{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0170278637770898,
  "eval_steps": 50,
  "global_step": 1314,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 6e-06,
      "loss": 1.3528,
      "step": 1
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.2e-05,
      "loss": 1.3449,
      "step": 2
    },
    {
      "epoch": 0.0,
      "learning_rate": 1.8e-05,
      "loss": 1.2907,
      "step": 3
    },
    {
      "epoch": 0.0,
      "learning_rate": 2.4e-05,
      "loss": 1.3997,
      "step": 4
    },
    {
      "epoch": 0.0,
      "learning_rate": 3e-05,
      "loss": 1.3751,
      "step": 5
    },
    {
      "epoch": 0.0,
      "learning_rate": 3.6e-05,
      "loss": 1.3271,
      "step": 6
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.2e-05,
      "loss": 1.2757,
      "step": 7
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.8e-05,
      "loss": 1.2364,
      "step": 8
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.1987,
      "step": 9
    },
    {
      "epoch": 0.01,
      "learning_rate": 6e-05,
      "loss": 1.314,
      "step": 10
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999999443547221e-05,
      "loss": 1.1383,
      "step": 11
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999997774189092e-05,
      "loss": 1.1465,
      "step": 12
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999994991926231e-05,
      "loss": 1.1017,
      "step": 13
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.99999109675967e-05,
      "loss": 1.1974,
      "step": 14
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.9999860886908546e-05,
      "loss": 1.1773,
      "step": 15
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.9999799677216426e-05,
      "loss": 1.119,
      "step": 16
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999972733854306e-05,
      "loss": 1.1467,
      "step": 17
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999964387091525e-05,
      "loss": 1.0846,
      "step": 18
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.999954927436399e-05,
      "loss": 0.9089,
      "step": 19
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9999443548924355e-05,
      "loss": 1.0313,
      "step": 20
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999932669463558e-05,
      "loss": 1.053,
      "step": 21
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9999198711541e-05,
      "loss": 1.0601,
      "step": 22
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9999059599688106e-05,
      "loss": 1.1186,
      "step": 23
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9998909359128495e-05,
      "loss": 0.9551,
      "step": 24
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.99987479899179e-05,
      "loss": 1.026,
      "step": 25
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999857549211619e-05,
      "loss": 0.956,
      "step": 26
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999839186578736e-05,
      "loss": 0.9429,
      "step": 27
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.9998197110999523e-05,
      "loss": 1.1377,
      "step": 28
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999799122782492e-05,
      "loss": 1.0053,
      "step": 29
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999777421633994e-05,
      "loss": 1.053,
      "step": 30
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999754607662509e-05,
      "loss": 0.9801,
      "step": 31
    },
    {
      "epoch": 0.02,
      "learning_rate": 5.999730680876498e-05,
      "loss": 1.0854,
      "step": 32
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.99970564128484e-05,
      "loss": 1.0073,
      "step": 33
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999679488896822e-05,
      "loss": 1.0055,
      "step": 34
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999652223722146e-05,
      "loss": 1.077,
      "step": 35
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999623845770926e-05,
      "loss": 1.0049,
      "step": 36
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9995943550536915e-05,
      "loss": 1.037,
      "step": 37
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9995637515813805e-05,
      "loss": 1.0184,
      "step": 38
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9995320353653467e-05,
      "loss": 1.0514,
      "step": 39
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9994992064173556e-05,
      "loss": 0.9558,
      "step": 40
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999465264749586e-05,
      "loss": 1.0158,
      "step": 41
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999430210374629e-05,
      "loss": 1.0178,
      "step": 42
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999394043305488e-05,
      "loss": 0.9685,
      "step": 43
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.9993567635555814e-05,
      "loss": 0.9661,
      "step": 44
    },
    {
      "epoch": 0.03,
      "learning_rate": 5.999318371138738e-05,
      "loss": 1.0643,
      "step": 45
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.9992788660691994e-05,
      "loss": 0.9666,
      "step": 46
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999238248361622e-05,
      "loss": 0.9656,
      "step": 47
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999196518031074e-05,
      "loss": 0.9473,
      "step": 48
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999153675093034e-05,
      "loss": 1.0628,
      "step": 49
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999109719563396e-05,
      "loss": 1.0203,
      "step": 50
    },
    {
      "epoch": 0.04,
      "eval_loss": 1.0092148780822754,
      "eval_runtime": 14.3039,
      "eval_samples_per_second": 5.733,
      "eval_steps_per_second": 5.733,
      "step": 50
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999064651458468e-05,
      "loss": 0.9855,
      "step": 51
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.999018470794967e-05,
      "loss": 1.0158,
      "step": 52
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.9989711775900255e-05,
      "loss": 1.1334,
      "step": 53
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.998922771861187e-05,
      "loss": 0.9961,
      "step": 54
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.998873253626409e-05,
      "loss": 0.9928,
      "step": 55
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.998822622904061e-05,
      "loss": 1.0314,
      "step": 56
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.998770879712925e-05,
      "loss": 0.9761,
      "step": 57
    },
    {
      "epoch": 0.04,
      "learning_rate": 5.998718024072198e-05,
      "loss": 1.0083,
      "step": 58
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9986640560014846e-05,
      "loss": 0.952,
      "step": 59
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9986089755208086e-05,
      "loss": 0.9763,
      "step": 60
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998552782650601e-05,
      "loss": 1.0366,
      "step": 61
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9984954774117075e-05,
      "loss": 1.0147,
      "step": 62
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998437059825389e-05,
      "loss": 1.0294,
      "step": 63
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998377529913313e-05,
      "loss": 1.0446,
      "step": 64
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998316887697566e-05,
      "loss": 0.9677,
      "step": 65
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9982551332006425e-05,
      "loss": 1.1324,
      "step": 66
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998192266445453e-05,
      "loss": 1.0193,
      "step": 67
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998128287455318e-05,
      "loss": 0.9358,
      "step": 68
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.998063196253973e-05,
      "loss": 0.899,
      "step": 69
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.997996992865563e-05,
      "loss": 0.924,
      "step": 70
    },
    {
      "epoch": 0.05,
      "learning_rate": 5.9979296773146486e-05,
      "loss": 0.959,
      "step": 71
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997861249626202e-05,
      "loss": 0.9175,
      "step": 72
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997791709825606e-05,
      "loss": 0.9295,
      "step": 73
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.9977210579386595e-05,
      "loss": 0.9717,
      "step": 74
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997649293991571e-05,
      "loss": 0.9112,
      "step": 75
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.9975764180109634e-05,
      "loss": 0.9751,
      "step": 76
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997502430023871e-05,
      "loss": 1.0222,
      "step": 77
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997427330057741e-05,
      "loss": 0.9514,
      "step": 78
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997351118140434e-05,
      "loss": 0.9049,
      "step": 79
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.9972737943002204e-05,
      "loss": 1.0462,
      "step": 80
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997195358565787e-05,
      "loss": 1.0072,
      "step": 81
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.99711581096623e-05,
      "loss": 0.8974,
      "step": 82
    },
    {
      "epoch": 0.06,
      "learning_rate": 5.997035151531057e-05,
      "loss": 0.9284,
      "step": 83
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996953380290194e-05,
      "loss": 1.0063,
      "step": 84
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.9968704972739736e-05,
      "loss": 0.9174,
      "step": 85
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.9967865025131417e-05,
      "loss": 0.9491,
      "step": 86
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.99670139603886e-05,
