_rate": 2.197330116156487e-05,
      "loss": 0.9128,
      "step": 785
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.0260596186565206e-05,
      "loss": 0.8532,
      "step": 790
    },
    {
      "epoch": 1.75,
      "learning_rate": 1.8605752221991858e-05,
      "loss": 1.0068,
      "step": 795
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.7010750073074816e-05,
      "loss": 0.954,
      "step": 800
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.5477498915946135e-05,
      "loss": 0.955,
      "step": 805
    },
    {
      "epoch": 1.78,
      "learning_rate": 1.40078340124038e-05,
      "loss": 0.8937,
      "step": 810
    },
    {
      "epoch": 1.8,
      "learning_rate": 1.2603514513153006e-05,
      "loss": 0.8846,
      "step": 815
    },
    {
      "epoch": 1.81,
      "learning_rate": 1.126622135214779e-05,
      "loss": 0.9227,
      "step": 820
    },
    {
      "epoch": 1.82,
      "learning_rate": 9.997555234556263e-06,
      "loss": 0.9755,
      "step": 825
    },
    {
      "epoch": 1.83,
      "learning_rate": 8.799034720760158e-06,
      "loss": 1.0972,
      "step": 830
    },
    {
      "epoch": 1.84,
      "learning_rate": 7.672094408674397e-06,
      "loss": 1.0254,
      "step": 835
    },
    {
      "epoch": 1.85,
      "learning_rate": 6.618083216572745e-06,
      "loss": 0.9993,
      "step": 840
    },
    {
      "epoch": 1.86,
      "learning_rate": 5.638262768466794e-06,
      "loss": 0.9833,
      "step": 845
    },
    {
      "epoch": 1.87,
      "learning_rate": 4.733805883976356e-06,
      "loss": 0.9683,
      "step": 850
    },
    {
      "epoch": 1.88,
      "learning_rate": 3.905795174492459e-06,
      "loss": 1.0143,
      "step": 855
    },
    {
      "epoch": 1.89,
      "learning_rate": 3.155221747321248e-06,
      "loss": 1.0293,
      "step": 860
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.482984019353904e-06,
      "loss": 0.9645,
      "step": 865
    },
    {
      "epoch": 1.92,
      "learning_rate": 1.8898866416844749e-06,
      "loss": 0.9395,
      "step": 870
    },
    {
      "epoch": 1.93,
      "learning_rate": 1.37663953646536e-06,
      "loss": 1.0553,
      "step": 875
    },
    {
      "epoch": 1.94,
      "learning_rate": 9.438570471458076e-07,
      "loss": 1.0763,
      "step": 880
    },
    {
      "epoch": 1.95,
      "learning_rate": 5.920572031214673e-07,
      "loss": 0.987,
      "step": 885
    },
    {
      "epoch": 1.96,
      "learning_rate": 3.216610996650991e-07,
      "loss": 1.0021,
      "step": 890
    },
    {
      "epoch": 1.97,
      "learning_rate": 1.3299239388720947e-07,
      "loss": 0.8033,
      "step": 895
    },
    {
      "epoch": 1.98,
      "learning_rate": 2.6276917326665837e-08,
      "loss": 1.0829,
      "step": 900
    },
    {
      "epoch": 1.99,
      "learning_rate": 1.6424056362936757e-09,
      "loss": 0.9621,
      "step": 905
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.8025060296058655,
      "eval_runtime": 8.3951,
      "eval_samples_per_second": 76.95,
      "eval_steps_per_second": 9.649,
      "step": 908
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.939154059863554e-05,
      "loss": 1.0652,
      "step": 910
    },
    {
      "epoch": 2.03,
      "learning_rate": 4.157558500206058e-05,
      "loss": 0.9825,
      "step": 915
    },
    {
      "epoch": 2.04,
      "learning_rate": 4.379255449236861e-05,
      "loss": 0.8959,
      "step": 920
    },
    {
      "epoch": 2.06,
      "learning_rate": 4.603974803373273e-05,
      "loss": 1.0768,
      "step": 925
    },
    {
      "epoch": 2.07,
      "learning_rate": 4.831442776697826e-05,
      "loss": 0.9137,
      "step": 930
    },
    {
      "epoch": 2.08,
      "learning_rate": 5.061382234523686e-05,
      "loss": 0.9653,
      "step": 935
    },
    {
      "epoch": 2.09,
      "learning_rate": 5.293513031040953e-05,
      "loss": 0.921,
      "step": 940
    },
    {
      "epoch": 2.1,
      "learning_rate": 5.527552350630886e-05,
      "loss": 0.9621,
      "step": 945
    },
    {
      "epoch": 2.11,
      "learning_rate": 5.763215052433939e-05,
      "loss": 0.933,
      "step": 950
    },
    {
      "epoch": 2.12,
      "learning_rate": 6.000214017748833e-05,
      "loss": 1.1698,
      "step": 955
    },
    {
      "epoch": 2.13,
      "learning_rate": 6.238260499843221e-05,
      "loss": 1.0466,
      "step": 960
    },
    {
      "epoch": 2.14,
      "learning_rate": 6.477064475746826e-05,
      "loss": 0.9793,
      "step": 965
    },
    {
      "epoch": 2.16,
      "learning_rate": 6.716334999600135e-05,
      "loss": 1.0029,
      "step": 970
    },
    {
      "epoch": 2.17,
      "learning_rate": 6.955780557126535e-05,
      "loss": 0.901,
      "step": 975
    },
    {
      "epoch": 2.18,
      "learning_rate": 7.195109420797938e-05,
