{
  "best_global_step": 4000,
  "best_metric": 0.8817942142486572,
  "best_model_checkpoint": "runs/emotts_ravdess\\checkpoint-4000",
  "epoch": 97.5679012345679,
  "eval_steps": 1000,
  "global_step": 4000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.6172839506172839,
      "grad_norm": 46.678199768066406,
      "learning_rate": 4.800000000000001e-07,
      "loss": 3.4472,
      "step": 25
    },
    {
      "epoch": 1.2222222222222223,
      "grad_norm": 26.903335571289062,
      "learning_rate": 9.800000000000001e-07,
      "loss": 2.9051,
      "step": 50
    },
    {
      "epoch": 1.8395061728395061,
      "grad_norm": 16.712799072265625,
      "learning_rate": 1.48e-06,
      "loss": 2.2302,
      "step": 75
    },
    {
      "epoch": 2.4444444444444446,
      "grad_norm": 11.607951164245605,
      "learning_rate": 1.98e-06,
      "loss": 1.7683,
      "step": 100
    },
    {
      "epoch": 3.049382716049383,
      "grad_norm": 7.216983318328857,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 1.5434,
      "step": 125
    },
    {
      "epoch": 3.6666666666666665,
      "grad_norm": 10.899630546569824,
      "learning_rate": 2.9800000000000003e-06,
      "loss": 1.4385,
      "step": 150
    },
    {
      "epoch": 4.271604938271605,
      "grad_norm": 6.701765537261963,
      "learning_rate": 3.48e-06,
      "loss": 1.3262,
      "step": 175
    },
    {
      "epoch": 4.888888888888889,
      "grad_norm": 9.419053077697754,
      "learning_rate": 3.980000000000001e-06,
      "loss": 1.285,
      "step": 200
    },
    {
      "epoch": 5.493827160493828,
      "grad_norm": 5.913278579711914,
      "learning_rate": 4.48e-06,
      "loss": 1.2503,
      "step": 225
    },
    {
      "epoch": 6.098765432098766,
      "grad_norm": 8.171669006347656,
      "learning_rate": 4.980000000000001e-06,
      "loss": 1.1868,
      "step": 250
    },
    {
      "epoch": 6.716049382716049,
      "grad_norm": 5.54558801651001,
      "learning_rate": 5.480000000000001e-06,
      "loss": 1.1478,
      "step": 275
    },
    {
      "epoch": 7.320987654320987,
      "grad_norm": 5.325434684753418,
      "learning_rate": 5.98e-06,
      "loss": 1.1245,
      "step": 300
    },
    {
      "epoch": 7.938271604938271,
      "grad_norm": 5.406148433685303,
      "learning_rate": 6.480000000000001e-06,
      "loss": 1.1145,
      "step": 325
    },
    {
      "epoch": 8.54320987654321,
      "grad_norm": 8.461536407470703,
      "learning_rate": 6.98e-06,
      "loss": 1.0641,
      "step": 350
    },
    {
      "epoch": 9.148148148148149,
      "grad_norm": 3.8533031940460205,
      "learning_rate": 7.48e-06,
      "loss": 1.0573,
      "step": 375
    },
    {
      "epoch": 9.765432098765432,
      "grad_norm": 7.569976806640625,
      "learning_rate": 7.980000000000002e-06,
      "loss": 1.061,
      "step": 400
    },
    {
      "epoch": 10.37037037037037,
      "grad_norm": 10.156228065490723,
      "learning_rate": 8.48e-06,
      "loss": 1.0485,
      "step": 425
    },
    {
      "epoch": 10.987654320987655,
      "grad_norm": 4.668756484985352,
      "learning_rate": 8.98e-06,
      "loss": 1.0216,
      "step": 450
    },
    {
      "epoch": 11.592592592592592,
      "grad_norm": 5.087125301361084,
      "learning_rate": 9.48e-06,
      "loss": 1.0319,
      "step": 475
    },
    {
      "epoch": 12.197530864197532,
      "grad_norm": 7.943349361419678,
      "learning_rate": 9.980000000000001e-06,
      "loss": 1.0,
      "step": 500
    },
    {
      "epoch": 12.814814814814815,