      "loss": 0.9228,
      "step": 87
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996615177882699e-05,
      "loss": 0.9828,
      "step": 88
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.9965278480766434e-05,
      "loss": 0.9737,
      "step": 89
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996439406653088e-05,
      "loss": 0.9446,
      "step": 90
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996349853644845e-05,
      "loss": 0.8599,
      "step": 91
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996259189085134e-05,
      "loss": 0.92,
      "step": 92
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996167413007588e-05,
      "loss": 0.9635,
      "step": 93
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.996074525446254e-05,
      "loss": 0.9384,
      "step": 94
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.99598052643559e-05,
      "loss": 0.9687,
      "step": 95
    },
    {
      "epoch": 0.07,
      "learning_rate": 5.995885416010467e-05,
      "loss": 0.9615,
      "step": 96
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.995789194206168e-05,
      "loss": 0.9118,
      "step": 97
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.995691861058389e-05,
      "loss": 0.9355,
      "step": 98
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.995593416603235e-05,
      "loss": 0.9507,
      "step": 99
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.995493860877228e-05,
      "loss": 0.9366,
      "step": 100
    },
    {
      "epoch": 0.08,
      "eval_loss": 0.9740197658538818,
      "eval_runtime": 14.3321,
      "eval_samples_per_second": 5.721,
      "eval_steps_per_second": 5.721,
      "step": 100
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9953931939172995e-05,
      "loss": 1.0358,
      "step": 101
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9952914157607934e-05,
      "loss": 0.9567,
      "step": 102
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.995188526445466e-05,
      "loss": 0.9613,
      "step": 103
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9950845260094875e-05,
      "loss": 0.9635,
      "step": 104
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.994979414491438e-05,
      "loss": 0.9957,
      "step": 105
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9948731919303095e-05,
      "loss": 0.9309,
      "step": 106
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9947658583655087e-05,
      "loss": 0.9494,
      "step": 107
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.994657413836852e-05,
      "loss": 0.9189,
      "step": 108
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.9945478583845686e-05,
      "loss": 0.9197,
      "step": 109
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.994437192049303e-05,
      "loss": 0.9303,
      "step": 110
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.994325414872104e-05,
      "loss": 1.039,
      "step": 111
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.994212526894441e-05,
      "loss": 0.9252,
      "step": 112
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.9940985281581914e-05,
      "loss": 0.9062,
      "step": 113
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993983418705644e-05,
      "loss": 0.9566,
      "step": 114
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993867198579503e-05,
      "loss": 0.9317,
      "step": 115
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.99374986782288e-05,
      "loss": 0.9046,
      "step": 116
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.9936314264793025e-05,
      "loss": 0.9501,
      "step": 117
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993511874592708e-05,
      "loss": 0.9414,
      "step": 118
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993391212207446e-05,
      "loss": 0.9857,
      "step": 119
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993269439368279e-05,
      "loss": 0.907,
      "step": 120
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.9931465561203805e-05,
      "loss": 0.9606,
      "step": 121
    },
    {
      "epoch": 0.09,
      "learning_rate": 5.993022562509337e-05,
      "loss": 0.8788,
      "step": 122
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9928974585811446e-05,
      "loss": 0.9131,
      "step": 123
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9927712443822156e-05,
      "loss": 1.1033,
      "step": 124
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9926439199593695e-05,
      "loss": 0.9284,
      "step": 125
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.992515485359841e-05,
      "loss": 0.9336,
      "step": 126
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.992385940631273e-05,
      "loss": 0.9167,
      "step": 127
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9922552858217255e-05,
      "loss": 0.9539,
      "step": 128
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.992123520979665e-05,
      "loss": 0.9554,
      "step": 129
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.991990646153973e-05,
      "loss": 0.9995,
      "step": 130
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.991856661393942e-05,
      "loss": 0.9189,
      "step": 131
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9917215667492765e-05,
      "loss": 1.0112,
      "step": 132
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.9915853622700904e-05,
      "loss": 0.9819,
      "step": 133
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.991448048006914e-05,
      "loss": 0.9668,
      "step": 134
    },
    {
      "epoch": 0.1,
      "learning_rate": 5.991309624010684e-05,
      "loss": 0.9559,
      "step": 135
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9911700903327534e-05,
      "loss": 0.8581,
      "step": 136
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.991029447024884e-05,
      "loss": 1.008,
      "step": 137
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.99088769413925e-05,
      "loss": 0.9794,
      "step": 138
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9907448317284366e-05,
      "loss": 0.9236,
      "step": 139
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9906008598454426e-05,
      "loss": 0.9119,
      "step": 140
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9904557785436764e-05,
      "loss": 0.9184,
      "step": 141
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.990309587876958e-05,
      "loss": 0.9256,
      "step": 142
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9901622878995217e-05,
      "loss": 0.9921,
      "step": 143
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.990013878666008e-05,
      "loss": 0.9549,
      "step": 144
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.989864360231474e-05,
      "loss": 0.9589,
      "step": 145
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.989713732651386e-05,
      "loss": 0.9441,
      "step": 146
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9895619959816226e-05,
      "loss": 0.9112,
      "step": 147
    },
    {
      "epoch": 0.11,
      "learning_rate": 5.9894091502784726e-05,
      "loss": 0.9471,
      "step": 148
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.989255195598636e-05,
      "loss": 0.8758,
      "step": 149
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.989100131999227e-05,
      "loss": 0.9341,
      "step": 150
    },
    {
      "epoch": 0.12,
      "eval_loss": 0.9579644799232483,
      "eval_runtime": 14.3455,
      "eval_samples_per_second": 5.716,
      "eval_steps_per_second": 5.716,
      "step": 150
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9889439595377686e-05,
      "loss": 1.0078,
      "step": 151
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.988786678272196e-05,
      "loss": 0.9289,
      "step": 152
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9886282882608555e-05,
      "loss": 0.9127,
      "step": 153
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9884687895625036e-05,
      "loss": 0.9824,
      "step": 154
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.988308182236312e-05,
      "loss": 0.9168,
      "step": 155
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.988146466341859e-05,
      "loss": 0.915,
      "step": 156
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9879836419391356e-05,
      "loss": 0.8693,
      "step": 157
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.987819709088547e-05,
      "loss": 1.0086,
      "step": 158
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9876546678509035e-05,
      "loss": 0.8625,
      "step": 159
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9874885182874336e-05,
      "loss": 0.9213,
      "step": 160
    },
    {
      "epoch": 0.12,
      "learning_rate": 5.9873212604597726e-05,
      "loss": 0.8849,
      "step": 161
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.9871528944299666e-05,
      "loss": 0.8412,
      "step": 162
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.986983420260475e-05,
      "loss": 0.9405,
      "step": 163
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.986812838014168e-05,
      "loss": 0.9492,
      "step": 164
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.9866411477543254e-05,
      "loss": 0.9946,
      "step": 165
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.986468349544639e-05,
      "loss": 0.8268,
      "step": 166
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.986294443449212e-05,
      "loss": 0.874,
      "step": 167
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.986119429532557e-05,
      "loss": 0.8546,
      "step": 168
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.985943307859599e-05,
      "loss": 0.8573,
      "step": 169
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.9857660784956754e-05,
      "loss": 0.9122,
      "step": 170
