{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15239256324291375,
  "eval_steps": 500,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001015950421619425,
      "grad_norm": 17.625,
      "learning_rate": 5e-06,
      "loss": 3.4264,
      "step": 10
    },
    {
      "epoch": 0.00203190084323885,
      "grad_norm": 12.5625,
      "learning_rate": 1e-05,
      "loss": 3.432,
      "step": 20
    },
    {
      "epoch": 0.003047851264858275,
      "grad_norm": 14.0625,
      "learning_rate": 1.5e-05,
      "loss": 3.23,
      "step": 30
    },
    {
      "epoch": 0.0040638016864777,
      "grad_norm": 12.4375,
      "learning_rate": 2e-05,
      "loss": 2.9762,
      "step": 40
    },
    {
      "epoch": 0.005079752108097125,
      "grad_norm": 10.0625,
      "learning_rate": 2.5e-05,
      "loss": 2.6173,
      "step": 50
    },
    {
      "epoch": 0.00609570252971655,
      "grad_norm": 10.1875,
      "learning_rate": 3e-05,
      "loss": 2.2004,
      "step": 60
    },
    {
      "epoch": 0.007111652951335975,
      "grad_norm": 7.03125,
      "learning_rate": 3.5e-05,
      "loss": 1.4176,
      "step": 70
    },
    {
      "epoch": 0.0081276033729554,
      "grad_norm": 4.375,
      "learning_rate": 4e-05,
      "loss": 1.0122,
      "step": 80
    },
    {
      "epoch": 0.009143553794574825,
      "grad_norm": 6.5625,
      "learning_rate": 4.5e-05,
      "loss": 0.9116,
      "step": 90
    },
    {
      "epoch": 0.01015950421619425,
      "grad_norm": 5.28125,
      "learning_rate": 5e-05,
      "loss": 0.6832,
      "step": 100
    },
    {
      "epoch": 0.011175454637813675,
      "grad_norm": 5.5,
      "learning_rate": 4.9999870035728426e-05,
      "loss": 0.7355,
      "step": 110
    },
    {
      "epoch": 0.0121914050594331,
      "grad_norm": 5.1875,
      "learning_rate": 4.9999480144264944e-05,
      "loss": 0.6673,
      "step": 120
    },
    {
      "epoch": 0.013207355481052525,
      "grad_norm": 4.5,
      "learning_rate": 4.9998830329663314e-05,
      "loss": 0.6792,
      "step": 130
    },
    {
      "epoch": 0.01422330590267195,
      "grad_norm": 3.9375,
      "learning_rate": 4.9997920598679756e-05,
      "loss": 0.6207,
      "step": 140
    },
    {
      "epoch": 0.015239256324291375,
      "grad_norm": 3.15625,
      "learning_rate": 4.999675096077286e-05,
      "loss": 0.483,
      "step": 150
    },
    {
      "epoch": 0.0162552067459108,
      "grad_norm": 5.28125,
      "learning_rate": 4.999532142810354e-05,
      "loss": 0.5319,
      "step": 160
    },
    {
      "epoch": 0.017271157167530225,
      "grad_norm": 4.59375,
      "learning_rate": 4.999363201553483e-05,
      "loss": 0.6052,
      "step": 170
    },
    {
      "epoch": 0.01828710758914965,
      "grad_norm": 5.03125,
      "learning_rate": 4.9991682740631794e-05,
      "loss": 0.4258,
      "step": 180
    },
    {
      "epoch": 0.019303058010769075,
      "grad_norm": 3.859375,
      "learning_rate": 4.998947362366133e-05,
      "loss": 0.4309,
      "step": 190
    },
    {
      "epoch": 0.0203190084323885,
      "grad_norm": 3.328125,
      "learning_rate": 4.998700468759193e-05,
      "loss": 0.3957,
      "step": 200
    },
    {
      "epoch": 0.021334958854007924,
      "grad_norm": 4.9375,
      "learning_rate": 4.9984275958093475e-05,
      "loss": 0.4777,
      "step": 210
    },
    {
      "epoch": 0.02235090927562735,
      "grad_norm": 4.78125,
      "learning_rate": 4.998128746353695e-05,
      "loss": 0.3549,