      "grad_norm": 7.655898571014404,
      "learning_rate": 9.931428571428571e-06,
      "loss": 1.0052,
      "step": 525
    },
    {
      "epoch": 13.419753086419753,
      "grad_norm": 4.458106994628906,
      "learning_rate": 9.86e-06,
      "loss": 1.0001,
      "step": 550
    },
    {
      "epoch": 14.024691358024691,
      "grad_norm": 9.058222770690918,
      "learning_rate": 9.78857142857143e-06,
      "loss": 1.0015,
      "step": 575
    },
    {
      "epoch": 14.641975308641975,
      "grad_norm": 4.795205593109131,
      "learning_rate": 9.717142857142858e-06,
      "loss": 0.9836,
      "step": 600
    },
    {
      "epoch": 15.246913580246913,
      "grad_norm": 10.566876411437988,
      "learning_rate": 9.645714285714286e-06,
      "loss": 1.0019,
      "step": 625
    },
    {
      "epoch": 15.864197530864198,
      "grad_norm": 7.610626220703125,
      "learning_rate": 9.574285714285715e-06,
      "loss": 0.9779,
      "step": 650
    },
    {
      "epoch": 16.469135802469136,
      "grad_norm": 6.008159637451172,
      "learning_rate": 9.502857142857144e-06,
      "loss": 0.9798,
      "step": 675
    },
    {
      "epoch": 17.074074074074073,
      "grad_norm": 6.685286521911621,
      "learning_rate": 9.431428571428573e-06,
      "loss": 0.9753,
      "step": 700
    },
    {
      "epoch": 17.691358024691358,
      "grad_norm": 2.7540247440338135,
      "learning_rate": 9.360000000000002e-06,
      "loss": 0.967,
      "step": 725
    },
    {
      "epoch": 18.296296296296298,
      "grad_norm": 4.825072288513184,
      "learning_rate": 9.28857142857143e-06,
      "loss": 0.9575,
      "step": 750
    },
    {
      "epoch": 18.91358024691358,
      "grad_norm": 6.618119716644287,
      "learning_rate": 9.217142857142858e-06,
      "loss": 0.9675,
      "step": 775
    },
    {
      "epoch": 19.51851851851852,
      "grad_norm": 5.465808391571045,
      "learning_rate": 9.145714285714287e-06,
      "loss": 0.9626,
      "step": 800
    },
    {
      "epoch": 20.123456790123456,
      "grad_norm": 4.9501051902771,
      "learning_rate": 9.074285714285716e-06,
      "loss": 0.9638,
      "step": 825
    },
    {
      "epoch": 20.74074074074074,
      "grad_norm": 4.926831245422363,
      "learning_rate": 9.002857142857144e-06,
      "loss": 0.9582,
      "step": 850
    },
    {
      "epoch": 21.34567901234568,
      "grad_norm": 6.605464458465576,
      "learning_rate": 8.931428571428573e-06,
      "loss": 0.9551,
      "step": 875
    },
    {
      "epoch": 21.962962962962962,
      "grad_norm": 5.774538040161133,
      "learning_rate": 8.860000000000002e-06,
      "loss": 0.9596,
      "step": 900
    },
    {
      "epoch": 22.567901234567902,
      "grad_norm": 4.304802417755127,
      "learning_rate": 8.788571428571429e-06,
      "loss": 0.9489,
      "step": 925
    },
    {
      "epoch": 23.17283950617284,
      "grad_norm": 5.171604633331299,
      "learning_rate": 8.717142857142858e-06,
      "loss": 0.953,
      "step": 950
    },
    {
      "epoch": 23.790123456790123,
      "grad_norm": 7.152281761169434,
      "learning_rate": 8.645714285714287e-06,
      "loss": 0.9604,
      "step": 975
    },
    {
      "epoch": 24.395061728395063,
      "grad_norm": 4.954558849334717,
      "learning_rate": 8.574285714285714e-06,
      "loss": 0.9489,
      "step": 1000
    },
    {
      "epoch": 24.395061728395063,
      "eval_loss": 0.9205830097198486,
      "eval_runtime": 2.2708,
      "eval_samples_per_second": 63.413,
      "eval_steps_per_second": 31.707,
