{
  "best_global_step": 150,
  "best_metric": 1.2925209999084473,
  "best_model_checkpoint": "adapter/checkpoint-150",
  "epoch": 8.0,
  "eval_steps": 500,
  "global_step": 240,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 1.155246615409851,
      "learning_rate": 0.0,
      "loss": 2.294318675994873,
      "step": 1
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 1.227621078491211,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 2.344038486480713,
      "step": 2
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 1.1472781896591187,
      "learning_rate": 6.666666666666667e-06,
      "loss": 2.272017240524292,
      "step": 3
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 1.3359848260879517,
      "learning_rate": 1e-05,
      "loss": 2.4868245124816895,
      "step": 4
    },
    {
      "epoch": 0.16806722689075632,
      "grad_norm": 1.2019633054733276,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 2.292177677154541,
      "step": 5
    },
    {
      "epoch": 0.20168067226890757,
      "grad_norm": 1.1751525402069092,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2553842067718506,
      "step": 6
    },
    {
      "epoch": 0.23529411764705882,
      "grad_norm": 1.0292246341705322,
      "learning_rate": 2e-05,
      "loss": 2.288325309753418,
      "step": 7
    },
    {
      "epoch": 0.2689075630252101,
      "grad_norm": 1.0636998414993286,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 2.1868786811828613,
      "step": 8
    },
    {
      "epoch": 0.3025210084033613,
      "grad_norm": 1.0602788925170898,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 2.149629831314087,
      "step": 9
    },
    {
      "epoch": 0.33613445378151263,
      "grad_norm": 0.9715706706047058,
      "learning_rate": 3e-05,
      "loss": 2.2972798347473145,
      "step": 10
    },
    {
      "epoch": 0.3697478991596639,
      "grad_norm": 0.9472726583480835,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.1498613357543945,
      "step": 11
    },
    {
      "epoch": 0.40336134453781514,
      "grad_norm": 0.7821086049079895,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 2.07391357421875,
      "step": 12
    },
    {
      "epoch": 0.4369747899159664,
      "grad_norm": 0.7451765537261963,
      "learning_rate": 4e-05,
      "loss": 2.0267810821533203,
      "step": 13
    },
    {
      "epoch": 0.47058823529411764,
      "grad_norm": 0.7123281359672546,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 2.092998504638672,
      "step": 14
    },
    {
      "epoch": 0.5042016806722689,
      "grad_norm": 0.6559141278266907,
      "learning_rate": 4.666666666666667e-05,
      "loss": 1.9753941297531128,
      "step": 15
    },
    {
      "epoch": 0.5378151260504201,
      "grad_norm": 0.61635422706604,
      "learning_rate": 5e-05,
      "loss": 1.9742653369903564,
      "step": 16
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.6374775171279907,
      "learning_rate": 5.333333333333333e-05,
      "loss": 2.000692367553711,
      "step": 17
    },
    {
      "epoch": 0.6050420168067226,
      "grad_norm": 0.6087096333503723,
      "learning_rate": 5.666666666666667e-05,
      "loss": 2.0749123096466064,
      "step": 18
    },
    {
      "epoch": 0.6386554621848739,
      "grad_norm": 0.5434087514877319,
      "learning_rate": 6e-05,
      "loss": 1.8835960626602173,
      "step": 19
    },
    {
      "epoch": 0.6722689075630253,
      "grad_norm": 0.5283316969871521,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.8923404216766357,
      "step": 20
    },
    {
      "epoch": 0.7058823529411765,
      "grad_norm": 0.5417094230651855,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.881527304649353,
      "step": 21
    },
    {
      "epoch": 0.7394957983193278,
      "grad_norm": 0.5917208194732666,
      "learning_rate": 7e-05,
      "loss": 1.887539267539978,
      "step": 22
    },
    {
      "epoch": 0.773109243697479,
      "grad_norm": 0.5762194991111755,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.8085060119628906,
      "step": 23
    },
    {
      "epoch": 0.8067226890756303,
      "grad_norm": 0.6470560431480408,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.8922410011291504,
      "step": 24
    },
    {
      "epoch": 0.8403361344537815,
      "grad_norm": 0.6626067757606506,
      "learning_rate": 8e-05,
      "loss": 1.761276364326477,
      "step": 25
    },
    {
      "epoch": 0.8739495798319328,
      "grad_norm": 0.6730513572692871,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7892605066299438,
      "step": 26
    },
    {
      "epoch": 0.907563025210084,
      "grad_norm": 0.7920926809310913,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.6900041103363037,
      "step": 27
    },
    {
      "epoch": 0.9411764705882353,
      "grad_norm": 0.7173868417739868,
      "learning_rate": 9e-05,
      "loss": 1.6060148477554321,
      "step": 28
    },
    {
      "epoch": 0.9747899159663865,
      "grad_norm": 0.6930776834487915,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.7407147884368896,
      "step": 29
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.7688128352165222,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.7529323101043701,
      "step": 30
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6525782346725464,
      "eval_runtime": 10.316,
      "eval_samples_per_second": 2.908,
      "eval_steps_per_second": 0.775,
      "step": 30
    },
    {
      "epoch": 1.0336134453781514,
      "grad_norm": 0.647661030292511,
      "learning_rate": 0.0001,
      "loss": 1.6719216108322144,