      "step": 220
    },
    {
      "epoch": 0.023366859697246774,
      "grad_norm": 4.0625,
      "learning_rate": 4.997803923499417e-05,
      "loss": 0.4447,
      "step": 230
    },
    {
      "epoch": 0.0243828101188662,
      "grad_norm": 6.375,
      "learning_rate": 4.99745313062374e-05,
      "loss": 0.3808,
      "step": 240
    },
    {
      "epoch": 0.025398760540485624,
      "grad_norm": 3.59375,
      "learning_rate": 4.99707637137391e-05,
      "loss": 0.3827,
      "step": 250
    },
    {
      "epoch": 0.02641471096210505,
      "grad_norm": 3.015625,
      "learning_rate": 4.996673649667145e-05,
      "loss": 0.3694,
      "step": 260
    },
    {
      "epoch": 0.027430661383724474,
      "grad_norm": 2.296875,
      "learning_rate": 4.9962449696906e-05,
      "loss": 0.3586,
      "step": 270
    },
    {
      "epoch": 0.0284466118053439,
      "grad_norm": 4.125,
      "learning_rate": 4.9957903359013214e-05,
      "loss": 0.3832,
      "step": 280
    },
    {
      "epoch": 0.029462562226963324,
      "grad_norm": 3.296875,
      "learning_rate": 4.995309753026201e-05,
      "loss": 0.328,
      "step": 290
    },
    {
      "epoch": 0.03047851264858275,
      "grad_norm": 4.5,
      "learning_rate": 4.994803226061927e-05,
      "loss": 0.3667,
      "step": 300
    },
    {
      "epoch": 0.03149446307020217,
      "grad_norm": 4.3125,
      "learning_rate": 4.994270760274933e-05,
      "loss": 0.3811,
      "step": 310
    },
    {
      "epoch": 0.0325104134918216,
      "grad_norm": 3.421875,
      "learning_rate": 4.99371236120134e-05,
      "loss": 0.3065,
      "step": 320
    },
    {
      "epoch": 0.03352636391344102,
      "grad_norm": 4.6875,
      "learning_rate": 4.993128034646902e-05,
      "loss": 0.4177,
      "step": 330
    },
    {
      "epoch": 0.03454231433506045,
      "grad_norm": 3.046875,
      "learning_rate": 4.992517786686947e-05,
      "loss": 0.33,
      "step": 340
    },
    {
      "epoch": 0.03555826475667987,
      "grad_norm": 1.8828125,
      "learning_rate": 4.9918816236663077e-05,
      "loss": 0.3287,
      "step": 350
    },
    {
      "epoch": 0.0365742151782993,
      "grad_norm": 3.8125,
      "learning_rate": 4.991219552199262e-05,
      "loss": 0.2934,
      "step": 360
    },
    {
      "epoch": 0.03759016559991872,
      "grad_norm": 4.28125,
      "learning_rate": 4.99053157916946e-05,
      "loss": 0.3176,
      "step": 370
    },
    {
      "epoch": 0.03860611602153815,
      "grad_norm": 2.609375,
      "learning_rate": 4.989817711729856e-05,
      "loss": 0.3318,
      "step": 380
    },
    {
      "epoch": 0.03962206644315757,
      "grad_norm": 2.375,
      "learning_rate": 4.98907795730263e-05,
      "loss": 0.3234,
      "step": 390
    },
    {
      "epoch": 0.040638016864777,
      "grad_norm": 4.46875,
      "learning_rate": 4.988312323579114e-05,
      "loss": 0.267,
      "step": 400
    },
    {
      "epoch": 0.04165396728639642,
      "grad_norm": 3.75,
      "learning_rate": 4.98752081851971e-05,
      "loss": 0.3081,
      "step": 410
    },
    {
      "epoch": 0.04266991770801585,
      "grad_norm": 2.203125,
      "learning_rate": 4.986703450353809e-05,
      "loss": 0.2917,
      "step": 420
    },
    {
      "epoch": 0.04368586812963527,
      "grad_norm": 1.6015625,
      "learning_rate": 4.985860227579703e-05,
      "loss": 0.2805,
      "step": 430
    },
    {
      "epoch": 0.0447018185512547,
      "grad_norm": 3.140625,