      "step": 1000
    },
    {
      "epoch": 25.0,
      "grad_norm": 10.266937255859375,
      "learning_rate": 8.502857142857143e-06,
      "loss": 0.9541,
      "step": 1025
    },
    {
      "epoch": 25.617283950617285,
      "grad_norm": 3.225881814956665,
      "learning_rate": 8.431428571428572e-06,
      "loss": 0.9451,
      "step": 1050
    },
    {
      "epoch": 26.22222222222222,
      "grad_norm": 4.001440048217773,
      "learning_rate": 8.36e-06,
      "loss": 0.9422,
      "step": 1075
    },
    {
      "epoch": 26.839506172839506,
      "grad_norm": 5.347984313964844,
      "learning_rate": 8.288571428571429e-06,
      "loss": 0.9434,
      "step": 1100
    },
    {
      "epoch": 27.444444444444443,
      "grad_norm": 4.1566901206970215,
      "learning_rate": 8.217142857142858e-06,
      "loss": 0.942,
      "step": 1125
    },
    {
      "epoch": 28.049382716049383,
      "grad_norm": 3.2101686000823975,
      "learning_rate": 8.145714285714287e-06,
      "loss": 0.9365,
      "step": 1150
    },
    {
      "epoch": 28.666666666666668,
      "grad_norm": 5.183631896972656,
      "learning_rate": 8.074285714285714e-06,
      "loss": 0.941,
      "step": 1175
    },
    {
      "epoch": 29.271604938271604,
      "grad_norm": 4.704529285430908,
      "learning_rate": 8.002857142857143e-06,
      "loss": 0.9374,
      "step": 1200
    },
    {
      "epoch": 29.88888888888889,
      "grad_norm": 4.460058689117432,
      "learning_rate": 7.931428571428572e-06,
      "loss": 0.9383,
      "step": 1225
    },
    {
      "epoch": 30.493827160493826,
      "grad_norm": 3.616530418395996,
      "learning_rate": 7.860000000000001e-06,
      "loss": 0.9321,
      "step": 1250
    },
    {
      "epoch": 31.098765432098766,
      "grad_norm": 3.92207932472229,
      "learning_rate": 7.788571428571428e-06,
      "loss": 0.9347,
      "step": 1275
    },
    {
      "epoch": 31.71604938271605,
      "grad_norm": 3.6962461471557617,
      "learning_rate": 7.717142857142857e-06,
      "loss": 0.9305,
      "step": 1300
    },
    {
      "epoch": 32.32098765432099,
      "grad_norm": 4.276056289672852,
      "learning_rate": 7.645714285714286e-06,
      "loss": 0.9336,
      "step": 1325
    },
    {
      "epoch": 32.93827160493827,
      "grad_norm": 5.176277160644531,
      "learning_rate": 7.574285714285715e-06,
      "loss": 0.9351,
      "step": 1350
    },
    {
      "epoch": 33.54320987654321,
      "grad_norm": 7.2538347244262695,
      "learning_rate": 7.502857142857144e-06,
      "loss": 0.9241,
      "step": 1375
    },
    {
      "epoch": 34.148148148148145,
      "grad_norm": 4.3576273918151855,
      "learning_rate": 7.431428571428572e-06,
      "loss": 0.9316,
      "step": 1400
    },
    {
      "epoch": 34.76543209876543,
      "grad_norm": 9.138855934143066,
      "learning_rate": 7.360000000000001e-06,
      "loss": 0.9277,
      "step": 1425
    },
    {
      "epoch": 35.370370370370374,
      "grad_norm": 4.475003719329834,
      "learning_rate": 7.28857142857143e-06,
      "loss": 0.9245,
      "step": 1450
    },
    {
      "epoch": 35.98765432098765,
      "grad_norm": 7.28753137588501,
      "learning_rate": 7.217142857142858e-06,
      "loss": 0.9266,
      "step": 1475
    },
    {
      "epoch": 36.592592592592595,
      "grad_norm": 5.1342949867248535,
      "learning_rate": 7.145714285714286e-06,
      "loss": 0.9297,
      "step": 1500
    },
    {
      "epoch": 37.19753086419753,
      "grad_norm": 2.7765142917633057,
      "learning_rate": 7.074285714285715e-06,