      "loss": 0.8933,
      "step": 980
    },
    {
      "epoch": 2.19,
      "learning_rate": 7.434030005259555e-05,
      "loss": 0.9533,
      "step": 985
    },
    {
      "epoch": 2.2,
      "learning_rate": 7.672251222582502e-05,
      "loss": 1.0477,
      "step": 990
    },
    {
      "epoch": 2.21,
      "learning_rate": 7.90948283690844e-05,
      "loss": 1.0604,
      "step": 995
    },
    {
      "epoch": 2.22,
      "learning_rate": 8.145435818058043e-05,
      "loss": 1.0593,
      "step": 1000
    },
    {
      "epoch": 2.23,
      "learning_rate": 8.379822693669456e-05,
      "loss": 0.889,
      "step": 1005
    },
    {
      "epoch": 2.24,
      "learning_rate": 8.612357899439467e-05,
      "loss": 1.0466,
      "step": 1010
    },
    {
      "epoch": 2.26,
      "learning_rate": 8.842758127039052e-05,
      "loss": 0.8741,
      "step": 1015
    },
    {
      "epoch": 2.27,
      "learning_rate": 9.070742669281316e-05,
      "loss": 0.9787,
      "step": 1020
    },
    {
      "epoch": 2.28,
      "learning_rate": 9.296033762119679e-05,
      "loss": 0.9187,
      "step": 1025
    },
    {
      "epoch": 2.29,
      "learning_rate": 9.518356923061407e-05,
      "loss": 0.918,
      "step": 1030
    },
    {
      "epoch": 2.3,
      "learning_rate": 9.737441285580787e-05,
      "loss": 0.887,
      "step": 1035
    },
    {
      "epoch": 2.31,
      "learning_rate": 9.953019929129537e-05,
      "loss": 1.0572,
      "step": 1040
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00010164830204337668,
      "loss": 0.9164,
      "step": 1045
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.00010372614053012052,
      "loss": 0.9702,
      "step": 1050
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00010576118322539557,
      "loss": 1.0737,
      "step": 1055
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00010775095074315191,
      "loss": 0.9764,
      "step": 1060
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.00010969301885816937,
      "loss": 1.0461,
      "step": 1065
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.00011158502145960167,
      "loss": 1.034,
      "step": 1070
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.00011342465343372117,
      "loss": 0.9559,
      "step": 1075
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00011520967347234022,
      "loss": 1.0916,
      "step": 1080
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.00011693790680350301,
      "loss": 0.9443,
      "step": 1085
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00011860724784110814,
      "loss": 0.9271,
      "step": 1090
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.00012021566275024623,
      "loss": 0.9245,
      "step": 1095
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00012176119192510649,
      "loss": 0.8889,
      "step": 1100
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.00012324195237645988,
      "loss": 0.9344,
      "step": 1105
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00012465614002578945,
      "loss": 1.0672,
      "step": 1110
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.0001260020319032846,
      "loss": 0.9582,
      "step": 1115
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00012727798824701078,
      "loss": 0.9114,
      "step": 1120
    },
    {
      "epoch": 2.5,
      "learning_rate": 0.00012848245450070912,
      "loss": 1.1439,
      "step": 1125
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00012961396320778244,
      "loss": 1.0116,
      "step": 1130
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.00013067113579916855,
      "loss": 0.8955,
      "step": 1135
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00013165268427290888,
      "loss": 1.1116,
      "step": 1140
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.0001325574127633844,
      "loss": 0.9538,
      "step": 1145
    },
    {
      "epoch": 2.56,
      "learning_rate": 0.00013338421899829092,
      "loss": 1.0351,
      "step": 1150
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00013413209564159262,
      "loss": 1.0751,
      "step": 1155
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.0001348001315208005,
      "loss": 1.0118,
      "step": 1160
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00013538751273709884,
      "loss": 1.0048,
      "step": 1165
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.00013589352365695444,
      "loss": 1.0141,
      "step": 1170
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00013631754778400696,
      "loss": 1.0117,
      "step": 1175
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.0001366590685101732,
      "loss": 1.0794,
      "step": 1180
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00013691766974505563,
      "loss": 1.1812,