      "learning_rate": 4.984991158964499e-05,
      "loss": 0.3534,
      "step": 440
    },
    {
      "epoch": 0.04571776897287412,
      "grad_norm": 3.296875,
      "learning_rate": 4.9840962535440265e-05,
      "loss": 0.335,
      "step": 450
    },
    {
      "epoch": 0.04673371939449355,
      "grad_norm": 3.25,
      "learning_rate": 4.983175520622744e-05,
      "loss": 0.2544,
      "step": 460
    },
    {
      "epoch": 0.04774966981611297,
      "grad_norm": 2.25,
      "learning_rate": 4.982228969773642e-05,
      "loss": 0.3449,
      "step": 470
    },
    {
      "epoch": 0.0487656202377324,
      "grad_norm": 4.9375,
      "learning_rate": 4.9812566108381435e-05,
      "loss": 0.2964,
      "step": 480
    },
    {
      "epoch": 0.04978157065935182,
      "grad_norm": 1.5703125,
      "learning_rate": 4.9802584539260035e-05,
      "loss": 0.2799,
      "step": 490
    },
    {
      "epoch": 0.05079752108097125,
      "grad_norm": 2.828125,
      "learning_rate": 4.979234509415199e-05,
      "loss": 0.3231,
      "step": 500
    },
    {
      "epoch": 0.05181347150259067,
      "grad_norm": 2.9375,
      "learning_rate": 4.978184787951828e-05,
      "loss": 0.2943,
      "step": 510
    },
    {
      "epoch": 0.0528294219242101,
      "grad_norm": 2.34375,
      "learning_rate": 4.977109300449992e-05,
      "loss": 0.2705,
      "step": 520
    },
    {
      "epoch": 0.05384537234582952,
      "grad_norm": 3.140625,
      "learning_rate": 4.9760080580916876e-05,
      "loss": 0.2998,
      "step": 530
    },
    {
      "epoch": 0.05486132276744895,
      "grad_norm": 3.5625,
      "learning_rate": 4.974881072326688e-05,
      "loss": 0.2595,
      "step": 540
    },
    {
      "epoch": 0.05587727318906837,
      "grad_norm": 4.25,
      "learning_rate": 4.9737283548724236e-05,
      "loss": 0.2803,
      "step": 550
    },
    {
      "epoch": 0.0568932236106878,
      "grad_norm": 4.0625,
      "learning_rate": 4.97254991771386e-05,
      "loss": 0.3511,
      "step": 560
    },
    {
      "epoch": 0.05790917403230722,
      "grad_norm": 2.515625,
      "learning_rate": 4.971345773103377e-05,
      "loss": 0.312,
      "step": 570
    },
    {
      "epoch": 0.05892512445392665,
      "grad_norm": 3.21875,
      "learning_rate": 4.9701159335606365e-05,
      "loss": 0.2482,
      "step": 580
    },
    {
      "epoch": 0.05994107487554607,
      "grad_norm": 5.5,
      "learning_rate": 4.968860411872454e-05,
      "loss": 0.2537,
      "step": 590
    },
    {
      "epoch": 0.0609570252971655,
      "grad_norm": 3.546875,
      "learning_rate": 4.967579221092666e-05,
      "loss": 0.3125,
      "step": 600
    },
    {
      "epoch": 0.06197297571878492,
      "grad_norm": 2.984375,
      "learning_rate": 4.966272374541996e-05,
      "loss": 0.2354,
      "step": 610
    },
    {
      "epoch": 0.06298892614040434,
      "grad_norm": 3.6875,
      "learning_rate": 4.964939885807912e-05,
      "loss": 0.3213,
      "step": 620
    },
    {
      "epoch": 0.06400487656202378,
      "grad_norm": 2.140625,
      "learning_rate": 4.9635817687444876e-05,
      "loss": 0.3003,
      "step": 630
    },
    {
      "epoch": 0.0650208269836432,
      "grad_norm": 3.484375,
      "learning_rate": 4.962198037472259e-05,
      "loss": 0.2996,
      "step": 640
    },
    {
      "epoch": 0.06603677740526262,
      "grad_norm": 3.21875,
      "learning_rate": 4.9607887063780776e-05,
      "loss": 0.2257,
      "step": 650
    },