      "loss": 0.9253,
      "step": 1525
    },
    {
      "epoch": 37.81481481481482,
      "grad_norm": 3.8011326789855957,
      "learning_rate": 7.002857142857143e-06,
      "loss": 0.9203,
      "step": 1550
    },
    {
      "epoch": 38.41975308641975,
      "grad_norm": 7.432782173156738,
      "learning_rate": 6.931428571428572e-06,
      "loss": 0.9196,
      "step": 1575
    },
    {
      "epoch": 39.02469135802469,
      "grad_norm": 4.179474830627441,
      "learning_rate": 6.860000000000001e-06,
      "loss": 0.9188,
      "step": 1600
    },
    {
      "epoch": 39.641975308641975,
      "grad_norm": 8.513073921203613,
      "learning_rate": 6.7885714285714286e-06,
      "loss": 0.9268,
      "step": 1625
    },
    {
      "epoch": 40.24691358024691,
      "grad_norm": 3.699882984161377,
      "learning_rate": 6.7171428571428576e-06,
      "loss": 0.9216,
      "step": 1650
    },
    {
      "epoch": 40.864197530864196,
      "grad_norm": 3.949507713317871,
      "learning_rate": 6.645714285714287e-06,
      "loss": 0.9238,
      "step": 1675
    },
    {
      "epoch": 41.46913580246913,
      "grad_norm": 3.7951810359954834,
      "learning_rate": 6.574285714285716e-06,
      "loss": 0.9198,
      "step": 1700
    },
    {
      "epoch": 42.074074074074076,
      "grad_norm": 5.373620986938477,
      "learning_rate": 6.502857142857143e-06,
      "loss": 0.9135,
      "step": 1725
    },
    {
      "epoch": 42.69135802469136,
      "grad_norm": 6.875067234039307,
      "learning_rate": 6.431428571428572e-06,
      "loss": 0.918,
      "step": 1750
    },
    {
      "epoch": 43.2962962962963,
      "grad_norm": 7.167726039886475,
      "learning_rate": 6.360000000000001e-06,
      "loss": 0.9276,
      "step": 1775
    },
    {
      "epoch": 43.91358024691358,
      "grad_norm": 3.7067105770111084,
      "learning_rate": 6.288571428571429e-06,
      "loss": 0.9169,
      "step": 1800
    },
    {
      "epoch": 44.51851851851852,
      "grad_norm": 4.474793434143066,
      "learning_rate": 6.217142857142857e-06,
      "loss": 0.9191,
      "step": 1825
    },
    {
      "epoch": 45.123456790123456,
      "grad_norm": 5.386421203613281,
      "learning_rate": 6.145714285714286e-06,
      "loss": 0.9145,
      "step": 1850
    },
    {
      "epoch": 45.74074074074074,
      "grad_norm": 3.068861246109009,
      "learning_rate": 6.0742857142857145e-06,
      "loss": 0.9095,
      "step": 1875
    },
    {
      "epoch": 46.34567901234568,
      "grad_norm": 3.804973840713501,
      "learning_rate": 6.0028571428571435e-06,
      "loss": 0.912,
      "step": 1900
    },
    {
      "epoch": 46.96296296296296,
      "grad_norm": 2.9225473403930664,
      "learning_rate": 5.9314285714285725e-06,
      "loss": 0.9049,
      "step": 1925
    },
    {
      "epoch": 47.5679012345679,
      "grad_norm": 4.022708892822266,
      "learning_rate": 5.86e-06,
      "loss": 0.9049,
      "step": 1950
    },
    {
      "epoch": 48.17283950617284,
      "grad_norm": 3.421691417694092,
      "learning_rate": 5.788571428571429e-06,
      "loss": 0.9101,
      "step": 1975
    },
    {
      "epoch": 48.79012345679013,
      "grad_norm": 6.732350826263428,
      "learning_rate": 5.717142857142858e-06,
      "loss": 0.9105,
      "step": 2000
    },
    {
      "epoch": 48.79012345679013,
      "eval_loss": 0.8953001499176025,
      "eval_runtime": 2.1587,
      "eval_samples_per_second": 66.707,
      "eval_steps_per_second": 33.353,
      "step": 2000
    },
    {
      "epoch": 49.39506172839506,
