{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 907,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.197802197802198e-06,
      "loss": 0.9976,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0989010989010989e-05,
      "loss": 1.0153,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.1978021978021977e-05,
      "loss": 0.9871,
      "step": 10
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.296703296703297e-05,
      "loss": 1.0189,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.3956043956043955e-05,
      "loss": 1.0091,
      "step": 20
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.494505494505495e-05,
      "loss": 1.0102,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.593406593406594e-05,
      "loss": 1.0129,
      "step": 30
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.692307692307693e-05,
      "loss": 0.9946,
      "step": 35
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.791208791208791e-05,
      "loss": 1.0025,
      "step": 40
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.89010989010989e-05,
      "loss": 1.0178,
      "step": 45
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001098901098901099,
      "loss": 1.0272,
      "step": 50
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00012087912087912087,
      "loss": 1.0014,
      "step": 55
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013186813186813188,
      "loss": 1.0247,
      "step": 60
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014285714285714287,
      "loss": 1.0231,
      "step": 65
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015384615384615385,
      "loss": 1.0145,
      "step": 70
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016483516483516484,
      "loss": 1.0011,
      "step": 75
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017582417582417582,
      "loss": 1.0068,
      "step": 80
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00018681318681318683,
      "loss": 0.9846,
      "step": 85
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001978021978021978,
      "loss": 1.0145,
      "step": 90
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001999881422898077,
      "loss": 1.0,
      "step": 95
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993997516168689,
      "loss": 1.0174,
      "step": 100
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019985477534331582,
      "loss": 0.9989,
      "step": 105
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001997325744054297,
      "loss": 0.9733,
      "step": 110
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019957341762950344,
      "loss": 0.9994,
      "step": 115
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019937736399097282,
      "loss": 1.0359,
      "step": 120
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.9979,
      "step": 125
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001988748703614594,
      "loss": 0.9894,
      "step": 130
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019856861656915143,
      "loss": 1.0121,
      "step": 135
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019822583824259283,
      "loss": 1.0195,
      "step": 140
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001978466623980609,
      "loss": 0.995,
      "step": 145
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019743122953890855,
      "loss": 1.0107,
      "step": 150
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019697969360350098,
      "loss": 0.9857,
      "step": 155
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001964922219081738,
      "loss": 1.0334,
      "step": 160
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019596899508523432,
      "loss": 1.019,
      "step": 165
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019541020701602813,
      "loss": 0.9974,
      "step": 170
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001948160647590966,
      "loss": 1.0064,
      "step": 175
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0001941867884734515,
      "loss": 0.9926,
      "step": 180
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019352261133699511,
      "loss": 1.0183,
      "step": 185
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019282377946011652,
      "loss": 1.0132,
      "step": 190
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001920905517944954,
      "loss": 1.0062,
      "step": 195
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019132320003714757,
      "loss": 1.0345,
      "step": 200
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019052200852974819,
      "loss": 1.012,
      "step": 205
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.9995,
      "step": 210
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018881930621796847,
      "loss": 1.0069,
      "step": 215
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018791842634877898,
      "loss": 1.0279,
      "step": 220
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018698496836612693,
      "loss": 1.0194,
      "step": 225
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018601927816223697,
      "loss": 1.0007,
      "step": 230
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018502171357296144,
      "loss": 1.0155,
      "step": 235
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018399264424518466,
      "loss": 1.0004,
      "step": 240
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018293245149985054,
      "loss": 0.9994,
      "step": 245
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018184152819066435,
      "loss": 0.9984,
      "step": 250
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018072027855852097,
      "loss": 1.0245,
      "step": 255
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017956911808171376,
      "loss": 0.9968,
      "step": 260
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017838847332197938,
      "loss": 1.028,
      "step": 265
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001771787817664356,
      "loss": 0.9899,
      "step": 270
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017594049166547073,
      "loss": 1.0358,
      "step": 275
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017467406186664474,
      "loss": 1.0091,
      "step": 280
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017337996164466373,
      "loss": 1.0222,
      "step": 285
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017205867052749025,
      "loss": 0.9967,
      "step": 290
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.9786,
      "step": 295
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001693364839158333,
      "loss": 0.9759,
      "step": 300
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016793659712575898,
      "loss": 0.9941,
      "step": 305
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016651153647553567,
      "loss": 1.0202,
      "step": 310
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001650618300204242,