      "step": 31
    },
    {
      "epoch": 1.0672268907563025,
      "grad_norm": 0.6397345066070557,
      "learning_rate": 9.952380952380953e-05,
      "loss": 1.668287992477417,
      "step": 32
    },
    {
      "epoch": 1.1008403361344539,
      "grad_norm": 0.6300156712532043,
      "learning_rate": 9.904761904761905e-05,
      "loss": 1.5873429775238037,
      "step": 33
    },
    {
      "epoch": 1.134453781512605,
      "grad_norm": 0.6707726120948792,
      "learning_rate": 9.857142857142858e-05,
      "loss": 1.6546002626419067,
      "step": 34
    },
    {
      "epoch": 1.1680672268907564,
      "grad_norm": 0.7279041409492493,
      "learning_rate": 9.80952380952381e-05,
      "loss": 1.655625581741333,
      "step": 35
    },
    {
      "epoch": 1.2016806722689075,
      "grad_norm": 0.667449414730072,
      "learning_rate": 9.761904761904762e-05,
      "loss": 1.515287160873413,
      "step": 36
    },
    {
      "epoch": 1.2352941176470589,
      "grad_norm": 0.6200292706489563,
      "learning_rate": 9.714285714285715e-05,
      "loss": 1.4442039728164673,
      "step": 37
    },
    {
      "epoch": 1.26890756302521,
      "grad_norm": 0.675460934638977,
      "learning_rate": 9.666666666666667e-05,
      "loss": 1.5320563316345215,
      "step": 38
    },
    {
      "epoch": 1.3025210084033614,
      "grad_norm": 0.699114203453064,
      "learning_rate": 9.61904761904762e-05,
      "loss": 1.4822273254394531,
      "step": 39
    },
    {
      "epoch": 1.3361344537815127,
      "grad_norm": 0.6445063948631287,
      "learning_rate": 9.571428571428573e-05,
      "loss": 1.5780315399169922,
      "step": 40
    },
    {
      "epoch": 1.3697478991596639,
      "grad_norm": 0.6698673963546753,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.4848202466964722,
      "step": 41
    },
    {
      "epoch": 1.403361344537815,
      "grad_norm": 0.6834254860877991,
      "learning_rate": 9.476190476190476e-05,
      "loss": 1.468376874923706,
      "step": 42
    },
    {
      "epoch": 1.4369747899159664,
      "grad_norm": 0.6594065427780151,
      "learning_rate": 9.428571428571429e-05,
      "loss": 1.5328936576843262,
      "step": 43
    },
    {
      "epoch": 1.4705882352941178,
      "grad_norm": 0.6601908206939697,
      "learning_rate": 9.380952380952381e-05,
      "loss": 1.4440678358078003,
      "step": 44
    },
    {
      "epoch": 1.504201680672269,
      "grad_norm": 0.640671968460083,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.4095360040664673,
      "step": 45
    },
    {
      "epoch": 1.53781512605042,
      "grad_norm": 0.6808314323425293,
      "learning_rate": 9.285714285714286e-05,
      "loss": 1.385438323020935,
      "step": 46
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.7171391248703003,
      "learning_rate": 9.238095238095239e-05,
      "loss": 1.46902596950531,
      "step": 47
    },
    {
      "epoch": 1.6050420168067228,
      "grad_norm": 0.7047857642173767,
      "learning_rate": 9.19047619047619e-05,
      "loss": 1.417210340499878,
      "step": 48
    },
    {
      "epoch": 1.638655462184874,
      "grad_norm": 0.7122965455055237,
      "learning_rate": 9.142857142857143e-05,
      "loss": 1.5123244524002075,
      "step": 49
    },
    {
      "epoch": 1.6722689075630253,
      "grad_norm": 0.7607484459877014,
      "learning_rate": 9.095238095238096e-05,
      "loss": 1.4195809364318848,
      "step": 50
    },
    {
      "epoch": 1.7058823529411766,
      "grad_norm": 0.718349039554596,
      "learning_rate": 9.047619047619048e-05,
      "loss": 1.3647619485855103,
      "step": 51
    },
    {
      "epoch": 1.7394957983193278,
      "grad_norm": 0.7725448608398438,
      "learning_rate": 9e-05,
      "loss": 1.4874149560928345,
      "step": 52
    },
    {
      "epoch": 1.773109243697479,
      "grad_norm": 0.775120735168457,
      "learning_rate": 8.952380952380953e-05,
      "loss": 1.453145980834961,
      "step": 53
    },
    {
      "epoch": 1.8067226890756303,
      "grad_norm": 0.7395671010017395,
      "learning_rate": 8.904761904761905e-05,
      "loss": 1.4509263038635254,
      "step": 54
    },
    {
      "epoch": 1.8403361344537816,
      "grad_norm": 0.8163217306137085,
      "learning_rate": 8.857142857142857e-05,
      "loss": 1.3568434715270996,
      "step": 55
    },
    {
      "epoch": 1.8739495798319328,
      "grad_norm": 0.7869181632995605,
      "learning_rate": 8.80952380952381e-05,
      "loss": 1.407705307006836,
      "step": 56
    },
    {
      "epoch": 1.907563025210084,
      "grad_norm": 0.8495688438415527,
      "learning_rate": 8.761904761904762e-05,
      "loss": 1.4618957042694092,
      "step": 57
    },
    {
      "epoch": 1.9411764705882353,
      "grad_norm": 0.7417442798614502,
      "learning_rate": 8.714285714285715e-05,
      "loss": 1.4034532308578491,
      "step": 58
    },
    {
      "epoch": 1.9747899159663866,
      "grad_norm": 0.7855961322784424,
      "learning_rate": 8.666666666666667e-05,
      "loss": 1.4118345975875854,
      "step": 59
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.8862755298614502,
      "learning_rate": 8.61904761904762e-05,
      "loss": 1.2757116556167603,
      "step": 60
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.4056180715560913,
      "eval_runtime": 3.9176,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 2.042,
      "step": 60
    },
    {
      "epoch": 2.033613445378151,
      "grad_norm": 0.7814940214157104,
      "learning_rate": 8.571428571428571e-05,
      "loss": 1.2302533388137817,
      "step": 61