      "grad_norm": 5.506401538848877,
      "learning_rate": 5.645714285714287e-06,
      "loss": 0.9036,
      "step": 2025
    },
    {
      "epoch": 50.0,
      "grad_norm": 9.19892406463623,
      "learning_rate": 5.574285714285714e-06,
      "loss": 0.9107,
      "step": 2050
    },
    {
      "epoch": 50.617283950617285,
      "grad_norm": 3.324119806289673,
      "learning_rate": 5.502857142857143e-06,
      "loss": 0.9118,
      "step": 2075
    },
    {
      "epoch": 51.22222222222222,
      "grad_norm": 5.142299652099609,
      "learning_rate": 5.431428571428572e-06,
      "loss": 0.9098,
      "step": 2100
    },
    {
      "epoch": 51.839506172839506,
      "grad_norm": 2.8806934356689453,
      "learning_rate": 5.36e-06,
      "loss": 0.9013,
      "step": 2125
    },
    {
      "epoch": 52.44444444444444,
      "grad_norm": 4.728231430053711,
      "learning_rate": 5.2885714285714285e-06,
      "loss": 0.9049,
      "step": 2150
    },
    {
      "epoch": 53.04938271604938,
      "grad_norm": 4.9596991539001465,
      "learning_rate": 5.2171428571428575e-06,
      "loss": 0.9128,
      "step": 2175
    },
    {
      "epoch": 53.666666666666664,
      "grad_norm": 3.160998821258545,
      "learning_rate": 5.145714285714286e-06,
      "loss": 0.9003,
      "step": 2200
    },
    {
      "epoch": 54.27160493827161,
      "grad_norm": 3.833195924758911,
      "learning_rate": 5.074285714285715e-06,
      "loss": 0.9088,
      "step": 2225
    },
    {
      "epoch": 54.888888888888886,
      "grad_norm": 5.242589950561523,
      "learning_rate": 5.002857142857144e-06,
      "loss": 0.9005,
      "step": 2250
    },
    {
      "epoch": 55.49382716049383,
      "grad_norm": 3.781388759613037,
      "learning_rate": 4.931428571428572e-06,
      "loss": 0.9028,
      "step": 2275
    },
    {
      "epoch": 56.098765432098766,
      "grad_norm": 6.0595574378967285,
      "learning_rate": 4.86e-06,
      "loss": 0.9124,
      "step": 2300
    },
    {
      "epoch": 56.71604938271605,
      "grad_norm": 2.7515597343444824,
      "learning_rate": 4.788571428571429e-06,
      "loss": 0.9025,
      "step": 2325
    },
    {
      "epoch": 57.32098765432099,
      "grad_norm": 6.520521640777588,
      "learning_rate": 4.717142857142857e-06,
      "loss": 0.9065,
      "step": 2350
    },
    {
      "epoch": 57.93827160493827,
      "grad_norm": 3.289445638656616,
      "learning_rate": 4.645714285714286e-06,
      "loss": 0.9004,
      "step": 2375
    },
    {
      "epoch": 58.54320987654321,
      "grad_norm": 3.6132805347442627,
      "learning_rate": 4.574285714285714e-06,
      "loss": 0.9021,
      "step": 2400
    },
    {
      "epoch": 59.148148148148145,
      "grad_norm": 5.021145343780518,
      "learning_rate": 4.5028571428571434e-06,
      "loss": 0.8957,
      "step": 2425
    },
    {
      "epoch": 59.76543209876543,
      "grad_norm": 5.366466522216797,
      "learning_rate": 4.431428571428572e-06,
      "loss": 0.8986,
      "step": 2450
    },
    {
      "epoch": 60.370370370370374,
      "grad_norm": 5.833218574523926,
      "learning_rate": 4.360000000000001e-06,
      "loss": 0.9045,
      "step": 2475
    },
    {
      "epoch": 60.98765432098765,
      "grad_norm": 5.301181793212891,
      "learning_rate": 4.288571428571429e-06,
      "loss": 0.8975,
      "step": 2500
    },
    {
      "epoch": 61.592592592592595,
      "grad_norm": 3.989539861679077,
      "learning_rate": 4.217142857142858e-06,
      "loss": 0.9021,
      "step": 2525
    },
    {
      "epoch": 62.19753086419753,