    {
      "epoch": 0.06705272782688204,
      "grad_norm": 5.375,
      "learning_rate": 4.9593537901149564e-05,
      "loss": 0.223,
      "step": 660
    },
    {
      "epoch": 0.06806867824850148,
      "grad_norm": 4.1875,
      "learning_rate": 4.957893303601924e-05,
      "loss": 0.3407,
      "step": 670
    },
    {
      "epoch": 0.0690846286701209,
      "grad_norm": 3.328125,
      "learning_rate": 4.956407262023866e-05,
      "loss": 0.2589,
      "step": 680
    },
    {
      "epoch": 0.07010057909174032,
      "grad_norm": 2.953125,
      "learning_rate": 4.954895680831367e-05,
      "loss": 0.2949,
      "step": 690
    },
    {
      "epoch": 0.07111652951335974,
      "grad_norm": 4.0625,
      "learning_rate": 4.9533585757405506e-05,
      "loss": 0.2995,
      "step": 700
    },
    {
      "epoch": 0.07213247993497918,
      "grad_norm": 4.625,
      "learning_rate": 4.951795962732917e-05,
      "loss": 0.2894,
      "step": 710
    },
    {
      "epoch": 0.0731484303565986,
      "grad_norm": 3.0,
      "learning_rate": 4.9502078580551755e-05,
      "loss": 0.3082,
      "step": 720
    },
    {
      "epoch": 0.07416438077821802,
      "grad_norm": 3.65625,
      "learning_rate": 4.9485942782190734e-05,
      "loss": 0.2308,
      "step": 730
    },
    {
      "epoch": 0.07518033119983744,
      "grad_norm": 4.78125,
      "learning_rate": 4.9469552400012306e-05,
      "loss": 0.2272,
      "step": 740
    },
    {
      "epoch": 0.07619628162145688,
      "grad_norm": 4.25,
      "learning_rate": 4.94529076044296e-05,
      "loss": 0.2701,
      "step": 750
    },
    {
      "epoch": 0.0772122320430763,
      "grad_norm": 3.140625,
      "learning_rate": 4.94360085685009e-05,
      "loss": 0.2686,
      "step": 760
    },
    {
      "epoch": 0.07822818246469572,
      "grad_norm": 0.765625,
      "learning_rate": 4.9418855467927894e-05,
      "loss": 0.2051,
      "step": 770
    },
    {
      "epoch": 0.07924413288631514,
      "grad_norm": 1.796875,
      "learning_rate": 4.940144848105379e-05,
      "loss": 0.2267,
      "step": 780
    },
    {
      "epoch": 0.08026008330793458,
      "grad_norm": 4.5625,
      "learning_rate": 4.93837877888615e-05,
      "loss": 0.2597,
      "step": 790
    },
    {
      "epoch": 0.081276033729554,
      "grad_norm": 3.03125,
      "learning_rate": 4.9365873574971745e-05,
      "loss": 0.3701,
      "step": 800
    },
    {
      "epoch": 0.08229198415117342,
      "grad_norm": 4.5625,
      "learning_rate": 4.9347706025641136e-05,
      "loss": 0.2559,
      "step": 810
    },
    {
      "epoch": 0.08330793457279284,
      "grad_norm": 3.90625,
      "learning_rate": 4.9329285329760275e-05,
      "loss": 0.2799,
      "step": 820
    },
    {
      "epoch": 0.08432388499441228,
      "grad_norm": 3.140625,
      "learning_rate": 4.9310611678851735e-05,
      "loss": 0.2866,
      "step": 830
    },
    {
      "epoch": 0.0853398354160317,
      "grad_norm": 2.46875,
      "learning_rate": 4.929168526706811e-05,
      "loss": 0.3105,
      "step": 840
    },
    {
      "epoch": 0.08635578583765112,
      "grad_norm": 13.625,
      "learning_rate": 4.927250629119e-05,
      "loss": 0.2454,
      "step": 850
    },
    {
      "epoch": 0.08737173625927054,
      "grad_norm": 3.921875,
      "learning_rate": 4.9253074950623925e-05,
      "loss": 0.2424,
      "step": 860
    },
    {
      "epoch": 0.08838768668088998,
      "grad_norm": 2.90625,
      "learning_rate": 4.9233391447400286e-05,
