{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9995764506565015,
  "eval_steps": 500,
  "global_step": 1180,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.6949152542372882e-06,
      "loss": 1.9981,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.47457627118644e-06,
      "loss": 2.0358,
      "step": 5
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.694915254237288e-05,
      "loss": 1.9674,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 2.5423728813559322e-05,
      "loss": 1.6753,
      "step": 15
    },
    {
      "epoch": 0.02,
      "learning_rate": 3.389830508474576e-05,
      "loss": 1.277,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.2372881355932206e-05,
      "loss": 0.9453,
      "step": 25
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.0847457627118643e-05,
      "loss": 0.7953,
      "step": 30
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.932203389830509e-05,
      "loss": 0.7426,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 6.779661016949152e-05,
      "loss": 0.6909,
      "step": 40
    },
    {
      "epoch": 0.04,
      "learning_rate": 7.627118644067796e-05,
      "loss": 0.723,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.474576271186441e-05,
      "loss": 0.6646,
      "step": 50
    },
    {
      "epoch": 0.05,
      "learning_rate": 9.322033898305085e-05,
      "loss": 0.6685,
      "step": 55
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00010169491525423729,
      "loss": 0.6565,
      "step": 60
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011016949152542372,
      "loss": 0.6032,
      "step": 65
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00011864406779661017,
      "loss": 0.6357,
      "step": 70
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0001271186440677966,
      "loss": 0.641,
      "step": 75
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013559322033898305,
      "loss": 0.581,
      "step": 80
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00014406779661016949,
      "loss": 0.5263,
      "step": 85
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00015254237288135592,
      "loss": 0.5573,
      "step": 90
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016101694915254236,
      "loss": 0.4486,
      "step": 95
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00016949152542372882,
      "loss": 0.4374,
      "step": 100
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00017796610169491526,
      "loss": 0.4425,
      "step": 105
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001864406779661017,
      "loss": 0.4849,
      "step": 110
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019491525423728814,
      "loss": 0.3484,
      "step": 115
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019999824983320177,
      "loss": 0.3903,
      "step": 120
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019997856116026692,
      "loss": 0.3913,
      "step": 125
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019993700042749937,
      "loss": 0.3313,
      "step": 130
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019987357672703672,
      "loss": 0.3447,
      "step": 135
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001997883039339234,
      "loss": 0.3978,
      "step": 140
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.000199681200703075,
      "loss": 0.3689,
      "step": 145
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001995522904651977,
      "loss": 0.3055,
      "step": 150
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019940160142166172,
      "loss": 0.3499,
      "step": 155
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019922916653833248,
      "loss": 0.3107,
      "step": 160
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019903502353835813,
      "loss": 0.313,
      "step": 165
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019881921489391737,
      "loss": 0.3267,
      "step": 170
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019858178781692774,
      "loss": 0.3396,
      "step": 175
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00019832279424871719,
      "loss": 0.3315,
      "step": 180
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019804229084866102,
      "loss": 0.2894,
      "step": 185
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019774033898178667,
      "loss": 0.2326,
      "step": 190
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019741700470534906,
      "loss": 0.2904,
      "step": 195
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019707235875437933,
      "loss": 0.2489,
      "step": 200
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019670647652621041,
      "loss": 0.231,
      "step": 205
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019631943806398252,
      "loss": 0.2691,
      "step": 210
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001959113280391322,
      "loss": 0.3092,
      "step": 215
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001954822357328692,
      "loss": 0.2461,
      "step": 220
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0001950322550166444,
      "loss": 0.2451,
      "step": 225
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019456148433161387,
      "loss": 0.2183,
      "step": 230
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019407002666710336,
      "loss": 0.2332,
      "step": 235
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019355798953807715,
      "loss": 0.2203,