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.985587741506531e-05,
      "loss": 0.9282,
      "step": 171
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.985408296958323e-05,
      "loss": 0.8424,
      "step": 172
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.98522774491762e-05,
      "loss": 0.8827,
      "step": 173
    },
    {
      "epoch": 0.13,
      "learning_rate": 5.985046085451401e-05,
      "loss": 0.886,
      "step": 174
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.984863318627057e-05,
      "loss": 0.8363,
      "step": 175
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.984679444512388e-05,
      "loss": 0.9607,
      "step": 176
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.984494463175605e-05,
      "loss": 0.97,
      "step": 177
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.984308374685331e-05,
      "loss": 0.8727,
      "step": 178
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.984121179110598e-05,
      "loss": 0.9653,
      "step": 179
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.983932876520851e-05,
      "loss": 0.9436,
      "step": 180
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.9837434669859435e-05,
      "loss": 0.9764,
      "step": 181
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.983552950576141e-05,
      "loss": 0.867,
      "step": 182
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.983361327362118e-05,
      "loss": 0.8783,
      "step": 183
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.983168597414962e-05,
      "loss": 0.9174,
      "step": 184
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.9829747608061686e-05,
      "loss": 0.9021,
      "step": 185
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.9827798176076464e-05,
      "loss": 0.9501,
      "step": 186
    },
    {
      "epoch": 0.14,
      "learning_rate": 5.9825837678917114e-05,
      "loss": 0.9088,
      "step": 187
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.982386611731094e-05,
      "loss": 0.9459,
      "step": 188
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.9821883491989313e-05,
      "loss": 0.9144,
      "step": 189
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.981988980368773e-05,
      "loss": 0.8691,
      "step": 190
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.981788505314579e-05,
      "loss": 0.8543,
      "step": 191
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.981586924110719e-05,
      "loss": 0.966,
      "step": 192
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.981384236831973e-05,
      "loss": 0.9013,
      "step": 193
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.981180443553531e-05,
      "loss": 0.9596,
      "step": 194
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.980975544350995e-05,
      "loss": 0.9167,
      "step": 195
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.9807695393003765e-05,
      "loss": 0.9444,
      "step": 196
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.9805624284780955e-05,
      "loss": 0.9015,
      "step": 197
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.980354211960985e-05,
      "loss": 0.8981,
      "step": 198
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.980144889826285e-05,
      "loss": 0.9672,
      "step": 199
    },
    {
      "epoch": 0.15,
      "learning_rate": 5.979934462151649e-05,
      "loss": 0.9574,
      "step": 200
    },
    {
      "epoch": 0.15,
      "eval_loss": 0.9466971755027771,
      "eval_runtime": 14.339,
      "eval_samples_per_second": 5.719,
      "eval_steps_per_second": 5.719,
      "step": 200
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.979722929015139e-05,
      "loss": 1.0925,
      "step": 201
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.9795102904952266e-05,
      "loss": 0.8727,
      "step": 202
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.9792965466707936e-05,
      "loss": 0.9032,
      "step": 203
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.9790816976211334e-05,
      "loss": 0.9172,
      "step": 204
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.978865743425947e-05,
      "loss": 0.9406,
      "step": 205
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.978648684165347e-05,
      "loss": 0.8997,
      "step": 206
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.978430519919856e-05,
      "loss": 0.881,
      "step": 207
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.978211250770406e-05,
      "loss": 0.9005,
      "step": 208
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.9779908767983376e-05,
      "loss": 0.9645,
      "step": 209
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.977769398085405e-05,
      "loss": 0.9006,
      "step": 210
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.977546814713768e-05,
      "loss": 0.9797,
      "step": 211
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.977323126765999e-05,
      "loss": 0.9193,
      "step": 212
    },
    {
      "epoch": 0.16,
      "learning_rate": 5.977098334325078e-05,
      "loss": 0.9866,
      "step": 213
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.976872437474397e-05,
      "loss": 1.107,
      "step": 214
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9766454362977564e-05,
      "loss": 0.9714,
      "step": 215
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9764173308793666e-05,
      "loss": 0.9226,
      "step": 216
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9761881213038465e-05,
      "loss": 1.001,
      "step": 217
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.975957807656228e-05,
      "loss": 0.9818,
      "step": 218
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.975726390021947e-05,
      "loss": 0.8939,
      "step": 219
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.975493868486854e-05,
      "loss": 0.8813,
      "step": 220
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.975260243137208e-05,
      "loss": 0.9387,
      "step": 221
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9750255140596756e-05,
      "loss": 0.8727,
      "step": 222
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.9747896813413335e-05,
      "loss": 0.8764,
      "step": 223
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.974552745069669e-05,
      "loss": 0.8334,
      "step": 224
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.974314705332577e-05,
      "loss": 0.964,
      "step": 225
    },
    {
      "epoch": 0.17,
      "learning_rate": 5.974075562218364e-05,
      "loss": 0.8916,
      "step": 226
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.973835315815744e-05,
      "loss": 0.9837,
      "step": 227
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9735939662138406e-05,
      "loss": 0.9812,
      "step": 228
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9733515135021864e-05,
      "loss": 0.908,
      "step": 229
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9731079577707245e-05,
      "loss": 0.8595,
      "step": 230
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9728632991098076e-05,
      "loss": 0.9381,
      "step": 231
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9726175376101943e-05,
      "loss": 0.9119,
      "step": 232
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.972370673363056e-05,
      "loss": 0.8801,
      "step": 233
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.972122706459969e-05,
      "loss": 0.8782,
      "step": 234
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.971873636992925e-05,
      "loss": 0.9719,
      "step": 235
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.971623465054317e-05,
      "loss": 0.9726,
      "step": 236
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.971372190736955e-05,
      "loss": 0.8699,
      "step": 237
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.9711198141340505e-05,
      "loss": 0.9727,
      "step": 238
    },
    {
      "epoch": 0.18,
      "learning_rate": 5.970866335339228e-05,
      "loss": 0.9451,
      "step": 239
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.970611754446522e-05,
      "loss": 0.9522,
      "step": 240
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.970356071550371e-05,
      "loss": 0.9961,
      "step": 241
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.970099286745628e-05,
      "loss": 0.8883,
      "step": 242
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.969841400127551e-05,
      "loss": 0.9045,
      "step": 243
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.969582411791807e-05,
      "loss": 0.9338,
      "step": 244
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.9693223218344734e-05,
      "loss": 0.9816,
      "step": 245
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.9690611303520356e-05,
      "loss": 0.9122,
      "step": 246
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.9687988374413874e-05,
      "loss": 0.8637,
      "step": 247
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.968535443199831e-05,
      "loss": 0.9587,
      "step": 248
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.9682709477250775e-05,
      "loss": 0.9989,
      "step": 249
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.968005351115245e-05,
      "loss": 0.9073,
      "step": 250
    },
    {
      "epoch": 0.19,
      "eval_loss": 0.9367482662200928,
      "eval_runtime": 14.3489,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 250
    },
    {
      "epoch": 0.19,
      "learning_rate": 5.967738653468864e-05,
      "loss": 0.9046,
      "step": 251
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.967470854884869e-05,
      "loss": 0.9685,
      "step": 252
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.967201955462606e-05,
      "loss": 0.9696,
      "step": 253
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.966931955301827e-05,