      "loss": 0.2481,
      "step": 870
    },
    {
      "epoch": 0.0894036371025094,
      "grad_norm": 2.96875,
      "learning_rate": 4.921345598617125e-05,
      "loss": 0.2231,
      "step": 880
    },
    {
      "epoch": 0.09041958752412882,
      "grad_norm": 5.375,
      "learning_rate": 4.9193268774208654e-05,
      "loss": 0.3447,
      "step": 890
    },
    {
      "epoch": 0.09143553794574824,
      "grad_norm": 2.0,
      "learning_rate": 4.9172830021401785e-05,
      "loss": 0.229,
      "step": 900
    },
    {
      "epoch": 0.09245148836736768,
      "grad_norm": 3.1875,
      "learning_rate": 4.9152139940255245e-05,
      "loss": 0.2122,
      "step": 910
    },
    {
      "epoch": 0.0934674387889871,
      "grad_norm": 3.40625,
      "learning_rate": 4.913119874588677e-05,
      "loss": 0.2386,
      "step": 920
    },
    {
      "epoch": 0.09448338921060652,
      "grad_norm": 1.4609375,
      "learning_rate": 4.911000665602489e-05,
      "loss": 0.1944,
      "step": 930
    },
    {
      "epoch": 0.09549933963222594,
      "grad_norm": 5.0625,
      "learning_rate": 4.9088563891006786e-05,
      "loss": 0.2038,
      "step": 940
    },
    {
      "epoch": 0.09651529005384538,
      "grad_norm": 4.53125,
      "learning_rate": 4.906687067377592e-05,
      "loss": 0.3122,
      "step": 950
    },
    {
      "epoch": 0.0975312404754648,
      "grad_norm": 2.84375,
      "learning_rate": 4.904492722987976e-05,
      "loss": 0.3157,
      "step": 960
    },
    {
      "epoch": 0.09854719089708422,
      "grad_norm": 2.171875,
      "learning_rate": 4.902273378746738e-05,
      "loss": 0.3077,
      "step": 970
    },
    {
      "epoch": 0.09956314131870364,
      "grad_norm": 2.84375,
      "learning_rate": 4.9000290577287165e-05,
      "loss": 0.2756,
      "step": 980
    },
    {
      "epoch": 0.10057909174032308,
      "grad_norm": 0.99609375,
      "learning_rate": 4.897759783268434e-05,
      "loss": 0.2915,
      "step": 990
    },
    {
      "epoch": 0.1015950421619425,
      "grad_norm": 3.53125,
      "learning_rate": 4.895465578959859e-05,
      "loss": 0.2052,
      "step": 1000
    },
    {
      "epoch": 0.10261099258356192,
      "grad_norm": 4.0,
      "learning_rate": 4.893146468656159e-05,
      "loss": 0.2499,
      "step": 1010
    },
    {
      "epoch": 0.10362694300518134,
      "grad_norm": 1.65625,
      "learning_rate": 4.890802476469452e-05,
      "loss": 0.278,
      "step": 1020
    },
    {
      "epoch": 0.10464289342680078,
      "grad_norm": 3.625,
      "learning_rate": 4.888433626770558e-05,
      "loss": 0.2143,
      "step": 1030
    },
    {
      "epoch": 0.1056588438484202,
      "grad_norm": 5.0625,
      "learning_rate": 4.886039944188741e-05,
      "loss": 0.2878,
      "step": 1040
    },
    {
      "epoch": 0.10667479427003962,
      "grad_norm": 4.5,
      "learning_rate": 4.883621453611461e-05,
      "loss": 0.2744,
      "step": 1050
    },
    {
      "epoch": 0.10769074469165904,
      "grad_norm": 4.5625,
      "learning_rate": 4.881178180184106e-05,
      "loss": 0.2734,
      "step": 1060
    },
    {
      "epoch": 0.10870669511327848,
      "grad_norm": 3.125,
      "learning_rate": 4.878710149309735e-05,
      "loss": 0.3574,
      "step": 1070
    },
    {
      "epoch": 0.1097226455348979,
      "grad_norm": 3.0625,
      "learning_rate": 4.876217386648816e-05,
      "loss": 0.2625,
      "step": 1080
    },
    {
      "epoch": 0.11073859595651732,