    },
    {
      "epoch": 2.0672268907563027,
      "grad_norm": 0.7992838025093079,
      "learning_rate": 8.523809523809524e-05,
      "loss": 1.216611385345459,
      "step": 62
    },
    {
      "epoch": 2.100840336134454,
      "grad_norm": 0.7737162113189697,
      "learning_rate": 8.476190476190477e-05,
      "loss": 1.3414034843444824,
      "step": 63
    },
    {
      "epoch": 2.134453781512605,
      "grad_norm": 0.8357487320899963,
      "learning_rate": 8.428571428571429e-05,
      "loss": 1.3190107345581055,
      "step": 64
    },
    {
      "epoch": 2.168067226890756,
      "grad_norm": 0.8190802931785583,
      "learning_rate": 8.380952380952382e-05,
      "loss": 1.2389566898345947,
      "step": 65
    },
    {
      "epoch": 2.2016806722689077,
      "grad_norm": 0.864143431186676,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.2354176044464111,
      "step": 66
    },
    {
      "epoch": 2.235294117647059,
      "grad_norm": 0.8392678499221802,
      "learning_rate": 8.285714285714287e-05,
      "loss": 1.1950651407241821,
      "step": 67
    },
    {
      "epoch": 2.26890756302521,
      "grad_norm": 0.9009263515472412,
      "learning_rate": 8.238095238095238e-05,
      "loss": 1.208898663520813,
      "step": 68
    },
    {
      "epoch": 2.302521008403361,
      "grad_norm": 0.9575037360191345,
      "learning_rate": 8.19047619047619e-05,
      "loss": 1.2858699560165405,
      "step": 69
    },
    {
      "epoch": 2.3361344537815127,
      "grad_norm": 0.9792712926864624,
      "learning_rate": 8.142857142857143e-05,
      "loss": 1.2072560787200928,
      "step": 70
    },
    {
      "epoch": 2.369747899159664,
      "grad_norm": 0.9120011329650879,
      "learning_rate": 8.095238095238096e-05,
      "loss": 1.323483943939209,
      "step": 71
    },
    {
      "epoch": 2.403361344537815,
      "grad_norm": 0.945496678352356,
      "learning_rate": 8.047619047619048e-05,
      "loss": 1.2234930992126465,
      "step": 72
    },
    {
      "epoch": 2.4369747899159666,
      "grad_norm": 0.8917703032493591,
      "learning_rate": 8e-05,
      "loss": 1.243606686592102,
      "step": 73
    },
    {
      "epoch": 2.4705882352941178,
      "grad_norm": 0.9565060138702393,
      "learning_rate": 7.952380952380952e-05,
      "loss": 1.304957389831543,
      "step": 74
    },
    {
      "epoch": 2.504201680672269,
      "grad_norm": 0.9710495471954346,
      "learning_rate": 7.904761904761905e-05,
      "loss": 1.3234366178512573,
      "step": 75
    },
    {
      "epoch": 2.53781512605042,
      "grad_norm": 0.9468457698822021,
      "learning_rate": 7.857142857142858e-05,
      "loss": 1.1979341506958008,
      "step": 76
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.9551314115524292,
      "learning_rate": 7.80952380952381e-05,
      "loss": 1.326904535293579,
      "step": 77
    },
    {
      "epoch": 2.6050420168067228,
      "grad_norm": 0.91373211145401,
      "learning_rate": 7.761904761904762e-05,
      "loss": 1.225470781326294,
      "step": 78
    },
    {
      "epoch": 2.638655462184874,
      "grad_norm": 1.0344769954681396,
      "learning_rate": 7.714285714285715e-05,
      "loss": 1.3594175577163696,
      "step": 79
    },
    {
      "epoch": 2.6722689075630255,
      "grad_norm": 0.9641366600990295,
      "learning_rate": 7.666666666666667e-05,
      "loss": 1.2756738662719727,
      "step": 80
    },
    {
      "epoch": 2.7058823529411766,
      "grad_norm": 1.0200080871582031,
      "learning_rate": 7.619047619047618e-05,
      "loss": 1.1892673969268799,
      "step": 81
    },
    {
      "epoch": 2.7394957983193278,
      "grad_norm": 1.0370545387268066,
      "learning_rate": 7.571428571428571e-05,
      "loss": 1.1881890296936035,
      "step": 82
    },
    {
      "epoch": 2.773109243697479,
      "grad_norm": 0.9938557147979736,
      "learning_rate": 7.523809523809524e-05,
      "loss": 1.2509745359420776,
      "step": 83
    },
    {
      "epoch": 2.80672268907563,
      "grad_norm": 1.0122029781341553,
      "learning_rate": 7.476190476190477e-05,
      "loss": 1.2329052686691284,
      "step": 84
    },
    {
      "epoch": 2.8403361344537816,
      "grad_norm": 0.9926727414131165,
      "learning_rate": 7.428571428571429e-05,
      "loss": 1.1865342855453491,
      "step": 85
    },
    {
      "epoch": 2.8739495798319328,
      "grad_norm": 1.0520062446594238,
      "learning_rate": 7.380952380952382e-05,
      "loss": 1.2175326347351074,
      "step": 86
    },
    {
      "epoch": 2.907563025210084,
      "grad_norm": 1.004095196723938,
      "learning_rate": 7.333333333333333e-05,
      "loss": 1.1574434041976929,
      "step": 87
    },
    {
      "epoch": 2.9411764705882355,
      "grad_norm": 1.032243251800537,
      "learning_rate": 7.285714285714286e-05,
      "loss": 1.235571026802063,
      "step": 88
    },
    {
      "epoch": 2.9747899159663866,
      "grad_norm": 1.018995761871338,
      "learning_rate": 7.238095238095238e-05,
      "loss": 1.2259873151779175,
      "step": 89
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.2478784322738647,
      "learning_rate": 7.19047619047619e-05,
      "loss": 1.1681110858917236,
      "step": 90
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.3273810148239136,
      "eval_runtime": 3.7073,
      "eval_samples_per_second": 8.092,
      "eval_steps_per_second": 2.158,
      "step": 90
    },
    {
      "epoch": 3.033613445378151,
      "grad_norm": 1.01819908618927,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.1786319017410278,
      "step": 91
    },