      "loss": 0.9046,
      "step": 254
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.9666608545026946e-05,
      "loss": 0.9596,
      "step": 255
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.9663886531657785e-05,
      "loss": 0.9658,
      "step": 256
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.9661153513920566e-05,
      "loss": 0.8072,
      "step": 257
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.965840949282915e-05,
      "loss": 0.9069,
      "step": 258
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.965565446940149e-05,
      "loss": 0.8832,
      "step": 259
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.96528884446596e-05,
      "loss": 0.9458,
      "step": 260
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.9650111419629606e-05,
      "loss": 0.956,
      "step": 261
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.9647323395341675e-05,
      "loss": 0.8134,
      "step": 262
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.96445243728301e-05,
      "loss": 0.9372,
      "step": 263
    },
    {
      "epoch": 0.2,
      "learning_rate": 5.964171435313321e-05,
      "loss": 1.0882,
      "step": 264
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.963889333729345e-05,
      "loss": 0.9947,
      "step": 265
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.963606132635731e-05,
      "loss": 0.9149,
      "step": 266
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.96332183213754e-05,
      "loss": 0.9228,
      "step": 267
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.963036432340237e-05,
      "loss": 0.9393,
      "step": 268
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.9627499333496965e-05,
      "loss": 0.8971,
      "step": 269
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.962462335272201e-05,
      "loss": 0.8505,
      "step": 270
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.96217363821444e-05,
      "loss": 0.9163,
      "step": 271
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.961883842283511e-05,
      "loss": 0.8878,
      "step": 272
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.961592947586919e-05,
      "loss": 0.9367,
      "step": 273
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.9613009542325765e-05,
      "loss": 0.9018,
      "step": 274
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.9610078623288056e-05,
      "loss": 0.9076,
      "step": 275
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.9607136719843326e-05,
      "loss": 0.9455,
      "step": 276
    },
    {
      "epoch": 0.21,
      "learning_rate": 5.9604183833082926e-05,
      "loss": 0.859,
      "step": 277
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.96012199641023e-05,
      "loss": 0.9633,
      "step": 278
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.959824511400093e-05,
      "loss": 0.8642,
      "step": 279
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.9595259283882404e-05,
      "loss": 0.9142,
      "step": 280
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.959226247485438e-05,
      "loss": 0.8873,
      "step": 281
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.9589254688028556e-05,
      "loss": 0.9313,
      "step": 282
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.958623592452074e-05,
      "loss": 0.8899,
      "step": 283
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.95832061854508e-05,
      "loss": 0.9243,
      "step": 284
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.9580165471942676e-05,
      "loss": 0.9604,
      "step": 285
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.9577113785124364e-05,
      "loss": 0.9449,
      "step": 286
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.957405112612795e-05,
      "loss": 0.8803,
      "step": 287
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.957097749608959e-05,
      "loss": 0.9243,
      "step": 288
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.95678928961495e-05,
      "loss": 0.8947,
      "step": 289
    },
    {
      "epoch": 0.22,
      "learning_rate": 5.9564797327451975e-05,
      "loss": 0.8416,
      "step": 290
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.9561690791145356e-05,
      "loss": 0.8503,
      "step": 291
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.955857328838209e-05,
      "loss": 0.9263,
      "step": 292
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.955544482031866e-05,
      "loss": 0.9338,
      "step": 293
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.955230538811564e-05,
      "loss": 0.8688,
      "step": 294
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.954915499293765e-05,
      "loss": 0.8991,
      "step": 295
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.954599363595339e-05,
      "loss": 0.9422,
      "step": 296
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.954282131833562e-05,
      "loss": 0.9208,
      "step": 297
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.953963804126119e-05,
      "loss": 0.8805,
      "step": 298
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.953644380591097e-05,
      "loss": 0.8969,
      "step": 299
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.953323861346993e-05,
      "loss": 0.9326,
      "step": 300
    },
    {
      "epoch": 0.23,
      "eval_loss": 0.9325690865516663,
      "eval_runtime": 14.3495,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 300
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.9530022465127104e-05,
      "loss": 0.9887,
      "step": 301
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.952679536207558e-05,
      "loss": 0.9263,
      "step": 302
    },
    {
      "epoch": 0.23,
      "learning_rate": 5.9523557305512495e-05,
      "loss": 0.9236,
      "step": 303
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.952030829663907e-05,
      "loss": 0.8056,
      "step": 304
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.951704833666061e-05,
      "loss": 0.9275,
      "step": 305
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.951377742678644e-05,
      "loss": 0.8818,
      "step": 306
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.951049556822996e-05,
      "loss": 0.9973,
      "step": 307
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.950720276220863e-05,
      "loss": 0.9542,
      "step": 308
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.9503899009944006e-05,
      "loss": 0.9337,
      "step": 309
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.950058431266165e-05,
      "loss": 0.9551,
      "step": 310
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.949725867159121e-05,
      "loss": 0.8586,
      "step": 311
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.949392208796642e-05,
      "loss": 0.8877,
      "step": 312
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.9490574563025014e-05,
      "loss": 0.8719,
      "step": 313
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.9487216098008846e-05,
      "loss": 0.9017,
      "step": 314
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.948384669416379e-05,
      "loss": 0.9108,
      "step": 315
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.948046635273978e-05,
      "loss": 0.8661,
      "step": 316
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.947707507499083e-05,
      "loss": 0.9431,
      "step": 317
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.947367286217499e-05,
      "loss": 0.8706,
      "step": 318
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.947025971555438e-05,
      "loss": 0.9148,
      "step": 319
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.946683563639516e-05,
      "loss": 0.9137,
      "step": 320
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.9463400625967564e-05,
      "loss": 0.9359,
      "step": 321
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.945995468554587e-05,
      "loss": 1.0004,
      "step": 322
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.945649781640841e-05,
      "loss": 0.915,
      "step": 323
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.945303001983758e-05,
      "loss": 0.841,
      "step": 324
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.9449551297119825e-05,
      "loss": 0.9262,
      "step": 325
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.944606164954563e-05,
      "loss": 0.8751,
      "step": 326
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.9442561078409554e-05,
      "loss": 0.9131,
      "step": 327
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.9439049585010195e-05,
      "loss": 0.9083,
      "step": 328
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.94355271706502e-05,
      "loss": 0.9454,
      "step": 329
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.94319938366363e-05,
      "loss": 0.965,
      "step": 330
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9428449584279216e-05,
      "loss": 0.9193,
      "step": 331
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.942489441489377e-05,
      "loss": 0.8919,
      "step": 332
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9421328329798834e-05,
      "loss": 0.9617,
      "step": 333
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.941775133031729e-05,
      "loss": 0.9865,
      "step": 334
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9414163417776094e-05,
      "loss": 0.8605,
      "step": 335
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9410564593506254e-05,
      "loss": 0.8571,
      "step": 336
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.940695485884282e-05,
      "loss": 0.9212,
      "step": 337
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9403334215124895e-05,
      "loss": 0.9161,
      "step": 338
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9399702663695626e-05,