      "step": 240
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019302548496161765,
      "loss": 0.2358,
      "step": 245
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0001924726294324196,
      "loss": 0.2191,
      "step": 250
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019189954389730468,
      "loss": 0.2226,
      "step": 255
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019130635372876246,
      "loss": 0.2194,
      "step": 260
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019069318869752283,
      "loss": 0.1904,
      "step": 265
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019006018294416647,
      "loss": 0.2449,
      "step": 270
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00018940747494977932,
      "loss": 0.2084,
      "step": 275
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018873520750565718,
      "loss": 0.2174,
      "step": 280
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00018804352768206782,
      "loss": 0.2243,
      "step": 285
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018733258679607672,
      "loss": 0.1996,
      "step": 290
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.2254,
      "step": 295
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00018585354813959858,
      "loss": 0.2027,
      "step": 300
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018508577393470013,
      "loss": 0.2096,
      "step": 305
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00018429938572779152,
      "loss": 0.1661,
      "step": 310
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018349455555505446,
      "loss": 0.2263,
      "step": 315
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00018267145948717338,
      "loss": 0.1851,
      "step": 320
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001818302775908169,
      "loss": 0.1796,
      "step": 325
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00018097119388924525,
      "loss": 0.1906,
      "step": 330
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001800943963220516,
      "loss": 0.1766,
      "step": 335
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001792000767040474,
      "loss": 0.1615,
      "step": 340
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00017828843068329924,
      "loss": 0.1624,
      "step": 345
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017735965769832753,
      "loss": 0.1694,
      "step": 350
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017641396093447592,
      "loss": 0.18,
      "step": 355
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00017545154727946065,
      "loss": 0.1672,
      "step": 360
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017447262727811062,
      "loss": 0.1708,
      "step": 365
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.00017347741508630672,
      "loss": 0.1739,
      "step": 370
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017246612842413173,
      "loss": 0.1595,
      "step": 375
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00017143898852824003,
      "loss": 0.1739,
      "step": 380
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001703962201034583,
      "loss": 0.1701,
      "step": 385
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016933805127362743,
      "loss": 0.1549,
      "step": 390
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00016826471353169646,
      "loss": 0.1693,
      "step": 395
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0001671764416890793,
      "loss": 0.1541,
      "step": 400
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00016607347382428578,
      "loss": 0.1554,
      "step": 405
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0001649560512308378,
      "loss": 0.1635,
      "step": 410
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00016382441836448202,
      "loss": 0.1499,
      "step": 415
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00016267882278971101,
      "loss": 0.1501,
      "step": 420
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001615195151256042,
      "loss": 0.1634,
      "step": 425
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0001603467489910004,
      "loss": 0.1623,
      "step": 430
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015916078094901445,
      "loss": 0.1666,
      "step": 435
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00015796187045090943,
      "loss": 0.1718,
      "step": 440
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001567502797793372,
      "loss": 0.162,
      "step": 445
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0001555262739909594,
      "loss": 0.166,
      "step": 450
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015429012085846182,
      "loss": 0.1682,
      "step": 455
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015304209081197425,
      "loss": 0.172,
      "step": 460
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00015178245687990938,
      "loss": 0.1414,
      "step": 465
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00015051149462923285,
      "loss": 0.1778,
      "step": 470
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00014922948210517822,
      "loss": 0.1411,
      "step": 475
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014793669977041977,
      "loss": 0.156,
      "step": 480
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00014663343044371633,
      "loss": 0.1383,
      "step": 485