      "grad_norm": 4.0625,
      "learning_rate": 4.873699918118955e-05,
      "loss": 0.2437,
      "step": 1090
    },
    {
      "epoch": 0.11175454637813674,
      "grad_norm": 1.59375,
      "learning_rate": 4.87115776989463e-05,
      "loss": 0.2051,
      "step": 1100
    },
    {
      "epoch": 0.11277049679975618,
      "grad_norm": 4.375,
      "learning_rate": 4.8685909684069153e-05,
      "loss": 0.1727,
      "step": 1110
    },
    {
      "epoch": 0.1137864472213756,
      "grad_norm": 2.28125,
      "learning_rate": 4.865999540343211e-05,
      "loss": 0.2256,
      "step": 1120
    },
    {
      "epoch": 0.11480239764299502,
      "grad_norm": 2.265625,
      "learning_rate": 4.86338351264696e-05,
      "loss": 0.3529,
      "step": 1130
    },
    {
      "epoch": 0.11581834806461444,
      "grad_norm": 2.34375,
      "learning_rate": 4.8607429125173754e-05,
      "loss": 0.2113,
      "step": 1140
    },
    {
      "epoch": 0.11683429848623388,
      "grad_norm": 0.7578125,
      "learning_rate": 4.858077767409149e-05,
      "loss": 0.2759,
      "step": 1150
    },
    {
      "epoch": 0.1178502489078533,
      "grad_norm": 3.640625,
      "learning_rate": 4.855388105032174e-05,
      "loss": 0.2482,
      "step": 1160
    },
    {
      "epoch": 0.11886619932947272,
      "grad_norm": 3.5,
      "learning_rate": 4.852673953351249e-05,
      "loss": 0.1865,
      "step": 1170
    },
    {
      "epoch": 0.11988214975109214,
      "grad_norm": 3.75,
      "learning_rate": 4.849935340585796e-05,
      "loss": 0.2659,
      "step": 1180
    },
    {
      "epoch": 0.12089810017271158,
      "grad_norm": 3.375,
      "learning_rate": 4.8471722952095586e-05,
      "loss": 0.1506,
      "step": 1190
    },
    {
      "epoch": 0.121914050594331,
      "grad_norm": 3.34375,
      "learning_rate": 4.844384845950312e-05,
      "loss": 0.307,
      "step": 1200
    },
    {
      "epoch": 0.12293000101595042,
      "grad_norm": 1.578125,
      "learning_rate": 4.841573021789561e-05,
      "loss": 0.1952,
      "step": 1210
    },
    {
      "epoch": 0.12394595143756984,
      "grad_norm": 1.2890625,
      "learning_rate": 4.838736851962239e-05,
      "loss": 0.1779,
      "step": 1220
    },
    {
      "epoch": 0.12496190185918928,
      "grad_norm": 1.265625,
      "learning_rate": 4.835876365956408e-05,
      "loss": 0.1235,
      "step": 1230
    },
    {
      "epoch": 0.12597785228080868,
      "grad_norm": 1.9609375,
      "learning_rate": 4.8329915935129436e-05,
      "loss": 0.1876,
      "step": 1240
    },
    {
      "epoch": 0.12699380270242813,
      "grad_norm": 1.6328125,
      "learning_rate": 4.830082564625235e-05,
      "loss": 0.2188,
      "step": 1250
    },
    {
      "epoch": 0.12800975312404755,
      "grad_norm": 3.96875,
      "learning_rate": 4.8271493095388684e-05,
      "loss": 0.2622,
      "step": 1260
    },
    {
      "epoch": 0.12902570354566698,
      "grad_norm": 3.765625,
      "learning_rate": 4.824191858751312e-05,
      "loss": 0.2724,
      "step": 1270
    },
    {
      "epoch": 0.1300416539672864,
      "grad_norm": 5.59375,
      "learning_rate": 4.821210243011601e-05,
      "loss": 0.2413,
      "step": 1280
    },
    {
      "epoch": 0.13105760438890582,
      "grad_norm": 3.34375,
      "learning_rate": 4.818204493320016e-05,
      "loss": 0.2618,
      "step": 1290
    },
    {
      "epoch": 0.13207355481052524,
      "grad_norm": 2.78125,
      "learning_rate": 4.8151746409277634e-05,