    {
      "epoch": 3.0672268907563027,
      "grad_norm": 1.0133390426635742,
      "learning_rate": 7.095238095238096e-05,
      "loss": 1.084567666053772,
      "step": 92
    },
    {
      "epoch": 3.100840336134454,
      "grad_norm": 1.033138632774353,
      "learning_rate": 7.047619047619048e-05,
      "loss": 1.1097135543823242,
      "step": 93
    },
    {
      "epoch": 3.134453781512605,
      "grad_norm": 0.9845293760299683,
      "learning_rate": 7e-05,
      "loss": 1.1596248149871826,
      "step": 94
    },
    {
      "epoch": 3.168067226890756,
      "grad_norm": 1.0302462577819824,
      "learning_rate": 6.952380952380952e-05,
      "loss": 0.9933599233627319,
      "step": 95
    },
    {
      "epoch": 3.2016806722689077,
      "grad_norm": 1.0635849237442017,
      "learning_rate": 6.904761904761905e-05,
      "loss": 1.124208927154541,
      "step": 96
    },
    {
      "epoch": 3.235294117647059,
      "grad_norm": 0.9977414011955261,
      "learning_rate": 6.857142857142858e-05,
      "loss": 1.0854753255844116,
      "step": 97
    },
    {
      "epoch": 3.26890756302521,
      "grad_norm": 1.0512261390686035,
      "learning_rate": 6.80952380952381e-05,
      "loss": 1.0794872045516968,
      "step": 98
    },
    {
      "epoch": 3.302521008403361,
      "grad_norm": 1.0492438077926636,
      "learning_rate": 6.761904761904763e-05,
      "loss": 1.154089093208313,
      "step": 99
    },
    {
      "epoch": 3.3361344537815127,
      "grad_norm": 1.1196621656417847,
      "learning_rate": 6.714285714285714e-05,
      "loss": 1.0679287910461426,
      "step": 100
    },
    {
      "epoch": 3.369747899159664,
      "grad_norm": 1.1757211685180664,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.0951473712921143,
      "step": 101
    },
    {
      "epoch": 3.403361344537815,
      "grad_norm": 1.095960259437561,
      "learning_rate": 6.619047619047619e-05,
      "loss": 1.0922937393188477,
      "step": 102
    },
    {
      "epoch": 3.4369747899159666,
      "grad_norm": 1.2442125082015991,
      "learning_rate": 6.571428571428571e-05,
      "loss": 1.1162358522415161,
      "step": 103
    },
    {
      "epoch": 3.4705882352941178,
      "grad_norm": 1.1093356609344482,
      "learning_rate": 6.523809523809524e-05,
      "loss": 1.0763335227966309,
      "step": 104
    },
    {
      "epoch": 3.504201680672269,
      "grad_norm": 1.120429515838623,
      "learning_rate": 6.476190476190477e-05,
      "loss": 1.04691481590271,
      "step": 105
    },
    {
      "epoch": 3.53781512605042,
      "grad_norm": 1.0883711576461792,
      "learning_rate": 6.428571428571429e-05,
      "loss": 1.0226696729660034,
      "step": 106
    },
    {
      "epoch": 3.571428571428571,
      "grad_norm": 1.2264426946640015,
      "learning_rate": 6.38095238095238e-05,
      "loss": 1.1683363914489746,
      "step": 107
    },
    {
      "epoch": 3.6050420168067228,
      "grad_norm": 1.2050789594650269,
      "learning_rate": 6.333333333333333e-05,
      "loss": 1.024131178855896,
      "step": 108
    },
    {
      "epoch": 3.638655462184874,
      "grad_norm": 1.180884599685669,
      "learning_rate": 6.285714285714286e-05,
      "loss": 1.1517013311386108,
      "step": 109
    },
    {
      "epoch": 3.6722689075630255,
      "grad_norm": 1.144343376159668,
      "learning_rate": 6.238095238095239e-05,
      "loss": 1.0957340002059937,
      "step": 110
    },
    {
      "epoch": 3.7058823529411766,
      "grad_norm": 1.183537483215332,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.9810922145843506,
      "step": 111
    },
    {
      "epoch": 3.7394957983193278,
      "grad_norm": 1.1150946617126465,
      "learning_rate": 6.142857142857143e-05,
      "loss": 1.0473538637161255,
      "step": 112
    },
    {
      "epoch": 3.773109243697479,
      "grad_norm": 1.221834421157837,
      "learning_rate": 6.0952380952380964e-05,
      "loss": 1.1923342943191528,
      "step": 113
    },
    {
      "epoch": 3.80672268907563,
      "grad_norm": 1.2329802513122559,
      "learning_rate": 6.047619047619047e-05,
      "loss": 1.0775328874588013,
      "step": 114
    },
    {
      "epoch": 3.8403361344537816,
      "grad_norm": 1.090965986251831,
      "learning_rate": 6e-05,
      "loss": 1.0452823638916016,
      "step": 115
    },
    {
      "epoch": 3.8739495798319328,
      "grad_norm": 1.173295497894287,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 1.0261826515197754,
      "step": 116
    },
    {
      "epoch": 3.907563025210084,
      "grad_norm": 1.2157574892044067,
      "learning_rate": 5.904761904761905e-05,
      "loss": 1.0396374464035034,
      "step": 117
    },
    {
      "epoch": 3.9411764705882355,
      "grad_norm": 1.1849799156188965,
      "learning_rate": 5.8571428571428575e-05,
      "loss": 1.0875635147094727,
      "step": 118
    },
    {
      "epoch": 3.9747899159663866,
      "grad_norm": 1.2327245473861694,
      "learning_rate": 5.8095238095238104e-05,
      "loss": 1.0007489919662476,
      "step": 119
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.4210413694381714,
      "learning_rate": 5.761904761904762e-05,
      "loss": 1.1383683681488037,
      "step": 120
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.2939602136611938,
      "eval_runtime": 3.7674,
      "eval_samples_per_second": 7.963,
      "eval_steps_per_second": 2.123,
      "step": 120
    },
    {
      "epoch": 4.033613445378151,
      "grad_norm": 1.3323708772659302,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.9700905084609985,
      "step": 121
    },