      "grad_norm": 13.111737251281738,
      "learning_rate": 4.145714285714286e-06,
      "loss": 0.9043,
      "step": 2550
    },
    {
      "epoch": 62.81481481481482,
      "grad_norm": 3.4066903591156006,
      "learning_rate": 4.074285714285714e-06,
      "loss": 0.8929,
      "step": 2575
    },
    {
      "epoch": 63.41975308641975,
      "grad_norm": 3.9170608520507812,
      "learning_rate": 4.002857142857143e-06,
      "loss": 0.8998,
      "step": 2600
    },
    {
      "epoch": 64.0246913580247,
      "grad_norm": 3.5934042930603027,
      "learning_rate": 3.931428571428571e-06,
      "loss": 0.898,
      "step": 2625
    },
    {
      "epoch": 64.64197530864197,
      "grad_norm": 3.3771822452545166,
      "learning_rate": 3.86e-06,
      "loss": 0.901,
      "step": 2650
    },
    {
      "epoch": 65.24691358024691,
      "grad_norm": 3.5741279125213623,
      "learning_rate": 3.7885714285714285e-06,
      "loss": 0.903,
      "step": 2675
    },
    {
      "epoch": 65.8641975308642,
      "grad_norm": 4.369333267211914,
      "learning_rate": 3.7171428571428575e-06,
      "loss": 0.8907,
      "step": 2700
    },
    {
      "epoch": 66.46913580246914,
      "grad_norm": 2.9996423721313477,
      "learning_rate": 3.6457142857142857e-06,
      "loss": 0.9008,
      "step": 2725
    },
    {
      "epoch": 67.07407407407408,
      "grad_norm": 5.098217487335205,
      "learning_rate": 3.5742857142857147e-06,
      "loss": 0.8979,
      "step": 2750
    },
    {
      "epoch": 67.69135802469135,
      "grad_norm": 3.8548665046691895,
      "learning_rate": 3.5028571428571433e-06,
      "loss": 0.8906,
      "step": 2775
    },
    {
      "epoch": 68.29629629629629,
      "grad_norm": 4.787322521209717,
      "learning_rate": 3.431428571428572e-06,
      "loss": 0.8949,
      "step": 2800
    },
    {
      "epoch": 68.91358024691358,
      "grad_norm": 2.8501498699188232,
      "learning_rate": 3.3600000000000004e-06,
      "loss": 0.8932,
      "step": 2825
    },
    {
      "epoch": 69.51851851851852,
      "grad_norm": 7.697382926940918,
      "learning_rate": 3.2885714285714286e-06,
      "loss": 0.8961,
      "step": 2850
    },
    {
      "epoch": 70.12345679012346,
      "grad_norm": 3.5617403984069824,
      "learning_rate": 3.2171428571428576e-06,
      "loss": 0.8975,
      "step": 2875
    },
    {
      "epoch": 70.74074074074075,
      "grad_norm": 4.286247253417969,
      "learning_rate": 3.1457142857142858e-06,
      "loss": 0.8988,
      "step": 2900
    },
    {
      "epoch": 71.34567901234568,
      "grad_norm": 3.0174379348754883,
      "learning_rate": 3.074285714285715e-06,
      "loss": 0.8986,
      "step": 2925
    },
    {
      "epoch": 71.96296296296296,
      "grad_norm": 5.708584308624268,
      "learning_rate": 3.002857142857143e-06,
      "loss": 0.8888,
      "step": 2950
    },
    {
      "epoch": 72.5679012345679,
      "grad_norm": 7.933815956115723,
      "learning_rate": 2.9314285714285716e-06,
      "loss": 0.9,
      "step": 2975
    },
    {
      "epoch": 73.17283950617283,
      "grad_norm": 3.4261972904205322,
      "learning_rate": 2.86e-06,
      "loss": 0.8951,
      "step": 3000
    },
    {
      "epoch": 73.17283950617283,
      "eval_loss": 0.8869494795799255,
      "eval_runtime": 2.1798,
      "eval_samples_per_second": 66.061,
      "eval_steps_per_second": 33.03,
      "step": 3000
    },
    {
      "epoch": 73.79012345679013,
      "grad_norm": 4.3120646476745605,
      "learning_rate": 2.7885714285714287e-06,