      "loss": 0.8645,
      "step": 339
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9396060205902186e-05,
      "loss": 0.8923,
      "step": 340
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.939240684309583e-05,
      "loss": 0.8962,
      "step": 341
    },
    {
      "epoch": 0.26,
      "learning_rate": 5.9388742576631825e-05,
      "loss": 0.8472,
      "step": 342
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.938506740786952e-05,
      "loss": 0.8725,
      "step": 343
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.938138133817226e-05,
      "loss": 0.8891,
      "step": 344
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.937768436890749e-05,
      "loss": 0.9247,
      "step": 345
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.937397650144665e-05,
      "loss": 0.8729,
      "step": 346
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.937025773716525e-05,
      "loss": 0.9109,
      "step": 347
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.936652807744283e-05,
      "loss": 0.999,
      "step": 348
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.936278752366297e-05,
      "loss": 0.8707,
      "step": 349
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.935903607721332e-05,
      "loss": 0.823,
      "step": 350
    },
    {
      "epoch": 0.27,
      "eval_loss": 0.9278062582015991,
      "eval_runtime": 14.3458,
      "eval_samples_per_second": 5.716,
      "eval_steps_per_second": 5.716,
      "step": 350
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.9355273739485516e-05,
      "loss": 0.8985,
      "step": 351
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.935150051187531e-05,
      "loss": 1.0011,
      "step": 352
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.9347716395782404e-05,
      "loss": 0.9014,
      "step": 353
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.934392139261061e-05,
      "loss": 0.874,
      "step": 354
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.9340115503767755e-05,
      "loss": 0.9043,
      "step": 355
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.933629873066571e-05,
      "loss": 0.9621,
      "step": 356
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.933247107472036e-05,
      "loss": 0.8471,
      "step": 357
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.932863253735165e-05,
      "loss": 0.9379,
      "step": 358
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.9324783119983564e-05,
      "loss": 0.9738,
      "step": 359
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.932092282404411e-05,
      "loss": 0.8806,
      "step": 360
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.931705165096534e-05,
      "loss": 0.9184,
      "step": 361
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.931316960218334e-05,
      "loss": 0.9544,
      "step": 362
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.930927667913821e-05,
      "loss": 0.941,
      "step": 363
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.930537288327412e-05,
      "loss": 0.8859,
      "step": 364
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.930145821603925e-05,
      "loss": 0.9242,
      "step": 365
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.929753267888582e-05,
      "loss": 0.8827,
      "step": 366
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.9293596273270074e-05,
      "loss": 1.0236,
      "step": 367
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.92896490006523e-05,
      "loss": 0.8813,
      "step": 368
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.9285690862496814e-05,
      "loss": 0.9873,
      "step": 369
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.928172186027195e-05,
      "loss": 0.9933,
      "step": 370
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.92777419954501e-05,
      "loss": 0.909,
      "step": 371
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.927375126950765e-05,
      "loss": 0.909,
      "step": 372
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.926974968392505e-05,
      "loss": 0.9498,
      "step": 373
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.926573724018676e-05,
      "loss": 0.9165,
      "step": 374
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.926171393978126e-05,
      "loss": 0.8861,
      "step": 375
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.9257679784201076e-05,
      "loss": 0.9242,
      "step": 376
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.9253634774942736e-05,
      "loss": 0.9005,
      "step": 377
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.9249578913506835e-05,
      "loss": 0.848,
      "step": 378
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.924551220139796e-05,
      "loss": 0.9174,
      "step": 379
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.9241434640124745e-05,
      "loss": 0.9594,
      "step": 380
    },
    {
      "epoch": 0.29,
      "learning_rate": 5.92373462311998e-05,
      "loss": 0.8323,
      "step": 381
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.9233246976139843e-05,
      "loss": 0.9557,
      "step": 382
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.9229136876465537e-05,
      "loss": 0.8413,
      "step": 383
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.922501593370161e-05,
      "loss": 0.9098,
      "step": 384
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.92208841493768e-05,
      "loss": 0.9021,
      "step": 385
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.921674152502387e-05,
      "loss": 0.8922,
      "step": 386
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.921258806217961e-05,
      "loss": 0.991,
      "step": 387
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.92084237623848e-05,
      "loss": 0.9665,
      "step": 388
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.92042486271843e-05,
      "loss": 0.9502,
      "step": 389
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.920006265812693e-05,
      "loss": 0.942,
      "step": 390
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.919586585676556e-05,
      "loss": 0.9667,
      "step": 391
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.919165822465706e-05,
      "loss": 0.8824,
      "step": 392
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.9187439763362343e-05,
      "loss": 0.9201,
      "step": 393
    },
    {
      "epoch": 0.3,
      "learning_rate": 5.918321047444632e-05,
      "loss": 1.009,
      "step": 394
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.917897035947793e-05,
      "loss": 0.8835,
      "step": 395
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.9174719420030106e-05,
      "loss": 0.8517,
      "step": 396
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.917045765767983e-05,
      "loss": 0.9925,
      "step": 397
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.9166185074008076e-05,
      "loss": 0.9388,
      "step": 398
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.9161901670599836e-05,
      "loss": 0.8664,
      "step": 399
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.915760744904412e-05,
      "loss": 0.905,
      "step": 400
    },
    {
      "epoch": 0.31,
      "eval_loss": 0.9229549169540405,
      "eval_runtime": 14.344,
      "eval_samples_per_second": 5.717,
      "eval_steps_per_second": 5.717,
      "step": 400
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.915330241093394e-05,
      "loss": 0.9731,
      "step": 401
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.914898655786635e-05,
      "loss": 0.8997,
      "step": 402
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.914465989144238e-05,
      "loss": 1.0159,
      "step": 403
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.9140322413267084e-05,
      "loss": 0.8836,
      "step": 404
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.913597412494954e-05,
      "loss": 0.9752,
      "step": 405
    },
    {
      "epoch": 0.31,
      "learning_rate": 5.913161502810282e-05,
      "loss": 0.899,
      "step": 406
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.912724512434402e-05,
      "loss": 0.9651,
      "step": 407
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.912286441529422e-05,
      "loss": 0.8707,
      "step": 408
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.911847290257854e-05,
      "loss": 0.8244,
      "step": 409
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.9114070587826095e-05,
      "loss": 0.9235,
      "step": 410
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.9109657472669995e-05,
      "loss": 0.8612,
      "step": 411
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.910523355874737e-05,
      "loss": 0.8909,
      "step": 412
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.910079884769935e-05,
      "loss": 0.9639,
      "step": 413
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.9096353341171085e-05,
      "loss": 0.9975,
      "step": 414
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.90918970408117e-05,
      "loss": 0.8918,
      "step": 415
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.9087429948274356e-05,
      "loss": 0.9594,
      "step": 416
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.90829520652162e-05,
      "loss": 0.868,
      "step": 417
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.907846339329838e-05,
      "loss": 0.9264,
      "step": 418
    },
    {
      "epoch": 0.32,
      "learning_rate": 5.907396393418607e-05,
      "loss": 0.9042,
      "step": 419
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.90694536895484e-05,
      "loss": 0.9016,
      "step": 420
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.9064932661058554e-05,
      "loss": 0.9021,
      "step": 421
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.906040085039368e-05,
      "loss": 0.9378,