    {
      "epoch": 4.067226890756302,
      "grad_norm": 1.157588243484497,
      "learning_rate": 5.666666666666667e-05,
      "loss": 0.9543254971504211,
      "step": 122
    },
    {
      "epoch": 4.100840336134453,
      "grad_norm": 1.1722387075424194,
      "learning_rate": 5.619047619047619e-05,
      "loss": 0.9472344517707825,
      "step": 123
    },
    {
      "epoch": 4.1344537815126055,
      "grad_norm": 1.1014832258224487,
      "learning_rate": 5.571428571428572e-05,
      "loss": 0.8803507089614868,
      "step": 124
    },
    {
      "epoch": 4.168067226890757,
      "grad_norm": 1.2056872844696045,
      "learning_rate": 5.5238095238095244e-05,
      "loss": 1.013951063156128,
      "step": 125
    },
    {
      "epoch": 4.201680672268908,
      "grad_norm": 1.1956983804702759,
      "learning_rate": 5.4761904761904766e-05,
      "loss": 0.9990006685256958,
      "step": 126
    },
    {
      "epoch": 4.235294117647059,
      "grad_norm": 1.2622699737548828,
      "learning_rate": 5.428571428571428e-05,
      "loss": 1.0677868127822876,
      "step": 127
    },
    {
      "epoch": 4.26890756302521,
      "grad_norm": 1.2382571697235107,
      "learning_rate": 5.380952380952381e-05,
      "loss": 1.0605125427246094,
      "step": 128
    },
    {
      "epoch": 4.302521008403361,
      "grad_norm": 1.3250623941421509,
      "learning_rate": 5.333333333333333e-05,
      "loss": 0.9158158302307129,
      "step": 129
    },
    {
      "epoch": 4.336134453781512,
      "grad_norm": 1.375975489616394,
      "learning_rate": 5.285714285714286e-05,
      "loss": 1.022152066230774,
      "step": 130
    },
    {
      "epoch": 4.369747899159664,
      "grad_norm": 1.2726337909698486,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.8684637546539307,
      "step": 131
    },
    {
      "epoch": 4.4033613445378155,
      "grad_norm": 1.3542131185531616,
      "learning_rate": 5.1904761904761913e-05,
      "loss": 0.9598578214645386,
      "step": 132
    },
    {
      "epoch": 4.436974789915967,
      "grad_norm": 1.2506901025772095,
      "learning_rate": 5.142857142857143e-05,
      "loss": 0.9017740488052368,
      "step": 133
    },
    {
      "epoch": 4.470588235294118,
      "grad_norm": 1.4717071056365967,
      "learning_rate": 5.095238095238095e-05,
      "loss": 1.0545717477798462,
      "step": 134
    },
    {
      "epoch": 4.504201680672269,
      "grad_norm": 1.401831030845642,
      "learning_rate": 5.047619047619048e-05,
      "loss": 0.9351727962493896,
      "step": 135
    },
    {
      "epoch": 4.53781512605042,
      "grad_norm": 1.3386850357055664,
      "learning_rate": 5e-05,
      "loss": 1.0716379880905151,
      "step": 136
    },
    {
      "epoch": 4.571428571428571,
      "grad_norm": 1.3194583654403687,
      "learning_rate": 4.9523809523809525e-05,
      "loss": 0.8626317977905273,
      "step": 137
    },
    {
      "epoch": 4.605042016806722,
      "grad_norm": 1.292224407196045,
      "learning_rate": 4.904761904761905e-05,
      "loss": 0.9414288401603699,
      "step": 138
    },
    {
      "epoch": 4.6386554621848735,
      "grad_norm": 1.3260385990142822,
      "learning_rate": 4.8571428571428576e-05,
      "loss": 1.0110278129577637,
      "step": 139
    },
    {
      "epoch": 4.6722689075630255,
      "grad_norm": 1.3317372798919678,
      "learning_rate": 4.80952380952381e-05,
      "loss": 0.867744505405426,
      "step": 140
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 1.3410000801086426,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.9864277839660645,
      "step": 141
    },
    {
      "epoch": 4.739495798319328,
      "grad_norm": 1.300334095954895,
      "learning_rate": 4.714285714285714e-05,
      "loss": 0.9903122782707214,
      "step": 142
    },
    {
      "epoch": 4.773109243697479,
      "grad_norm": 1.2690436840057373,
      "learning_rate": 4.666666666666667e-05,
      "loss": 0.9659175872802734,
      "step": 143
    },
    {
      "epoch": 4.80672268907563,
      "grad_norm": 1.296320915222168,
      "learning_rate": 4.6190476190476194e-05,
      "loss": 0.9871109127998352,
      "step": 144
    },
    {
      "epoch": 4.840336134453781,
      "grad_norm": 1.295183539390564,
      "learning_rate": 4.5714285714285716e-05,
      "loss": 0.9477449655532837,
      "step": 145
    },
    {
      "epoch": 4.873949579831933,
      "grad_norm": 1.2733242511749268,
      "learning_rate": 4.523809523809524e-05,
      "loss": 0.8972955942153931,
      "step": 146
    },
    {
      "epoch": 4.907563025210084,
      "grad_norm": 1.4080476760864258,
      "learning_rate": 4.476190476190477e-05,
      "loss": 0.8996440172195435,
      "step": 147
    },
    {
      "epoch": 4.9411764705882355,
      "grad_norm": 1.342236876487732,
      "learning_rate": 4.428571428571428e-05,
      "loss": 0.9778165221214294,
      "step": 148
    },
    {
      "epoch": 4.974789915966387,
      "grad_norm": 1.296331524848938,
      "learning_rate": 4.380952380952381e-05,
      "loss": 0.9994407892227173,
      "step": 149
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.4680155515670776,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.8228248357772827,
      "step": 150
    },
    {
      "epoch": 5.0,
      "eval_loss": 1.2925209999084473,
      "eval_runtime": 3.7565,
      "eval_samples_per_second": 7.986,
      "eval_steps_per_second": 2.13,
      "step": 150
    },
    {
      "epoch": 5.033613445378151,
      "grad_norm": 1.2372772693634033,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.9601858854293823,
      "step": 151