      "loss": 1.0278,
      "step": 315
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016358801494817174,
      "loss": 1.0186,
      "step": 320
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016209063737995715,
      "loss": 1.0085,
      "step": 325
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001605702521680263,
      "loss": 1.0019,
      "step": 330
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015902742269009197,
      "loss": 1.0096,
      "step": 335
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0001574627206405744,
      "loss": 1.008,
      "step": 340
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001558767258187605,
      "loss": 1.0011,
      "step": 345
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015427002591395964,
      "loss": 1.0084,
      "step": 350
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0001526432162877356,
      "loss": 1.031,
      "step": 355
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015099689975329582,
      "loss": 1.007,
      "step": 360
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014933168635211956,
      "loss": 0.9927,
      "step": 365
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014764819312790707,
      "loss": 1.0098,
      "step": 370
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014594704389793477,
      "loss": 1.0088,
      "step": 375
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.9908,
      "step": 380
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0001424943051683422,
      "loss": 1.0318,
      "step": 385
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014074399507872456,
      "loss": 1.0263,
      "step": 390
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013897858732926793,
      "loss": 0.9932,
      "step": 395
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013719873609062077,
      "loss": 0.9938,
      "step": 400
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013540510088545652,
      "loss": 1.0161,
      "step": 405
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013359834634408827,
      "loss": 0.9879,
      "step": 410
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013177914195819016,
      "loss": 1.0165,
      "step": 415
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00012994816183271786,
      "loss": 1.0061,
      "step": 420
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012810608443611943,
      "loss": 1.0172,
      "step": 425
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012625359234892907,
      "loss": 1.0136,
      "step": 430
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012439137201083773,
      "loss": 1.0296,
      "step": 435
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012252011346633305,
      "loss": 0.9975,
      "step": 440
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012064051010900397,
      "loss": 1.0068,
      "step": 445
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011875325842460423,
      "loss": 0.9895,
      "step": 450
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011685905773296992,
      "loss": 1.0042,
      "step": 455
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011495860992888712,
      "loss": 1.0158,
      "step": 460
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011305261922200519,
      "loss": 1.0148,
      "step": 465
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011114179187589233,
      "loss": 1.0249,
      "step": 470
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010922683594633021,
      "loss": 0.9987,
      "step": 475
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010730846101894428,
      "loss": 1.0055,
      "step": 480
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010538737794626734,
      "loss": 1.0224,
      "step": 485
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010346429858433352,
      "loss": 1.0175,
      "step": 490
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010153993552890069,
      "loss": 1.0067,
      "step": 495
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.961500185139843e-05,
      "loss": 1.0056,
      "step": 500
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.76902108346999e-05,
      "loss": 0.996,
      "step": 505
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.57662757088155e-05,
      "loss": 0.9962,
      "step": 510
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.384390938660572e-05,
      "loss": 1.0193,
      "step": 515
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.192382419961208e-05,
      "loss": 1.0069,
      "step": 520
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.000673163410288e-05,
      "loss": 0.9859,
      "step": 525
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.809334206743251e-05,
      "loss": 1.0014,
      "step": 530
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.61843645048118e-05,
      "loss": 1.0002,
      "step": 535
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.428050631658629e-05,
      "loss": 1.0092,
      "step": 540
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.238247297612091e-05,
      "loss": 1.0051,
      "step": 545
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.049096779838719e-05,
      "loss": 0.9793,
      "step": 550
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.860669167935028e-05,
      "loss": 0.9934,
      "step": 555
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.673034283625258e-05,
      "loss": 0.9943,
      "step": 560
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.486261654888973e-05,
      "loss": 1.018,
      "step": 565
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.300420490197524e-05,
      "loss": 1.0168,
      "step": 570
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.115579652868878e-05,
      "loss": 1.0069,
      "step": 575
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.931807635550383e-05,
      "loss": 1.0093,
      "step": 580
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.749172534838848e-05,
      "loss": 0.9982,
      "step": 585
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.567742026047406e-05,
      "loss": 1.0051,
      "step": 590
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.387583338128471e-05,
      "loss": 0.9981,
      "step": 595
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.208763228762082e-05,
      "loss": 1.0285,
      "step": 600
    },
    {
      "epoch": 0.67,
      "learning_rate": 6.0313479596189134e-05,
      "loss": 0.9736,
      "step": 605
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.855403271807033e-05,
      "loss": 1.0014,
      "step": 610
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.680994361511591e-05,
      "loss": 1.0186,
      "step": 615
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.508185855836425e-05,
      "loss": 1.0168,
      "step": 620
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.337041788856518e-05,
      "loss": 1.0123,
      "step": 625