      "step": 422
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.905585825923493e-05,
      "loss": 0.9121,
      "step": 423
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.905130488926748e-05,
      "loss": 0.9005,
      "step": 424
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.9046740742180475e-05,
      "loss": 0.8844,
      "step": 425
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.904216581966707e-05,
      "loss": 0.8901,
      "step": 426
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.9037580123424414e-05,
      "loss": 0.9657,
      "step": 427
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.903298365515367e-05,
      "loss": 0.9243,
      "step": 428
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.902837641655996e-05,
      "loss": 0.9058,
      "step": 429
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.902375840935245e-05,
      "loss": 0.8608,
      "step": 430
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.901912963524426e-05,
      "loss": 1.02,
      "step": 431
    },
    {
      "epoch": 0.33,
      "learning_rate": 5.901449009595253e-05,
      "loss": 0.9886,
      "step": 432
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.9009839793198364e-05,
      "loss": 0.9695,
      "step": 433
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.9005178728706905e-05,
      "loss": 0.8573,
      "step": 434
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.900050690420724e-05,
      "loss": 0.9105,
      "step": 435
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.899582432143247e-05,
      "loss": 0.9772,
      "step": 436
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.89911309821197e-05,
      "loss": 0.89,
      "step": 437
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.898642688801e-05,
      "loss": 0.8906,
      "step": 438
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.8981712040848446e-05,
      "loss": 0.9414,
      "step": 439
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.897698644238409e-05,
      "loss": 0.857,
      "step": 440
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.897225009436998e-05,
      "loss": 0.834,
      "step": 441
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.896750299856317e-05,
      "loss": 0.8266,
      "step": 442
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.896274515672467e-05,
      "loss": 0.9454,
      "step": 443
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.895797657061948e-05,
      "loss": 0.8975,
      "step": 444
    },
    {
      "epoch": 0.34,
      "learning_rate": 5.89531972420166e-05,
      "loss": 0.886,
      "step": 445
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.894840717268903e-05,
      "loss": 0.9169,
      "step": 446
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.894360636441371e-05,
      "loss": 0.8902,
      "step": 447
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.893879481897161e-05,
      "loss": 0.9005,
      "step": 448
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.893397253814765e-05,
      "loss": 0.9576,
      "step": 449
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.8929139523730735e-05,
      "loss": 0.8854,
      "step": 450
    },
    {
      "epoch": 0.35,
      "eval_loss": 0.9176666736602783,
      "eval_runtime": 14.3438,
      "eval_samples_per_second": 5.717,
      "eval_steps_per_second": 5.717,
      "step": 450
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.892429577751378e-05,
      "loss": 0.8726,
      "step": 451
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.8919441301293654e-05,
      "loss": 0.8685,
      "step": 452
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.8914576096871215e-05,
      "loss": 0.9095,
      "step": 453
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.89097001660513e-05,
      "loss": 0.9005,
      "step": 454
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.8904813510642724e-05,
      "loss": 0.9191,
      "step": 455
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.889991613245829e-05,
      "loss": 0.9875,
      "step": 456
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.889500803331476e-05,
      "loss": 0.886,
      "step": 457
    },
    {
      "epoch": 0.35,
      "learning_rate": 5.88900892150329e-05,
      "loss": 0.9026,
      "step": 458
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8885159679437414e-05,
      "loss": 0.9143,
      "step": 459
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.888021942835702e-05,
      "loss": 0.9503,
      "step": 460
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8875268463624406e-05,
      "loss": 0.989,
      "step": 461
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.88703067870762e-05,
      "loss": 0.8855,
      "step": 462
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8865334400553045e-05,
      "loss": 0.9237,
      "step": 463
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.886035130589953e-05,
      "loss": 0.9647,
      "step": 464
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.885535750496423e-05,
      "loss": 0.9134,
      "step": 465
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8850352999599685e-05,
      "loss": 0.9029,
      "step": 466
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8845337791662415e-05,
      "loss": 0.8842,
      "step": 467
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8840311883012904e-05,
      "loss": 0.8617,
      "step": 468
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.88352752755156e-05,
      "loss": 0.9173,
      "step": 469
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.883022797103893e-05,
      "loss": 0.8786,
      "step": 470
    },
    {
      "epoch": 0.36,
      "learning_rate": 5.8825169971455286e-05,
      "loss": 0.8795,
      "step": 471
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.882010127864102e-05,
      "loss": 0.8865,
      "step": 472
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.8815021894476465e-05,
      "loss": 0.8709,
      "step": 473
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.880993182084591e-05,
      "loss": 0.923,
      "step": 474
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.880483105963761e-05,
      "loss": 0.826,
      "step": 475
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.8799719612743794e-05,
      "loss": 1.0261,
      "step": 476
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.879459748206064e-05,
      "loss": 0.8337,
      "step": 477
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.8789464669488294e-05,
      "loss": 0.8766,
      "step": 478
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.878432117693088e-05,
      "loss": 0.8939,
      "step": 479
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.877916700629647e-05,
      "loss": 0.8606,
      "step": 480
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.877400215949708e-05,
      "loss": 0.905,
      "step": 481
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.876882663844873e-05,
      "loss": 0.8498,
      "step": 482
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.876364044507136e-05,
      "loss": 0.9171,
      "step": 483
    },
    {
      "epoch": 0.37,
      "learning_rate": 5.87584435812889e-05,
      "loss": 0.8669,
      "step": 484
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.8753236049029205e-05,
      "loss": 0.9325,
      "step": 485
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.874801785022412e-05,
      "loss": 0.8923,
      "step": 486
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.874278898680941e-05,
      "loss": 0.8181,
      "step": 487
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.8737549460724854e-05,
      "loss": 0.9525,
      "step": 488
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.873229927391412e-05,
      "loss": 0.8537,
      "step": 489
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.8727038428324876e-05,
      "loss": 0.9342,
      "step": 490
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.872176692590873e-05,
      "loss": 0.921,
      "step": 491
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.871648476862124e-05,
      "loss": 0.8135,
      "step": 492
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.8711191958421923e-05,
      "loss": 0.9138,
      "step": 493
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.8705888497274236e-05,
      "loss": 0.9068,
      "step": 494
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.870057438714562e-05,
      "loss": 0.8974,
      "step": 495
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.869524963000741e-05,
      "loss": 0.9027,
      "step": 496
    },
    {
      "epoch": 0.38,
      "learning_rate": 5.868991422783495e-05,
      "loss": 0.9058,
      "step": 497
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.8684568182607486e-05,
      "loss": 0.8869,
      "step": 498
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.8679211496308245e-05,
      "loss": 0.9143,
      "step": 499
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.8673844170924385e-05,
      "loss": 0.8421,
      "step": 500
    },
    {
      "epoch": 0.39,
      "eval_loss": 0.9152392745018005,
      "eval_runtime": 14.354,
      "eval_samples_per_second": 5.713,
      "eval_steps_per_second": 5.713,
      "step": 500
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.8668466208447025e-05,
      "loss": 0.909,
      "step": 501
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.86630776108712e-05,
      "loss": 0.9393,
      "step": 502
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.865767838019592e-05,
      "loss": 0.8721,
      "step": 503
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.865226851842414e-05,
      "loss": 0.8537,
      "step": 504
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.864684802756274e-05,
      "loss": 0.8315,
      "step": 505