    },
    {
      "epoch": 5.067226890756302,
      "grad_norm": 1.4262580871582031,
      "learning_rate": 4.2380952380952385e-05,
      "loss": 0.8740893006324768,
      "step": 152
    },
    {
      "epoch": 5.100840336134453,
      "grad_norm": 1.3301628828048706,
      "learning_rate": 4.190476190476191e-05,
      "loss": 0.869416356086731,
      "step": 153
    },
    {
      "epoch": 5.1344537815126055,
      "grad_norm": 1.246441125869751,
      "learning_rate": 4.1428571428571437e-05,
      "loss": 0.9064545631408691,
      "step": 154
    },
    {
      "epoch": 5.168067226890757,
      "grad_norm": 1.325980305671692,
      "learning_rate": 4.095238095238095e-05,
      "loss": 0.7957058548927307,
      "step": 155
    },
    {
      "epoch": 5.201680672268908,
      "grad_norm": 1.31040358543396,
      "learning_rate": 4.047619047619048e-05,
      "loss": 0.8725865483283997,
      "step": 156
    },
    {
      "epoch": 5.235294117647059,
      "grad_norm": 1.4009162187576294,
      "learning_rate": 4e-05,
      "loss": 0.8454779982566833,
      "step": 157
    },
    {
      "epoch": 5.26890756302521,
      "grad_norm": 1.4027854204177856,
      "learning_rate": 3.9523809523809526e-05,
      "loss": 0.7872403860092163,
      "step": 158
    },
    {
      "epoch": 5.302521008403361,
      "grad_norm": 1.493884563446045,
      "learning_rate": 3.904761904761905e-05,
      "loss": 0.8251349925994873,
      "step": 159
    },
    {
      "epoch": 5.336134453781512,
      "grad_norm": 1.4308027029037476,
      "learning_rate": 3.857142857142858e-05,
      "loss": 0.9870215654373169,
      "step": 160
    },
    {
      "epoch": 5.369747899159664,
      "grad_norm": 1.633083701133728,
      "learning_rate": 3.809523809523809e-05,
      "loss": 1.0086315870285034,
      "step": 161
    },
    {
      "epoch": 5.4033613445378155,
      "grad_norm": 1.4386212825775146,
      "learning_rate": 3.761904761904762e-05,
      "loss": 0.9549638032913208,
      "step": 162
    },
    {
      "epoch": 5.436974789915967,
      "grad_norm": 1.4481375217437744,
      "learning_rate": 3.7142857142857143e-05,
      "loss": 0.8349080085754395,
      "step": 163
    },
    {
      "epoch": 5.470588235294118,
      "grad_norm": 1.3857380151748657,
      "learning_rate": 3.6666666666666666e-05,
      "loss": 0.8275986909866333,
      "step": 164
    },
    {
      "epoch": 5.504201680672269,
      "grad_norm": 1.4976426362991333,
      "learning_rate": 3.619047619047619e-05,
      "loss": 0.941012978553772,
      "step": 165
    },
    {
      "epoch": 5.53781512605042,
      "grad_norm": 1.3737095594406128,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.9091029167175293,
      "step": 166
    },
    {
      "epoch": 5.571428571428571,
      "grad_norm": 1.4205622673034668,
      "learning_rate": 3.523809523809524e-05,
      "loss": 0.8211807608604431,
      "step": 167
    },
    {
      "epoch": 5.605042016806722,
      "grad_norm": 1.378404140472412,
      "learning_rate": 3.476190476190476e-05,
      "loss": 0.8508516550064087,
      "step": 168
    },
    {
      "epoch": 5.6386554621848735,
      "grad_norm": 1.3551448583602905,
      "learning_rate": 3.428571428571429e-05,
      "loss": 0.7649774551391602,
      "step": 169
    },
    {
      "epoch": 5.6722689075630255,
      "grad_norm": 1.374902367591858,
      "learning_rate": 3.380952380952381e-05,
      "loss": 0.86110919713974,
      "step": 170
    },
    {
      "epoch": 5.705882352941177,
      "grad_norm": 1.3408621549606323,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8505116701126099,
      "step": 171
    },
    {
      "epoch": 5.739495798319328,
      "grad_norm": 1.3615412712097168,
      "learning_rate": 3.285714285714286e-05,
      "loss": 0.8388904929161072,
      "step": 172
    },
    {
      "epoch": 5.773109243697479,
      "grad_norm": 1.412241816520691,
      "learning_rate": 3.2380952380952386e-05,
      "loss": 0.7976136207580566,
      "step": 173
    },
    {
      "epoch": 5.80672268907563,
      "grad_norm": 1.4513007402420044,
      "learning_rate": 3.19047619047619e-05,
      "loss": 0.8578696846961975,
      "step": 174
    },
    {
      "epoch": 5.840336134453781,
      "grad_norm": 1.510588526725769,
      "learning_rate": 3.142857142857143e-05,
      "loss": 0.8328684568405151,
      "step": 175
    },
    {
      "epoch": 5.873949579831933,
      "grad_norm": 1.4201253652572632,
      "learning_rate": 3.095238095238095e-05,
      "loss": 0.8719969987869263,
      "step": 176
    },
    {
      "epoch": 5.907563025210084,
      "grad_norm": 1.3854255676269531,
      "learning_rate": 3.0476190476190482e-05,
      "loss": 0.8317468762397766,
      "step": 177
    },
    {
      "epoch": 5.9411764705882355,
      "grad_norm": 1.5505516529083252,
      "learning_rate": 3e-05,
      "loss": 0.9684892296791077,
      "step": 178
    },
    {
      "epoch": 5.974789915966387,
      "grad_norm": 1.3831605911254883,
      "learning_rate": 2.9523809523809526e-05,
      "loss": 0.846987783908844,
      "step": 179
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.604284405708313,
      "learning_rate": 2.9047619047619052e-05,
      "loss": 0.7163129448890686,
      "step": 180
    },
    {
      "epoch": 6.0,
      "eval_loss": 1.3178263902664185,
      "eval_runtime": 3.7922,
      "eval_samples_per_second": 7.911,
      "eval_steps_per_second": 2.11,
      "step": 180
    },
    {
      "epoch": 6.033613445378151,
      "grad_norm": 1.3698841333389282,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.8407258987426758,