      "loss": 0.8897,
      "step": 3025
    },
    {
      "epoch": 74.39506172839506,
      "grad_norm": 3.6650469303131104,
      "learning_rate": 2.7171428571428577e-06,
      "loss": 0.8961,
      "step": 3050
    },
    {
      "epoch": 75.0,
      "grad_norm": 7.670346736907959,
      "learning_rate": 2.645714285714286e-06,
      "loss": 0.9003,
      "step": 3075
    },
    {
      "epoch": 75.61728395061728,
      "grad_norm": 3.292160987854004,
      "learning_rate": 2.574285714285715e-06,
      "loss": 0.8946,
      "step": 3100
    },
    {
      "epoch": 76.22222222222223,
      "grad_norm": 3.5280263423919678,
      "learning_rate": 2.502857142857143e-06,
      "loss": 0.8934,
      "step": 3125
    },
    {
      "epoch": 76.8395061728395,
      "grad_norm": 5.340327739715576,
      "learning_rate": 2.4314285714285717e-06,
      "loss": 0.8984,
      "step": 3150
    },
    {
      "epoch": 77.44444444444444,
      "grad_norm": 6.106954574584961,
      "learning_rate": 2.3600000000000003e-06,
      "loss": 0.8958,
      "step": 3175
    },
    {
      "epoch": 78.04938271604938,
      "grad_norm": 3.5689122676849365,
      "learning_rate": 2.288571428571429e-06,
      "loss": 0.8968,
      "step": 3200
    },
    {
      "epoch": 78.66666666666667,
      "grad_norm": 3.928802967071533,
      "learning_rate": 2.2171428571428575e-06,
      "loss": 0.8909,
      "step": 3225
    },
    {
      "epoch": 79.27160493827161,
      "grad_norm": 3.5558717250823975,
      "learning_rate": 2.145714285714286e-06,
      "loss": 0.8881,
      "step": 3250
    },
    {
      "epoch": 79.88888888888889,
      "grad_norm": 3.194141387939453,
      "learning_rate": 2.0742857142857146e-06,
      "loss": 0.8868,
      "step": 3275
    },
    {
      "epoch": 80.49382716049382,
      "grad_norm": 5.6881232261657715,
      "learning_rate": 2.0028571428571432e-06,
      "loss": 0.8973,
      "step": 3300
    },
    {
      "epoch": 81.09876543209876,
      "grad_norm": 3.105429172515869,
      "learning_rate": 1.9314285714285714e-06,
      "loss": 0.8935,
      "step": 3325
    },
    {
      "epoch": 81.71604938271605,
      "grad_norm": 3.2020113468170166,
      "learning_rate": 1.8600000000000002e-06,
      "loss": 0.89,
      "step": 3350
    },
    {
      "epoch": 82.32098765432099,
      "grad_norm": 3.5079753398895264,
      "learning_rate": 1.7885714285714288e-06,
      "loss": 0.8957,
      "step": 3375
    },
    {
      "epoch": 82.93827160493827,
      "grad_norm": 3.3880198001861572,
      "learning_rate": 1.7171428571428572e-06,
      "loss": 0.8914,
      "step": 3400
    },
    {
      "epoch": 83.54320987654322,
      "grad_norm": 6.072048664093018,
      "learning_rate": 1.6457142857142857e-06,
      "loss": 0.8904,
      "step": 3425
    },
    {
      "epoch": 84.14814814814815,
      "grad_norm": 2.919877529144287,
      "learning_rate": 1.5742857142857143e-06,
      "loss": 0.8842,
      "step": 3450
    },
    {
      "epoch": 84.76543209876543,
      "grad_norm": 3.742579936981201,
      "learning_rate": 1.502857142857143e-06,
      "loss": 0.8903,
      "step": 3475
    },
    {
      "epoch": 85.37037037037037,
      "grad_norm": 3.9216341972351074,
      "learning_rate": 1.4314285714285717e-06,
      "loss": 0.8962,
      "step": 3500
    },
    {
      "epoch": 85.98765432098766,
      "grad_norm": 3.594411849975586,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 0.894,
      "step": 3525
    },
    {
      "epoch": 86.5925925925926,
      "grad_norm": 3.7163913249969482,