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.864141690962254e-05,
      "loss": 0.8782,
      "step": 506
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.8635975166618324e-05,
      "loss": 0.951,
      "step": 507
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.863052280056881e-05,
      "loss": 0.8717,
      "step": 508
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.862505981349665e-05,
      "loss": 0.9315,
      "step": 509
    },
    {
      "epoch": 0.39,
      "learning_rate": 5.861958620742845e-05,
      "loss": 0.9339,
      "step": 510
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.861410198439472e-05,
      "loss": 0.9994,
      "step": 511
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.8608607146429966e-05,
      "loss": 0.9129,
      "step": 512
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.8603101695572585e-05,
      "loss": 0.8851,
      "step": 513
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.8597585633864924e-05,
      "loss": 0.8472,
      "step": 514
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.859205896335327e-05,
      "loss": 0.8707,
      "step": 515
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.858652168608785e-05,
      "loss": 0.8989,
      "step": 516
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.85809738041228e-05,
      "loss": 0.8433,
      "step": 517
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.857541531951623e-05,
      "loss": 0.9697,
      "step": 518
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.8569846234330156e-05,
      "loss": 0.9184,
      "step": 519
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.856426655063053e-05,
      "loss": 0.897,
      "step": 520
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.855867627048725e-05,
      "loss": 0.9788,
      "step": 521
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.8553075395974125e-05,
      "loss": 0.9255,
      "step": 522
    },
    {
      "epoch": 0.4,
      "learning_rate": 5.85474639291689e-05,
      "loss": 0.8777,
      "step": 523
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.8541841872153256e-05,
      "loss": 0.8764,
      "step": 524
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.85362092270128e-05,
      "loss": 0.8822,
      "step": 525
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.853056599583707e-05,
      "loss": 1.0576,
      "step": 526
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.8524912180719526e-05,
      "loss": 0.8794,
      "step": 527
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.851924778375754e-05,
      "loss": 0.9405,
      "step": 528
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.851357280705245e-05,
      "loss": 0.8427,
      "step": 529
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.8507887252709475e-05,
      "loss": 0.982,
      "step": 530
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.850219112283779e-05,
      "loss": 0.8303,
      "step": 531
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.849648441955047e-05,
      "loss": 0.9272,
      "step": 532
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.849076714496452e-05,
      "loss": 0.8439,
      "step": 533
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.848503930120088e-05,
      "loss": 0.8927,
      "step": 534
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.8479300890384386e-05,
      "loss": 0.8113,
      "step": 535
    },
    {
      "epoch": 0.41,
      "learning_rate": 5.847355191464382e-05,
      "loss": 0.9015,
      "step": 536
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.846779237611187e-05,
      "loss": 0.8994,
      "step": 537
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.8462022276925134e-05,
      "loss": 0.8438,
      "step": 538
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.8456241619224144e-05,
      "loss": 0.9202,
      "step": 539
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.8450450405153344e-05,
      "loss": 0.8469,
      "step": 540
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.844464863686109e-05,
      "loss": 0.8866,
      "step": 541
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.843883631649965e-05,
      "loss": 0.9187,
      "step": 542
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.843301344622523e-05,
      "loss": 0.9825,
      "step": 543
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.8427180028197904e-05,
      "loss": 0.9502,
      "step": 544
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.84213360645817e-05,
      "loss": 0.8491,
      "step": 545
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.8415481557544555e-05,
      "loss": 0.9165,
      "step": 546
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.840961650925829e-05,
      "loss": 0.8767,
      "step": 547
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.840374092189866e-05,
      "loss": 0.8619,
      "step": 548
    },
    {
      "epoch": 0.42,
      "learning_rate": 5.839785479764532e-05,
      "loss": 0.9788,
      "step": 549
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.839195813868185e-05,
      "loss": 0.9077,
      "step": 550
    },
    {
      "epoch": 0.43,
      "eval_loss": 0.9117449522018433,
      "eval_runtime": 14.3485,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 550
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.838605094719571e-05,
      "loss": 0.9642,
      "step": 551
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.838013322537828e-05,
      "loss": 0.8709,
      "step": 552
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.8374204975424865e-05,
      "loss": 0.9959,
      "step": 553
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.836826619953465e-05,
      "loss": 0.8574,
      "step": 554
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.8362316899910726e-05,
      "loss": 0.8509,
      "step": 555
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.835635707876011e-05,
      "loss": 0.8414,
      "step": 556
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.8350386738293695e-05,
      "loss": 0.9044,
      "step": 557
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.83444058807263e-05,
      "loss": 1.0612,
      "step": 558
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.833841450827663e-05,
      "loss": 0.8717,
      "step": 559
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.833241262316729e-05,
      "loss": 0.8887,
      "step": 560
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.83264002276248e-05,
      "loss": 0.9073,
      "step": 561
    },
    {
      "epoch": 0.43,
      "learning_rate": 5.832037732387957e-05,
      "loss": 0.9127,
      "step": 562
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.83143439141659e-05,
      "loss": 0.852,
      "step": 563
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.8308300000721996e-05,
      "loss": 0.9675,
      "step": 564
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.830224558578997e-05,
      "loss": 0.8847,
      "step": 565
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.82961806716158e-05,
      "loss": 0.8906,
      "step": 566
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.82901052604494e-05,
      "loss": 0.7885,
      "step": 567
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.8284019354544544e-05,
      "loss": 0.8548,
      "step": 568
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.827792295615891e-05,
      "loss": 0.8745,
      "step": 569
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.827181606755408e-05,
      "loss": 0.9804,
      "step": 570
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.8265698690995514e-05,
      "loss": 0.9415,
      "step": 571
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.825957082875255e-05,
      "loss": 0.8596,
      "step": 572
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.825343248309845e-05,
      "loss": 0.9504,
      "step": 573
    },
    {
      "epoch": 0.44,
      "learning_rate": 5.824728365631035e-05,
      "loss": 0.8962,
      "step": 574
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.8241124350669254e-05,
      "loss": 0.8937,
      "step": 575
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.823495456846009e-05,
      "loss": 0.9165,
      "step": 576
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.822877431197163e-05,
      "loss": 0.8571,
      "step": 577
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.822258358349656e-05,
      "loss": 0.9668,
      "step": 578
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.8216382385331474e-05,
      "loss": 0.9476,
      "step": 579
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.8210170719776796e-05,
      "loss": 0.9074,
      "step": 580
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.820394858913685e-05,
      "loss": 0.8916,
      "step": 581
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.819771599571987e-05,
      "loss": 0.8664,
      "step": 582
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.819147294183795e-05,
      "loss": 0.9233,
      "step": 583
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.8185219429807054e-05,
      "loss": 0.8575,
      "step": 584
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.8178955461947046e-05,
      "loss": 0.8917,
      "step": 585
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.817268104058167e-05,
      "loss": 0.8712,
      "step": 586
    },
    {
      "epoch": 0.45,
      "learning_rate": 5.816639616803851e-05,
      "loss": 0.8683,
      "step": 587
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.816010084664909e-05,
      "loss": 0.9248,
      "step": 588
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.815379507874876e-05,
      "loss": 0.9097,
      "step": 589
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.814747886667676e-05,
      "loss": 0.8979,
      "step": 590