      "step": 181
    },
    {
      "epoch": 6.067226890756302,
      "grad_norm": 1.3582322597503662,
      "learning_rate": 2.8095238095238096e-05,
      "loss": 0.7506957054138184,
      "step": 182
    },
    {
      "epoch": 6.100840336134453,
      "grad_norm": 1.3459149599075317,
      "learning_rate": 2.7619047619047622e-05,
      "loss": 0.7720663547515869,
      "step": 183
    },
    {
      "epoch": 6.1344537815126055,
      "grad_norm": 1.367708444595337,
      "learning_rate": 2.714285714285714e-05,
      "loss": 0.7555418014526367,
      "step": 184
    },
    {
      "epoch": 6.168067226890757,
      "grad_norm": 1.3215985298156738,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.7585124969482422,
      "step": 185
    },
    {
      "epoch": 6.201680672268908,
      "grad_norm": 1.3321973085403442,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.7861344814300537,
      "step": 186
    },
    {
      "epoch": 6.235294117647059,
      "grad_norm": 1.5063412189483643,
      "learning_rate": 2.5714285714285714e-05,
      "loss": 0.7867593765258789,
      "step": 187
    },
    {
      "epoch": 6.26890756302521,
      "grad_norm": 1.39756178855896,
      "learning_rate": 2.523809523809524e-05,
      "loss": 0.7141340970993042,
      "step": 188
    },
    {
      "epoch": 6.302521008403361,
      "grad_norm": 1.4180450439453125,
      "learning_rate": 2.4761904761904762e-05,
      "loss": 0.6977301836013794,
      "step": 189
    },
    {
      "epoch": 6.336134453781512,
      "grad_norm": 1.47915780544281,
      "learning_rate": 2.4285714285714288e-05,
      "loss": 0.8296221494674683,
      "step": 190
    },
    {
      "epoch": 6.369747899159664,
      "grad_norm": 1.4556329250335693,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.7570559978485107,
      "step": 191
    },
    {
      "epoch": 6.4033613445378155,
      "grad_norm": 1.5441046953201294,
      "learning_rate": 2.3333333333333336e-05,
      "loss": 0.8604129552841187,
      "step": 192
    },
    {
      "epoch": 6.436974789915967,
      "grad_norm": 1.4511024951934814,
      "learning_rate": 2.2857142857142858e-05,
      "loss": 0.7141028046607971,
      "step": 193
    },
    {
      "epoch": 6.470588235294118,
      "grad_norm": 1.484963297843933,
      "learning_rate": 2.2380952380952384e-05,
      "loss": 0.7948105335235596,
      "step": 194
    },
    {
      "epoch": 6.504201680672269,
      "grad_norm": 1.437523603439331,
      "learning_rate": 2.1904761904761906e-05,
      "loss": 0.8105779886245728,
      "step": 195
    },
    {
      "epoch": 6.53781512605042,
      "grad_norm": 1.4925854206085205,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.9170101284980774,
      "step": 196
    },
    {
      "epoch": 6.571428571428571,
      "grad_norm": 1.4464846849441528,
      "learning_rate": 2.0952380952380954e-05,
      "loss": 0.757552981376648,
      "step": 197
    },
    {
      "epoch": 6.605042016806722,
      "grad_norm": 1.4769630432128906,
      "learning_rate": 2.0476190476190476e-05,
      "loss": 0.8065693974494934,
      "step": 198
    },
    {
      "epoch": 6.6386554621848735,
      "grad_norm": 1.5437406301498413,
      "learning_rate": 2e-05,
      "loss": 0.7980015277862549,
      "step": 199
    },
    {
      "epoch": 6.6722689075630255,
      "grad_norm": 1.4256641864776611,
      "learning_rate": 1.9523809523809524e-05,
      "loss": 0.7723953127861023,
      "step": 200
    },
    {
      "epoch": 6.705882352941177,
      "grad_norm": 1.4764693975448608,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.771976888179779,
      "step": 201
    },
    {
      "epoch": 6.739495798319328,
      "grad_norm": 1.439523696899414,
      "learning_rate": 1.8571428571428572e-05,
      "loss": 0.9592650532722473,
      "step": 202
    },
    {
      "epoch": 6.773109243697479,
      "grad_norm": 1.4644689559936523,
      "learning_rate": 1.8095238095238094e-05,
      "loss": 0.832696795463562,
      "step": 203
    },
    {
      "epoch": 6.80672268907563,
      "grad_norm": 1.521827220916748,
      "learning_rate": 1.761904761904762e-05,
      "loss": 0.7094337344169617,
      "step": 204
    },
    {
      "epoch": 6.840336134453781,
      "grad_norm": 1.3857111930847168,
      "learning_rate": 1.7142857142857145e-05,
      "loss": 0.7968447804450989,
      "step": 205
    },
    {
      "epoch": 6.873949579831933,
      "grad_norm": 1.51412034034729,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8035678267478943,
      "step": 206
    },
    {
      "epoch": 6.907563025210084,
      "grad_norm": 1.4831445217132568,
      "learning_rate": 1.6190476190476193e-05,
      "loss": 0.722162127494812,
      "step": 207
    },
    {
      "epoch": 6.9411764705882355,
      "grad_norm": 1.5344971418380737,
      "learning_rate": 1.5714285714285715e-05,
      "loss": 0.775317907333374,
      "step": 208
    },
    {
      "epoch": 6.974789915966387,
      "grad_norm": 1.5456058979034424,
      "learning_rate": 1.5238095238095241e-05,
      "loss": 0.8764552474021912,
      "step": 209
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.6913789510726929,
      "learning_rate": 1.4761904761904763e-05,
      "loss": 0.8050098419189453,
      "step": 210
    },
    {
      "epoch": 7.0,
      "eval_loss": 1.3311940431594849,
      "eval_runtime": 3.7492,
      "eval_samples_per_second": 8.002,
      "eval_steps_per_second": 2.134,
      "step": 210
    },
    {
      "epoch": 7.033613445378151,
      "grad_norm": 1.4000321626663208,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.7460100650787354,