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.167625577890223e-05,
      "loss": 1.0272,
      "step": 630
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.000000000000002e-05,
      "loss": 1.0168,
      "step": 635
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.834227168730451e-05,
      "loss": 1.0421,
      "step": 640
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.670368511092166e-05,
      "loss": 1.0187,
      "step": 645
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.508484744799979e-05,
      "loss": 1.0103,
      "step": 650
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.3486358557740814e-05,
      "loss": 0.9988,
      "step": 655
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.1908810759122686e-05,
      "loss": 1.0021,
      "step": 660
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.0352788611415884e-05,
      "loss": 1.0118,
      "step": 665
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.881886869757565e-05,
      "loss": 1.0191,
      "step": 670
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.7307619410589376e-05,
      "loss": 1.0051,
      "step": 675
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.581960074285885e-05,
      "loss": 0.997,
      "step": 680
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.435536407869575e-05,
      "loss": 0.9964,
      "step": 685
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.291545199000636e-05,
      "loss": 1.0087,
      "step": 690
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.150039803524194e-05,
      "loss": 0.9939,
      "step": 695
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.0110726561689063e-05,
      "loss": 1.0096,
      "step": 700
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.874695251117303e-05,
      "loss": 1.0042,
      "step": 705
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7409581229246496e-05,
      "loss": 0.9954,
      "step": 710
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6099108277934103e-05,
      "loss": 1.0273,
      "step": 715
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.4816019252102273e-05,
      "loss": 1.0097,
      "step": 720
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3560789599522327e-05,
      "loss": 1.0043,
      "step": 725
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2333884444693652e-05,
      "loss": 0.9997,
      "step": 730
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.113575841649217e-05,
      "loss": 0.995,
      "step": 735
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9966855479707867e-05,
      "loss": 1.0051,
      "step": 740
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.882760877053388e-05,
      "loss": 0.9941,
      "step": 745
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7718440436068383e-05,
      "loss": 1.026,
      "step": 750
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.663976147788806e-05,
      "loss": 1.0037,
      "step": 755
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.55919715997518e-05,
      "loss": 1.0267,
      "step": 760
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.457545905949077e-05,
      "loss": 1.0115,
      "step": 765
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3590600525139763e-05,
      "loss": 1.0066,
      "step": 770
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.2637760935363053e-05,
      "loss": 1.0251,
      "step": 775
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1717293364226611e-05,
      "loss": 1.0204,
      "step": 780
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0829538890366864e-05,
      "loss": 1.0165,
      "step": 785
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.974826470604049e-06,
      "loss": 0.988,
      "step": 790
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.153472818047625e-06,
      "loss": 1.0213,
      "step": 795
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.365782284738488e-06,
      "loss": 0.9943,
      "step": 800
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.612046748871327e-06,
      "loss": 1.0327,
      "step": 805
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.892545506639558e-06,
      "loss": 1.0249,
      "step": 810
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.2075451687422124e-06,
      "loss": 1.0193,
      "step": 815
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.557299561591478e-06,
      "loss": 0.9919,
      "step": 820
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.942049633257673e-06,
      "loss": 1.0246,
      "step": 825
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.362023364185885e-06,
      "loss": 1.0219,
      "step": 830
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.817435682718096e-06,
      "loss": 1.0014,
      "step": 835
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.3084883854516137e-06,
      "loss": 1.0173,
      "step": 840
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.8353700624634494e-06,
      "loss": 0.9912,
      "step": 845
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.398256027428436e-06,
      "loss": 1.0085,
      "step": 850
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.9973082526568154e-06,
      "loss": 1.0114,
      "step": 855
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.6326753090755487e-06,
      "loss": 1.0128,
      "step": 860
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3044923111754427e-06,
      "loss": 0.9872,
      "step": 865
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0128808669445323e-06,
      "loss": 1.0028,
      "step": 870
    },
    {
      "epoch": 0.96,
      "learning_rate": 7.579490328064265e-07,
      "loss": 1.003,
      "step": 875
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.397912735799371e-07,
      "loss": 0.9967,
      "step": 880
    },
    {
      "epoch": 0.98,
      "learning_rate": 3.5848842747532306e-07,
      "loss": 0.9978,
      "step": 885
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.141076761396521e-07,
      "loss": 1.0215,
      "step": 890
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0670251976275803e-07,
      "loss": 1.0153,
      "step": 895
    },
    {
      "epoch": 0.99,
      "learning_rate": 3.6312757252743303e-08,
      "loss": 1.0008,
      "step": 900
    },
    {
      "epoch": 1.0,
      "learning_rate": 2.9644714885312953e-09,
      "loss": 1.0234,
      "step": 905
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.015771508216858,
      "eval_runtime": 455.9829,
      "eval_samples_per_second": 14.123,
      "eval_steps_per_second": 0.884,
      "step": 907
    },
    {
      "epoch": 1.0,
      "step": 907,
      "total_flos": 5.311564766957797e+18,
      "train_loss": 1.008174151806479,
      "train_runtime": 13465.8912,
      "train_samples_per_second": 4.31,
      "train_steps_per_second": 0.067
    }
  ],
  "logging_steps": 5,
  "max_steps": 907,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 5.311564766957797e+18,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}