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014531995923803973,
      "loss": 0.1653,
      "step": 490
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014399657349820134,
      "loss": 0.1507,
      "step": 495
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00014266356273799044,
      "loss": 0.1413,
      "step": 500
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00014132121857683783,
      "loss": 0.1659,
      "step": 505
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0001399698346760192,
      "loss": 0.1468,
      "step": 510
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013860970667441147,
      "loss": 0.1211,
      "step": 515
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0001372411321238166,
      "loss": 0.1353,
      "step": 520
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00013586441042386693,
      "loss": 0.1566,
      "step": 525
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00013447984275652636,
      "loss": 0.1449,
      "step": 530
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001330877320202014,
      "loss": 0.1635,
      "step": 535
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001316883827634769,
      "loss": 0.135,
      "step": 540
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.00013028210111849076,
      "loss": 0.1441,
      "step": 545
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0001288691947339621,
      "loss": 0.1637,
      "step": 550
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012744997270788775,
      "loss": 0.1479,
      "step": 555
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00012602474551992165,
      "loss": 0.1404,
      "step": 560
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012459382496345198,
      "loss": 0.1442,
      "step": 565
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00012315752407739093,
      "loss": 0.1464,
      "step": 570
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0001217161570776919,
      "loss": 0.1337,
      "step": 575
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00012027003928860937,
      "loss": 0.1497,
      "step": 580
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011881948707371608,
      "loss": 0.1451,
      "step": 585
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011736481776669306,
      "loss": 0.1421,
      "step": 590
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00011590634960190721,
      "loss": 0.1286,
      "step": 595
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011444440164479215,
      "loss": 0.1421,
      "step": 600
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00011297929372204692,
      "loss": 0.1374,
      "step": 605
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00011151134635166829,
      "loss": 0.1502,
      "step": 610
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.000110040880672832,
      "loss": 0.159,
      "step": 615
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010856821837563769,
      "loss": 0.1316,
      "step": 620
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010709368163073386,
      "loss": 0.1271,
      "step": 625
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00010561759301883714,
      "loss": 0.1289,
      "step": 630
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010414027546016222,
      "loss": 0.146,
      "step": 635
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.00010266205214377748,
      "loss": 0.1417,
      "step": 640
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00010118324645690161,
      "loss": 0.1563,
      "step": 645
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.970418191415703e-05,
      "loss": 0.1432,
      "step": 650
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.822518208679542e-05,
      "loss": 0.1336,
      "step": 655
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.674657053191079e-05,
      "loss": 0.1216,
      "step": 660
    },
    {
      "epoch": 0.56,
      "learning_rate": 9.526867072165581e-05,
      "loss": 0.1379,
      "step": 665
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.379180597247661e-05,
      "loss": 0.1471,
      "step": 670
    },
    {
      "epoch": 0.57,
      "learning_rate": 9.231629937438142e-05,
      "loss": 0.1385,
      "step": 675
    },
    {
      "epoch": 0.58,
      "learning_rate": 9.084247372025937e-05,
      "loss": 0.1532,
      "step": 680
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.937065143526347e-05,
      "loss": 0.1337,
      "step": 685
    },
    {
      "epoch": 0.58,
      "learning_rate": 8.790115450627485e-05,
      "loss": 0.1539,
      "step": 690
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.64343044114622e-05,
      "loss": 0.1218,
      "step": 695
    },
    {
      "epoch": 0.59,
      "learning_rate": 8.497042204995299e-05,
      "loss": 0.1282,
      "step": 700
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.350982767163104e-05,
      "loss": 0.1215,
      "step": 705
    },
    {
      "epoch": 0.6,
      "learning_rate": 8.205284080707634e-05,
      "loss": 0.129,
      "step": 710
    },
    {
      "epoch": 0.61,
      "learning_rate": 8.059978019766219e-05,
      "loss": 0.1435,
      "step": 715
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.915096372582466e-05,
      "loss": 0.1378,
      "step": 720
    },
    {
      "epoch": 0.61,
      "learning_rate": 7.770670834552074e-05,
      "loss": 0.1361,
      "step": 725
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.626733001288851e-05,
      "loss": 0.127,