      "step": 211
    },
    {
      "epoch": 7.067226890756302,
      "grad_norm": 1.3848246335983276,
      "learning_rate": 1.3809523809523811e-05,
      "loss": 0.7325513362884521,
      "step": 212
    },
    {
      "epoch": 7.100840336134453,
      "grad_norm": 1.425180435180664,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.789480447769165,
      "step": 213
    },
    {
      "epoch": 7.1344537815126055,
      "grad_norm": 1.4093279838562012,
      "learning_rate": 1.2857142857142857e-05,
      "loss": 0.7406297922134399,
      "step": 214
    },
    {
      "epoch": 7.168067226890757,
      "grad_norm": 1.4485373497009277,
      "learning_rate": 1.2380952380952381e-05,
      "loss": 0.6809248328208923,
      "step": 215
    },
    {
      "epoch": 7.201680672268908,
      "grad_norm": 1.4934123754501343,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 0.7255088686943054,
      "step": 216
    },
    {
      "epoch": 7.235294117647059,
      "grad_norm": 1.3703478574752808,
      "learning_rate": 1.1428571428571429e-05,
      "loss": 0.7459847331047058,
      "step": 217
    },
    {
      "epoch": 7.26890756302521,
      "grad_norm": 1.4828988313674927,
      "learning_rate": 1.0952380952380953e-05,
      "loss": 0.6294959187507629,
      "step": 218
    },
    {
      "epoch": 7.302521008403361,
      "grad_norm": 1.5071167945861816,
      "learning_rate": 1.0476190476190477e-05,
      "loss": 0.9096927642822266,
      "step": 219
    },
    {
      "epoch": 7.336134453781512,
      "grad_norm": 1.4290016889572144,
      "learning_rate": 1e-05,
      "loss": 0.7375680804252625,
      "step": 220
    },
    {
      "epoch": 7.369747899159664,
      "grad_norm": 1.5646793842315674,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.788483738899231,
      "step": 221
    },
    {
      "epoch": 7.4033613445378155,
      "grad_norm": 1.3855115175247192,
      "learning_rate": 9.047619047619047e-06,
      "loss": 0.6606609225273132,
      "step": 222
    },
    {
      "epoch": 7.436974789915967,
      "grad_norm": 1.441724181175232,
      "learning_rate": 8.571428571428573e-06,
      "loss": 0.6409944295883179,
      "step": 223
    },
    {
      "epoch": 7.470588235294118,
      "grad_norm": 1.5175784826278687,
      "learning_rate": 8.095238095238097e-06,
      "loss": 0.726190984249115,
      "step": 224
    },
    {
      "epoch": 7.504201680672269,
      "grad_norm": 1.4521149396896362,
      "learning_rate": 7.6190476190476205e-06,
      "loss": 0.752087414264679,
      "step": 225
    },
    {
      "epoch": 7.53781512605042,
      "grad_norm": 1.5643377304077148,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.8083716630935669,
      "step": 226
    },
    {
      "epoch": 7.571428571428571,
      "grad_norm": 1.5346543788909912,
      "learning_rate": 6.666666666666667e-06,
      "loss": 0.7418915629386902,
      "step": 227
    },
    {
      "epoch": 7.605042016806722,
      "grad_norm": 2.149428129196167,
      "learning_rate": 6.190476190476191e-06,
      "loss": 0.7584688663482666,
      "step": 228
    },
    {
      "epoch": 7.6386554621848735,
      "grad_norm": 1.6285721063613892,
      "learning_rate": 5.7142857142857145e-06,
      "loss": 0.7324772477149963,
      "step": 229
    },
    {
      "epoch": 7.6722689075630255,
      "grad_norm": 1.5537893772125244,
      "learning_rate": 5.2380952380952384e-06,
      "loss": 0.6794352531433105,
      "step": 230
    },
    {
      "epoch": 7.705882352941177,
      "grad_norm": 1.4391292333602905,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 0.7016686797142029,
      "step": 231
    },
    {
      "epoch": 7.739495798319328,
      "grad_norm": 1.5224608182907104,
      "learning_rate": 4.285714285714286e-06,
      "loss": 0.6977232694625854,
      "step": 232
    },
    {
      "epoch": 7.773109243697479,
      "grad_norm": 1.5121573209762573,
      "learning_rate": 3.8095238095238102e-06,
      "loss": 0.8366060853004456,
      "step": 233
    },
    {
      "epoch": 7.80672268907563,
      "grad_norm": 1.4309701919555664,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.7100837826728821,
      "step": 234
    },
    {
      "epoch": 7.840336134453781,
      "grad_norm": 1.4213911294937134,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.6945512294769287,
      "step": 235
    },
    {
      "epoch": 7.873949579831933,
      "grad_norm": 1.5106409788131714,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 0.7124489545822144,
      "step": 236
    },
    {
      "epoch": 7.907563025210084,
      "grad_norm": 1.600222110748291,
      "learning_rate": 1.9047619047619051e-06,
      "loss": 0.8561011552810669,
      "step": 237
    },
    {
      "epoch": 7.9411764705882355,
      "grad_norm": 1.5109663009643555,
      "learning_rate": 1.4285714285714286e-06,
      "loss": 0.7706875205039978,
      "step": 238
    },
    {
      "epoch": 7.974789915966387,
      "grad_norm": 1.4931998252868652,
      "learning_rate": 9.523809523809526e-07,
      "loss": 0.7473949193954468,
      "step": 239
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.663573980331421,
      "learning_rate": 4.761904761904763e-07,
      "loss": 0.7069568037986755,
      "step": 240
    },
    {
      "epoch": 8.0,
      "eval_loss": 1.3596175909042358,
      "eval_runtime": 3.7913,
      "eval_samples_per_second": 7.913,
      "eval_steps_per_second": 2.11,
      "step": 240
    }
  ],
  "logging_steps": 1,
  "max_steps": 240,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8932807519764480.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}