      "learning_rate": 1.2885714285714287e-06,
      "loss": 0.8931,
      "step": 3550
    },
    {
      "epoch": 87.19753086419753,
      "grad_norm": 2.8378684520721436,
      "learning_rate": 1.2171428571428573e-06,
      "loss": 0.8855,
      "step": 3575
    },
    {
      "epoch": 87.81481481481481,
      "grad_norm": 3.5566790103912354,
      "learning_rate": 1.1457142857142859e-06,
      "loss": 0.8911,
      "step": 3600
    },
    {
      "epoch": 88.41975308641975,
      "grad_norm": 3.187382936477661,
      "learning_rate": 1.0742857142857145e-06,
      "loss": 0.8979,
      "step": 3625
    },
    {
      "epoch": 89.0246913580247,
      "grad_norm": 3.7930212020874023,
      "learning_rate": 1.0028571428571428e-06,
      "loss": 0.8824,
      "step": 3650
    },
    {
      "epoch": 89.64197530864197,
      "grad_norm": 3.2194180488586426,
      "learning_rate": 9.314285714285714e-07,
      "loss": 0.8915,
      "step": 3675
    },
    {
      "epoch": 90.24691358024691,
      "grad_norm": 3.050337076187134,
      "learning_rate": 8.6e-07,
      "loss": 0.8866,
      "step": 3700
    },
    {
      "epoch": 90.8641975308642,
      "grad_norm": 5.006812572479248,
      "learning_rate": 7.885714285714287e-07,
      "loss": 0.8877,
      "step": 3725
    },
    {
      "epoch": 91.46913580246914,
      "grad_norm": 3.206684112548828,
      "learning_rate": 7.171428571428572e-07,
      "loss": 0.8894,
      "step": 3750
    },
    {
      "epoch": 92.07407407407408,
      "grad_norm": 4.174693584442139,
      "learning_rate": 6.457142857142858e-07,
      "loss": 0.8906,
      "step": 3775
    },
    {
      "epoch": 92.69135802469135,
      "grad_norm": 5.580083847045898,
      "learning_rate": 5.742857142857143e-07,
      "loss": 0.8962,
      "step": 3800
    },
    {
      "epoch": 93.29629629629629,
      "grad_norm": 4.221833229064941,
      "learning_rate": 5.028571428571429e-07,
      "loss": 0.8886,
      "step": 3825
    },
    {
      "epoch": 93.91358024691358,
      "grad_norm": 3.687716484069824,
      "learning_rate": 4.3142857142857146e-07,
      "loss": 0.8911,
      "step": 3850
    },
    {
      "epoch": 94.51851851851852,
      "grad_norm": 4.194035530090332,
      "learning_rate": 3.6e-07,
      "loss": 0.889,
      "step": 3875
    },
    {
      "epoch": 95.12345679012346,
      "grad_norm": 4.321438312530518,
      "learning_rate": 2.885714285714286e-07,
      "loss": 0.8926,
      "step": 3900
    },
    {
      "epoch": 95.74074074074075,
      "grad_norm": 4.36216926574707,
      "learning_rate": 2.1714285714285715e-07,
      "loss": 0.8923,
      "step": 3925
    },
    {
      "epoch": 96.34567901234568,
      "grad_norm": 3.93856143951416,
      "learning_rate": 1.4571428571428574e-07,
      "loss": 0.8849,
      "step": 3950
    },
    {
      "epoch": 96.96296296296296,
      "grad_norm": 2.968627691268921,
      "learning_rate": 7.428571428571429e-08,
      "loss": 0.8904,
      "step": 3975
    },
    {
      "epoch": 97.5679012345679,
      "grad_norm": 16.590002059936523,
      "learning_rate": 2.8571428571428576e-09,
      "loss": 0.8853,
      "step": 4000
    },
    {
      "epoch": 97.5679012345679,
      "eval_loss": 0.8817942142486572,
      "eval_runtime": 2.1317,
      "eval_samples_per_second": 67.551,
      "eval_steps_per_second": 33.775,
      "step": 4000
    }
  ],
  "logging_steps": 25,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 98,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3285475532317440.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}