      "step": 1185
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.00013709303642288383,
      "loss": 1.2511,
      "step": 1190
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001371849548863744,
      "loss": 0.8512,
      "step": 1195
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.00013719331314703827,
      "loss": 1.0474,
      "step": 1200
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00013711810102162237,
      "loss": 1.0574,
      "step": 1205
    },
    {
      "epoch": 2.69,
      "learning_rate": 0.00013695941014451606,
      "loss": 1.2136,
      "step": 1210
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00013671743385610847,
      "loss": 1.1405,
      "step": 1215
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.00013639246696723354,
      "loss": 0.9608,
      "step": 1220
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.000135984905399988,
      "loss": 1.0797,
      "step": 1225
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.00013549524570536192,
      "loss": 1.1173,
      "step": 1230
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.00013492408445826617,
      "loss": 1.0319,
      "step": 1235
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0001342721175307,
      "loss": 1.1431,
      "step": 1240
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.00013354013924393685,
      "loss": 1.1817,
      "step": 1245
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00013272904140076693,
      "loss": 1.1562,
      "step": 1250
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.00013183981219897135,
      "loss": 0.9705,
      "step": 1255
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.00013087353502735764,
      "loss": 0.9752,
      "step": 1260
    },
    {
      "epoch": 2.81,
      "learning_rate": 0.00012983138714581574,
      "loss": 1.1247,
      "step": 1265
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.00012871463825100976,
      "loss": 1.001,
      "step": 1270
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00012752464892944418,
      "loss": 1.0426,
      "step": 1275
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.00012626286899980387,
      "loss": 1.128,
      "step": 1280
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0001249308357465718,
      "loss": 1.1501,
      "step": 1285
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.0001235301720470826,
      "loss": 0.9987,
      "step": 1290
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.00012206258439429962,
      "loss": 1.1401,
      "step": 1295
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.0001205298608177108,
      "loss": 0.9013,
      "step": 1300
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0001189338687048974,
      "loss": 1.0983,
      "step": 1305
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00011727655252640518,
      "loss": 1.0951,
      "step": 1310
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.00011555993146670835,
      "loss": 1.097,
      "step": 1315
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00011378609696414153,
      "loss": 1.1505,
      "step": 1320
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.00011195721016280857,
      "loss": 1.0955,
      "step": 1325
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.00011007549927955844,
      "loss": 1.0874,
      "step": 1330
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00010814325688924864,
      "loss": 1.04,
      "step": 1335
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00010616283713158952,
      "loss": 1.1124,
      "step": 1340
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00010413665284299701,
      "loss": 1.0374,
      "step": 1345
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00010206717261691705,
      "loss": 1.103,
      "step": 1350
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.6717901825904846,
      "eval_runtime": 32.3216,
      "eval_samples_per_second": 21.1,
      "eval_steps_per_second": 2.661,
      "step": 1350
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0001141037890981026,
      "loss": 0.9662,
      "step": 1355
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.00011584107440876515,
      "loss": 0.9781,
      "step": 1360
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00011752255327383569,
      "loss": 1.0047,
      "step": 1365
    },
    {
      "epoch": 3.0,
      "learning_rate": 0.00011914623934224141,
      "loss": 1.0306,
      "step": 1370
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.536793053150177,
      "eval_runtime": 27.1721,
      "eval_samples_per_second": 23.002,
      "eval_steps_per_second": 2.907,
      "step": 1371
    }
  ],
  "max_steps": 1828,
  "num_train_epochs": 4,
  "total_flos": 1431619043328000.0,
  "trial_name": null,
  "trial_params": null
}