      "loss": 0.2295,
      "step": 1300
    },
    {
      "epoch": 0.13308950523214466,
      "grad_norm": 3.1875,
      "learning_rate": 4.8121207173366484e-05,
      "loss": 0.2733,
      "step": 1310
    },
    {
      "epoch": 0.13410545565376408,
      "grad_norm": 2.28125,
      "learning_rate": 4.809042754298746e-05,
      "loss": 0.2311,
      "step": 1320
    },
    {
      "epoch": 0.13512140607538353,
      "grad_norm": 2.171875,
      "learning_rate": 4.805940783816075e-05,
      "loss": 0.2059,
      "step": 1330
    },
    {
      "epoch": 0.13613735649700295,
      "grad_norm": 2.796875,
      "learning_rate": 4.8028148381402625e-05,
      "loss": 0.2102,
      "step": 1340
    },
    {
      "epoch": 0.13715330691862238,
      "grad_norm": 2.96875,
      "learning_rate": 4.7996649497722084e-05,
      "loss": 0.2708,
      "step": 1350
    },
    {
      "epoch": 0.1381692573402418,
      "grad_norm": 2.4375,
      "learning_rate": 4.7964911514617485e-05,
      "loss": 0.2429,
      "step": 1360
    },
    {
      "epoch": 0.13918520776186122,
      "grad_norm": 5.8125,
      "learning_rate": 4.793293476207312e-05,
      "loss": 0.2725,
      "step": 1370
    },
    {
      "epoch": 0.14020115818348064,
      "grad_norm": 2.40625,
      "learning_rate": 4.790071957255585e-05,
      "loss": 0.2098,
      "step": 1380
    },
    {
      "epoch": 0.14121710860510006,
      "grad_norm": 4.25,
      "learning_rate": 4.786826628101154e-05,
      "loss": 0.2101,
      "step": 1390
    },
    {
      "epoch": 0.14223305902671948,
      "grad_norm": 2.578125,
      "learning_rate": 4.783557522486167e-05,
      "loss": 0.2624,
      "step": 1400
    },
    {
      "epoch": 0.14324900944833893,
      "grad_norm": 3.125,
      "learning_rate": 4.780264674399978e-05,
      "loss": 0.2518,
      "step": 1410
    },
    {
      "epoch": 0.14426495986995835,
      "grad_norm": 3.671875,
      "learning_rate": 4.7769481180787966e-05,
      "loss": 0.3112,
      "step": 1420
    },
    {
      "epoch": 0.14528091029157778,
      "grad_norm": 3.984375,
      "learning_rate": 4.773607888005327e-05,
      "loss": 0.2747,
      "step": 1430
    },
    {
      "epoch": 0.1462968607131972,
      "grad_norm": 3.234375,
      "learning_rate": 4.770244018908416e-05,
      "loss": 0.1572,
      "step": 1440
    },
    {
      "epoch": 0.14731281113481662,
      "grad_norm": 4.09375,
      "learning_rate": 4.766856545762687e-05,
      "loss": 0.2148,
      "step": 1450
    },
    {
      "epoch": 0.14832876155643604,
      "grad_norm": 1.6875,
      "learning_rate": 4.763445503788178e-05,
      "loss": 0.2531,
      "step": 1460
    },
    {
      "epoch": 0.14934471197805546,
      "grad_norm": 2.375,
      "learning_rate": 4.760010928449976e-05,
      "loss": 0.199,
      "step": 1470
    },
    {
      "epoch": 0.15036066239967488,
      "grad_norm": 4.6875,
      "learning_rate": 4.7565528554578485e-05,
      "loss": 0.2366,
      "step": 1480
    },
    {
      "epoch": 0.15137661282129433,
      "grad_norm": 5.4375,
      "learning_rate": 4.75307132076587e-05,
      "loss": 0.1862,
      "step": 1490
    },
    {
      "epoch": 0.15239256324291375,
      "grad_norm": 2.484375,
      "learning_rate": 4.749566360572049e-05,
      "loss": 0.2143,
      "step": 1500
    }
  ],
  "logging_steps": 10,
  "max_steps": 9843,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "train_batch_size": 7,
  "trial_name": null,
  "trial_params": null
}