{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 666.6666666666666,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 6.67,
      "learning_rate": 4.998766400914329e-05,
      "loss": 1.0516,
      "step": 10
    },
    {
      "epoch": 13.33,
      "learning_rate": 4.995066821070679e-05,
      "loss": 1.0167,
      "step": 20
    },
    {
      "epoch": 20.0,
      "learning_rate": 4.9889049115077005e-05,
      "loss": 0.9676,
      "step": 30
    },
    {
      "epoch": 26.67,
      "learning_rate": 4.980286753286195e-05,
      "loss": 0.888,
      "step": 40
    },
    {
      "epoch": 33.33,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 0.798,
      "step": 50
    },
    {
      "epoch": 40.0,
      "learning_rate": 4.9557181268217227e-05,
      "loss": 0.6272,
      "step": 60
    },
    {
      "epoch": 46.67,
      "learning_rate": 4.939791904846869e-05,
      "loss": 0.5097,
      "step": 70
    },
    {
      "epoch": 53.33,
      "learning_rate": 4.9214579028215776e-05,
      "loss": 0.3408,
      "step": 80
    },
    {
      "epoch": 60.0,
      "learning_rate": 4.900734214192358e-05,
      "loss": 0.1979,
      "step": 90
    },
    {
      "epoch": 66.67,
      "learning_rate": 4.877641290737884e-05,
      "loss": 0.109,
      "step": 100
    },
    {
      "epoch": 73.33,
      "learning_rate": 4.852201922385564e-05,
      "loss": 0.0503,
      "step": 110
    },
    {
      "epoch": 80.0,
      "learning_rate": 4.8244412147206284e-05,
      "loss": 0.0281,
      "step": 120
    },
    {
      "epoch": 86.67,
      "learning_rate": 4.794386564209953e-05,
      "loss": 0.0152,
      "step": 130
    },
    {
      "epoch": 93.33,
      "learning_rate": 4.762067631165049e-05,
      "loss": 0.0102,
      "step": 140
    },
    {
      "epoch": 100.0,
      "learning_rate": 4.72751631047092e-05,
      "loss": 0.0075,
      "step": 150
    },
    {
      "epoch": 106.67,
      "learning_rate": 4.690766700109659e-05,
      "loss": 0.0063,
      "step": 160
    },
    {
      "epoch": 113.33,
      "learning_rate": 4.65185506750986e-05,
      "loss": 0.0053,
      "step": 170
    },
    {
      "epoch": 120.0,
      "learning_rate": 4.610819813755038e-05,
      "loss": 0.0049,
      "step": 180
    },
    {
      "epoch": 126.67,
      "learning_rate": 4.567701435686404e-05,
      "loss": 0.0045,
      "step": 190
    },
    {
      "epoch": 133.33,
      "learning_rate": 4.522542485937369e-05,
      "loss": 0.0041,
      "step": 200
    },
    {
      "epoch": 140.0,
      "learning_rate": 4.4753875309392266e-05,
      "loss": 0.0038,
      "step": 210
    },
    {
      "epoch": 146.67,
      "learning_rate": 4.426283106939474e-05,
      "loss": 0.0036,
      "step": 220
    },
    {
      "epoch": 153.33,
      "learning_rate": 4.375277674076149e-05,
      "loss": 0.0035,
      "step": 230
    },
    {
      "epoch": 160.0,
      "learning_rate": 4.3224215685535294e-05,
      "loss": 0.0033,
      "step": 240
    },
    {
      "epoch": 166.67,
      "learning_rate": 4.267766952966369e-05,
      "loss": 0.0032,
      "step": 250
    },
    {
      "epoch": 173.33,
      "learning_rate": 4.211367764821722e-05,
      "loss": 0.0032,
      "step": 260
    },
    {
      "epoch": 180.0,
      "learning_rate": 4.1532796633091296e-05,
      "loss": 0.0031,
      "step": 270
    },
    {
      "epoch": 186.67,
      "learning_rate": 4.093559974371725e-05,
      "loss": 0.003,
      "step": 280
    },
    {
      "epoch": 193.33,
      "learning_rate": 4.0322676341324415e-05,
      "loss": 0.0029,
      "step": 290
    },
    {
      "epoch": 200.0,
      "learning_rate": 3.969463130731183e-05,
      "loss": 0.0029,
      "step": 300
    },
    {
      "epoch": 206.67,
      "learning_rate": 3.905208444630327e-05,
      "loss": 0.0029,
      "step": 310
    },
    {
      "epoch": 213.33,
      "learning_rate": 3.8395669874474915e-05,
      "loss": 0.0028,
      "step": 320
    },
    {
      "epoch": 220.0,
      "learning_rate": 3.7726035393759285e-05,
      "loss": 0.0028,
      "step": 330
    },
    {
      "epoch": 226.67,
      "learning_rate": 3.704384185254288e-05,