      "step": 730
    },
    {
      "epoch": 0.62,
      "learning_rate": 7.483314361712685e-05,
      "loss": 0.1344,
      "step": 735
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.340446291160732e-05,
      "loss": 0.1439,
      "step": 740
    },
    {
      "epoch": 0.63,
      "learning_rate": 7.198160044523554e-05,
      "loss": 0.1239,
      "step": 745
    },
    {
      "epoch": 0.64,
      "learning_rate": 7.056486749407551e-05,
      "loss": 0.135,
      "step": 750
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.915457399325242e-05,
      "loss": 0.1532,
      "step": 755
    },
    {
      "epoch": 0.64,
      "learning_rate": 6.775102846914911e-05,
      "loss": 0.1206,
      "step": 760
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.635453797191034e-05,
      "loss": 0.1312,
      "step": 765
    },
    {
      "epoch": 0.65,
      "learning_rate": 6.496540800827036e-05,
      "loss": 0.1366,
      "step": 770
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.358394247471778e-05,
      "loss": 0.1473,
      "step": 775
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.221044359101317e-05,
      "loss": 0.13,
      "step": 780
    },
    {
      "epoch": 0.66,
      "learning_rate": 6.084521183407286e-05,
      "loss": 0.1126,
      "step": 785
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.9488545872234645e-05,
      "loss": 0.1235,
      "step": 790
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.8140742499918756e-05,
      "loss": 0.1425,
      "step": 795
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.680209657269871e-05,
      "loss": 0.1386,
      "step": 800
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.547290094279687e-05,
      "loss": 0.1325,
      "step": 805
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.4153446395017537e-05,
      "loss": 0.1237,
      "step": 810
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.2844021583132983e-05,
      "loss": 0.126,
      "step": 815
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.1544912966734994e-05,
      "loss": 0.1205,
      "step": 820
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.025640474856732e-05,
      "loss": 0.1358,
      "step": 825
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.897877881235091e-05,
      "loss": 0.1269,
      "step": 830
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.771231466111725e-05,
      "loss": 0.1173,
      "step": 835
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.645728935606194e-05,
      "loss": 0.1261,
      "step": 840
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.5213977455932785e-05,
      "loss": 0.1302,
      "step": 845
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.398265095696539e-05,
      "loss": 0.1237,
      "step": 850
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.2763579233379025e-05,
      "loss": 0.1214,
      "step": 855
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.155702897844641e-05,
      "loss": 0.1409,
      "step": 860
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.036326414614985e-05,
      "loss": 0.1182,
      "step": 865
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.918254589343683e-05,
      "loss": 0.138,
      "step": 870
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.8015132523087116e-05,
      "loss": 0.1221,
      "step": 875
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.686127942720463e-05,
      "loss": 0.1381,
      "step": 880
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.5721239031346066e-05,
      "loss": 0.1386,
      "step": 885
    },
    {
      "epoch": 0.75,
      "learning_rate": 3.459526073929818e-05,
      "loss": 0.1145,
      "step": 890
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.3483590878516435e-05,
      "loss": 0.1108,
      "step": 895
    },
    {
      "epoch": 0.76,
      "learning_rate": 3.2386472646236566e-05,
      "loss": 0.1218,
      "step": 900
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.1304146056271024e-05,
      "loss": 0.1142,
      "step": 905
    },
    {
      "epoch": 0.77,
      "learning_rate": 3.0236847886501542e-05,
      "loss": 0.128,
      "step": 910
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.9184811627079987e-05,
      "loss": 0.1268,
      "step": 915
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.814826742934823e-05,
      "loss": 0.1271,
      "step": 920
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.7127442055488615e-05,
      "loss": 0.1205,
      "step": 925
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.6122558828915646e-05,
      "loss": 0.1196,
      "step": 930
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.5133837585420084e-05,
      "loss": 0.1305,
      "step": 935
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.4161494625076165e-05,
      "loss": 0.1213,
      "step": 940
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.3205742664922004e-05,
      "loss": 0.1308,
      "step": 945
    },
    {
      "epoch": 0.8,
      "learning_rate": 2.2266790792424097e-05,
      "loss": 0.1229,
      "step": 950
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.1344844419735755e-05,
      "loss": 0.1212,
      "step": 955
    },
    {
      "epoch": 0.81,
      "learning_rate": 2.0440105238759687e-05,
      "loss": 0.138,
      "step": 960
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.9552771177024242e-05,
      "loss": 0.119,
      "step": 965
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.868303635438332e-05,
      "loss": 0.118,