      "loss": 0.0027,
      "step": 340
    },
    {
      "epoch": 233.33,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.0027,
      "step": 350
    },
    {
      "epoch": 240.0,
      "learning_rate": 3.564448228912682e-05,
      "loss": 0.0027,
      "step": 360
    },
    {
      "epoch": 246.67,
      "learning_rate": 3.4928697265869515e-05,
      "loss": 0.0027,
      "step": 370
    },
    {
      "epoch": 253.33,
      "learning_rate": 3.4203113817116957e-05,
      "loss": 0.0028,
      "step": 380
    },
    {
      "epoch": 260.0,
      "learning_rate": 3.346844800613229e-05,
      "loss": 0.0027,
      "step": 390
    },
    {
      "epoch": 266.67,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.0027,
      "step": 400
    },
    {
      "epoch": 273.33,
      "learning_rate": 3.1974777650980735e-05,
      "loss": 0.0027,
      "step": 410
    },
    {
      "epoch": 280.0,
      "learning_rate": 3.121724717912138e-05,
      "loss": 0.0026,
      "step": 420
    },
    {
      "epoch": 286.67,
      "learning_rate": 3.045358103491357e-05,
      "loss": 0.0026,
      "step": 430
    },
    {
      "epoch": 293.33,
      "learning_rate": 2.9684532864643122e-05,
      "loss": 0.0026,
      "step": 440
    },
    {
      "epoch": 300.0,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 0.0026,
      "step": 450
    },
    {
      "epoch": 306.67,
      "learning_rate": 2.8133330839107608e-05,
      "loss": 0.0026,
      "step": 460
    },
    {
      "epoch": 313.33,
      "learning_rate": 2.7352707832962865e-05,
      "loss": 0.0026,
      "step": 470
    },
    {
      "epoch": 320.0,
      "learning_rate": 2.656976298823284e-05,
      "loss": 0.0026,
      "step": 480
    },
    {
      "epoch": 326.67,
      "learning_rate": 2.578526897695321e-05,
      "loss": 0.0026,
      "step": 490
    },
    {
      "epoch": 333.33,
      "learning_rate": 2.5e-05,
      "loss": 0.0026,
      "step": 500
    },
    {
      "epoch": 340.0,
      "learning_rate": 2.4214731023046793e-05,
      "loss": 0.0025,
      "step": 510
    },
    {
      "epoch": 346.67,
      "learning_rate": 2.3430237011767167e-05,
      "loss": 0.0026,
      "step": 520
    },
    {
      "epoch": 353.33,
      "learning_rate": 2.2647292167037144e-05,
      "loss": 0.0025,
      "step": 530
    },
    {
      "epoch": 360.0,
      "learning_rate": 2.186666916089239e-05,
      "loss": 0.0026,
      "step": 540
    },
    {
      "epoch": 366.67,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.0025,
      "step": 550
    },
    {
      "epoch": 373.33,
      "learning_rate": 2.031546713535688e-05,
      "loss": 0.0025,
      "step": 560
    },
    {
      "epoch": 380.0,
      "learning_rate": 1.9546418965086442e-05,
      "loss": 0.0025,
      "step": 570
    },
    {
      "epoch": 386.67,
      "learning_rate": 1.8782752820878634e-05,
      "loss": 0.0025,
      "step": 580
    },
    {
      "epoch": 393.33,
      "learning_rate": 1.802522234901927e-05,
      "loss": 0.0025,
      "step": 590
    },
    {
      "epoch": 400.0,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 0.0025,
      "step": 600
    },
    {
      "epoch": 406.67,
      "learning_rate": 1.6531551993867717e-05,
      "loss": 0.0025,
      "step": 610
    },
    {
      "epoch": 413.33,
      "learning_rate": 1.5796886182883053e-05,
      "loss": 0.0025,
      "step": 620
    },
    {
      "epoch": 420.0,
      "learning_rate": 1.5071302734130489e-05,
      "loss": 0.0025,
      "step": 630
    },
    {
      "epoch": 426.67,
      "learning_rate": 1.4355517710873184e-05,
      "loss": 0.0025,
      "step": 640
    },
    {
      "epoch": 433.33,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 0.0025,
      "step": 650
    },
    {
      "epoch": 440.0,
      "learning_rate": 1.2956158147457115e-05,
      "loss": 0.0025,
      "step": 660
    },
    {
      "epoch": 446.67,
      "learning_rate": 1.2273964606240718e-05,
      "loss": 0.0025,
      "step": 670
    },
    {
      "epoch": 453.33,
      "learning_rate": 1.1604330125525079e-05,
      "loss": 0.0025,
      "step": 680
    },
    {
      "epoch": 460.0,
      "learning_rate": 1.0947915553696742e-05,
      "loss": 0.0025,
      "step": 690
    },
    {
      "epoch": 466.67,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.0025,
      "step": 700
    },
    {
      "epoch": 473.33,
      "learning_rate": 9.677323658675594e-06,
      "loss": 0.0025,
      "step": 710
    },
    {
      "epoch": 480.0,
      "learning_rate": 9.064400256282757e-06,
      "loss": 0.0025,
      "step": 720
    },
    {
      "epoch": 486.67,
      "learning_rate": 8.467203366908707e-06,
      "loss": 0.0025,
      "step": 730
    },
    {
      "epoch": 493.33,
      "learning_rate": 7.886322351782783e-06,
      "loss": 0.0025,
      "step": 740
    },
    {
      "epoch": 500.0,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.0025,
      "step": 750
    },
    {
      "epoch": 506.67,
      "learning_rate": 6.775784314464717e-06,
      "loss": 0.0025,
      "step": 760
    },
    {
      "epoch": 513.33,
      "learning_rate": 6.247223259238511e-06,
      "loss": 0.0025,
      "step": 770
    },
    {
      "epoch": 520.0,
      "learning_rate": 5.737168930605272e-06,
      "loss": 0.0025,
      "step": 780
    },
    {
      "epoch": 526.67,
      "learning_rate": 5.24612469060774e-06,
      "loss": 0.0025,
      "step": 790
    },
    {
      "epoch": 533.33,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 0.0025,
      "step": 800
    },
    {
      "epoch": 540.0,
      "learning_rate": 4.322985643135952e-06,
      "loss": 0.0025,
      "step": 810
    },
    {
      "epoch": 546.67,
      "learning_rate": 3.891801862449629e-06,
      "loss": 0.0025,
      "step": 820
    },
    {
      "epoch": 553.33,
      "learning_rate": 3.4814493249014116e-06,
      "loss": 0.0025,
      "step": 830
    },
    {
      "epoch": 560.0,
      "learning_rate": 3.092332998903416e-06,
      "loss": 0.0025,
      "step": 840
    },
    {
      "epoch": 566.67,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.0025,
      "step": 850
    },
    {
      "epoch": 573.33,
      "learning_rate": 2.379323688349516e-06,
      "loss": 0.0025,
      "step": 860
    },
    {
      "epoch": 580.0,
      "learning_rate": 2.0561343579004715e-06,
      "loss": 0.0024,
      "step": 870
    },
    {
      "epoch": 586.67,
      "learning_rate": 1.7555878527937164e-06,
      "loss": 0.0025,
      "step": 880
    },
    {
      "epoch": 593.33,
      "learning_rate": 1.4779807761443636e-06,
      "loss": 0.0025,
      "step": 890
    },
    {
      "epoch": 600.0,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 0.0025,
      "step": 900
    },
    {
      "epoch": 606.67,
      "learning_rate": 9.926578580764234e-07,
      "loss": 0.0024,
      "step": 910
    },
    {
      "epoch": 613.33,
      "learning_rate": 7.854209717842231e-07,
      "loss": 0.0025,
      "step": 920
    },
    {
      "epoch": 620.0,
      "learning_rate": 6.020809515313142e-07,
      "loss": 0.0025,
      "step": 930
    },
    {
      "epoch": 626.67,
      "learning_rate": 4.4281873178278475e-07,
      "loss": 0.0025,
      "step": 940
    },
    {
      "epoch": 633.33,
      "learning_rate": 3.077914851215585e-07,
      "loss": 0.0025,
      "step": 950
    },
    {
      "epoch": 640.0,
      "learning_rate": 1.9713246713805588e-07,
      "loss": 0.0024,
      "step": 960
    },
    {
      "epoch": 646.67,
      "learning_rate": 1.109508849230001e-07,
      "loss": 0.0025,
      "step": 970
    },
    {
      "epoch": 653.33,
      "learning_rate": 4.9331789293211026e-08,
      "loss": 0.0025,
      "step": 980
    },
    {
      "epoch": 660.0,
      "learning_rate": 1.233599085671e-08,
      "loss": 0.0025,
      "step": 990
    },
    {
      "epoch": 666.67,
      "learning_rate": 0.0,
      "loss": 0.0025,
      "step": 1000
    },
    {
      "epoch": 666.67,
      "step": 1000,
      "total_flos": 1.3543137746092032e+17,
      "train_loss": 0.06853693281114101,
      "train_runtime": 2944.4055,
      "train_samples_per_second": 3.396,
      "train_steps_per_second": 0.34
    }
  ],
  "max_steps": 1000,
  "num_train_epochs": 1000,
  "total_flos": 1.3543137746092032e+17,
  "trial_name": null,
  "trial_params": null
}