      "step": 970
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.7831091040549397e-05,
      "loss": 0.1286,
      "step": 975
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6997121613468458e-05,
      "loss": 0.1292,
      "step": 980
    },
    {
      "epoch": 0.83,
      "learning_rate": 1.6181310518546856e-05,
      "loss": 0.1232,
      "step": 985
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.5383836228737814e-05,
      "loss": 0.1282,
      "step": 990
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.4604873205497727e-05,
      "loss": 0.1235,
      "step": 995
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3844591860619383e-05,
      "loss": 0.1266,
      "step": 1000
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.3103158518951618e-05,
      "loss": 0.1248,
      "step": 1005
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.2380735382012576e-05,
      "loss": 0.1321,
      "step": 1010
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.1677480492505588e-05,
      "loss": 0.1261,
      "step": 1015
    },
    {
      "epoch": 0.86,
      "learning_rate": 1.0993547699744366e-05,
      "loss": 0.1274,
      "step": 1020
    },
    {
      "epoch": 0.87,
      "learning_rate": 1.0329086625995843e-05,
      "loss": 0.1243,
      "step": 1025
    },
    {
      "epoch": 0.87,
      "learning_rate": 9.684242633747642e-06,
      "loss": 0.1493,
      "step": 1030
    },
    {
      "epoch": 0.88,
      "learning_rate": 9.059156793907541e-06,
      "loss": 0.1342,
      "step": 1035
    },
    {
      "epoch": 0.88,
      "learning_rate": 8.453965854941748e-06,
      "loss": 0.1203,
      "step": 1040
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.868802212958703e-06,
      "loss": 0.1182,
      "step": 1045
    },
    {
      "epoch": 0.89,
      "learning_rate": 7.3037938827451805e-06,
      "loss": 0.1373,
      "step": 1050
    },
    {
      "epoch": 0.89,
      "learning_rate": 6.759064469760823e-06,
      "loss": 0.135,
      "step": 1055
    },
    {
      "epoch": 0.9,
      "learning_rate": 6.234733143097216e-06,
      "loss": 0.1093,
      "step": 1060
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.730914609407634e-06,
      "loss": 0.1354,
      "step": 1065
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.247719087812897e-06,
      "loss": 0.1156,
      "step": 1070
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.785252285789077e-06,
      "loss": 0.1157,
      "step": 1075
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.3436153760420654e-06,
      "loss": 0.1402,
      "step": 1080
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.922904974374309e-06,
      "loss": 0.1291,
      "step": 1085
    },
    {
      "epoch": 0.92,
      "learning_rate": 3.5232131185484076e-06,
      "loss": 0.1371,
      "step": 1090
    },
    {
      "epoch": 0.93,
      "learning_rate": 3.1446272481522543e-06,
      "loss": 0.1198,
      "step": 1095
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.78723018547008e-06,
      "loss": 0.1456,
      "step": 1100
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.451100117363603e-06,
      "loss": 0.1208,
      "step": 1105
    },
    {
      "epoch": 0.94,
      "learning_rate": 2.1363105781673888e-06,
      "loss": 0.1089,
      "step": 1110
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.842930433601775e-06,
      "loss": 0.1166,
      "step": 1115
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.5710238657074217e-06,
      "loss": 0.1258,
      "step": 1120
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.3206503588042762e-06,
      "loss": 0.1338,
      "step": 1125
    },
    {
      "epoch": 0.96,
      "learning_rate": 1.0918646864784166e-06,
      "loss": 0.1282,
      "step": 1130
    },
    {
      "epoch": 0.96,
      "learning_rate": 8.847168995992916e-07,
      "loss": 0.1266,
      "step": 1135
    },
    {
      "epoch": 0.97,
      "learning_rate": 6.992523153702691e-07,
      "loss": 0.1218,
      "step": 1140
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.35511507414721e-07,
      "loss": 0.1172,
      "step": 1145
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.9353029689974674e-07,
      "loss": 0.1367,
      "step": 1150
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.733397446997632e-07,
      "loss": 0.1164,
      "step": 1155
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.7496614460135176e-07,
      "loss": 0.1091,
      "step": 1160
    },
    {
      "epoch": 0.99,
      "learning_rate": 9.843101755101502e-08,
      "loss": 0.1402,
      "step": 1165
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.375110694713191e-08,
      "loss": 0.1242,
      "step": 1170
    },
    {
      "epoch": 1.0,
      "learning_rate": 1.0938374977020882e-08,
      "loss": 0.122,
      "step": 1175
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.1162,
      "step": 1180
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.10465715825557709,
      "eval_runtime": 0.1015,
      "eval_samples_per_second": 49.268,
      "eval_steps_per_second": 9.854,
      "step": 1180
    },
    {
      "epoch": 1.0,
      "step": 1180,
      "total_flos": 6.174977435684045e+16,
      "train_loss": 0.2257307288000139,
      "train_runtime": 713.6543,
      "train_samples_per_second": 13.23,
      "train_steps_per_second": 1.653
    }
  ],
  "logging_steps": 5,
  "max_steps": 1180,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 6.174977435684045e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}