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.814115221277621e-05,
      "loss": 0.8521,
      "step": 591
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.81348151193941e-05,
      "loss": 0.8079,
      "step": 592
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.812846758888127e-05,
      "loss": 0.9141,
      "step": 593
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.8122109623592495e-05,
      "loss": 0.8798,
      "step": 594
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.811574122588635e-05,
      "loss": 0.8782,
      "step": 595
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.8109362398125325e-05,
      "loss": 0.9246,
      "step": 596
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.8102973142675756e-05,
      "loss": 0.9663,
      "step": 597
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.809657346190785e-05,
      "loss": 0.9701,
      "step": 598
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.8090163358195705e-05,
      "loss": 0.919,
      "step": 599
    },
    {
      "epoch": 0.46,
      "learning_rate": 5.8083742833917254e-05,
      "loss": 0.9248,
      "step": 600
    },
    {
      "epoch": 0.46,
      "eval_loss": 0.9059345126152039,
      "eval_runtime": 14.3408,
      "eval_samples_per_second": 5.718,
      "eval_steps_per_second": 5.718,
      "step": 600
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.807731189145431e-05,
      "loss": 0.9101,
      "step": 601
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.807087053319256e-05,
      "loss": 0.8648,
      "step": 602
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.806441876152153e-05,
      "loss": 0.8518,
      "step": 603
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.805795657883465e-05,
      "loss": 0.8208,
      "step": 604
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.805148398752914e-05,
      "loss": 0.937,
      "step": 605
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.8045000990006184e-05,
      "loss": 0.868,
      "step": 606
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.803850758867072e-05,
      "loss": 0.8612,
      "step": 607
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.8032003785931634e-05,
      "loss": 0.8796,
      "step": 608
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.8025489584201604e-05,
      "loss": 0.8998,
      "step": 609
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.801896498589722e-05,
      "loss": 0.8788,
      "step": 610
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.801242999343888e-05,
      "loss": 0.8722,
      "step": 611
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.8005884609250866e-05,
      "loss": 0.908,
      "step": 612
    },
    {
      "epoch": 0.47,
      "learning_rate": 5.799932883576132e-05,
      "loss": 0.7785,
      "step": 613
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.7992762675402206e-05,
      "loss": 0.8833,
      "step": 614
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.798618613060939e-05,
      "loss": 0.9345,
      "step": 615
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.7979599203822534e-05,
      "loss": 0.8909,
      "step": 616
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.7973001897485216e-05,
      "loss": 0.8355,
      "step": 617
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.79663942140448e-05,
      "loss": 0.9329,
      "step": 618
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.795977615595254e-05,
      "loss": 0.8372,
      "step": 619
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.795314772566352e-05,
      "loss": 0.9102,
      "step": 620
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.794650892563669e-05,
      "loss": 0.8206,
      "step": 621
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.793985975833483e-05,
      "loss": 0.9362,
      "step": 622
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.793320022622456e-05,
      "loss": 0.9391,
      "step": 623
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.792653033177638e-05,
      "loss": 0.8853,
      "step": 624
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.791985007746459e-05,
      "loss": 0.9109,
      "step": 625
    },
    {
      "epoch": 0.48,
      "learning_rate": 5.791315946576737e-05,
      "loss": 0.9542,
      "step": 626
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.790645849916672e-05,
      "loss": 0.8725,
      "step": 627
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.789974718014848e-05,
      "loss": 0.8199,
      "step": 628
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.789302551120235e-05,
      "loss": 0.8111,
      "step": 629
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.788629349482185e-05,
      "loss": 0.9484,
      "step": 630
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.787955113350436e-05,
      "loss": 0.9182,
      "step": 631
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.787279842975106e-05,
      "loss": 0.9239,
      "step": 632
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.7866035386067006e-05,
      "loss": 0.9145,
      "step": 633
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.7859262004961065e-05,
      "loss": 0.8298,
      "step": 634
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.7852478288945966e-05,
      "loss": 0.899,
      "step": 635
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.784568424053823e-05,
      "loss": 0.8257,
      "step": 636
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.7838879862258265e-05,
      "loss": 1.0265,
      "step": 637
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.783206515663025e-05,
      "loss": 0.898,
      "step": 638
    },
    {
      "epoch": 0.49,
      "learning_rate": 5.7825240126182254e-05,
      "loss": 0.8298,
      "step": 639
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7818404773446126e-05,
      "loss": 0.9161,
      "step": 640
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.781155910095757e-05,
      "loss": 0.9423,
      "step": 641
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7804703111256125e-05,
      "loss": 0.8903,
      "step": 642
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.779783680688514e-05,
      "loss": 0.9239,
      "step": 643
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7790960190391804e-05,
      "loss": 0.9202,
      "step": 644
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7784073264327115e-05,
      "loss": 0.8425,
      "step": 645
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.777717603124593e-05,
      "loss": 0.8335,
      "step": 646
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.777026849370687e-05,
      "loss": 0.9355,
      "step": 647
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.776335065427244e-05,
      "loss": 0.8531,
      "step": 648
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.775642251550893e-05,
      "loss": 0.9,
      "step": 649
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7749484079986456e-05,
      "loss": 0.8229,
      "step": 650
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.9039155840873718,
      "eval_runtime": 14.346,
      "eval_samples_per_second": 5.716,
      "eval_steps_per_second": 5.716,
      "step": 650
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.7742535350278983e-05,
      "loss": 0.8567,
      "step": 651
    },
    {
      "epoch": 0.5,
      "learning_rate": 5.773557632896424e-05,
      "loss": 0.8965,
      "step": 652
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.772860701862383e-05,
      "loss": 0.8232,
      "step": 653
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.772162742184313e-05,
      "loss": 0.872,
      "step": 654
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.771463754121136e-05,
      "loss": 0.8713,
      "step": 655
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.770763737932155e-05,
      "loss": 0.8131,
      "step": 656
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.7700626938770524e-05,
      "loss": 0.8987,
      "step": 657
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.769360622215896e-05,
      "loss": 0.9732,
      "step": 658
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.768657523209129e-05,
      "loss": 0.9619,
      "step": 659
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.767953397117581e-05,
      "loss": 0.8869,
      "step": 660
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.767248244202461e-05,
      "loss": 0.8991,
      "step": 661
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.766542064725357e-05,
      "loss": 0.9926,
      "step": 662
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.76583485894824e-05,
      "loss": 0.8709,
      "step": 663
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.7651266271334626e-05,
      "loss": 0.8714,
      "step": 664
    },
    {
      "epoch": 0.51,
      "learning_rate": 5.764417369543755e-05,
      "loss": 0.9332,
      "step": 665
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.763707086442229e-05,
      "loss": 0.9,
      "step": 666
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.762995778092378e-05,
      "loss": 0.8855,
      "step": 667
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.762283444758075e-05,
      "loss": 0.9365,
      "step": 668
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.761570086703573e-05,
      "loss": 0.8918,
      "step": 669
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.7608557041935055e-05,
      "loss": 0.9494,
      "step": 670
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.760140297492886e-05,
      "loss": 0.8959,
      "step": 671
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.759423866867108e-05,
      "loss": 0.8714,
      "step": 672
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.7587064125819444e-05,
      "loss": 0.9425,
      "step": 673
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.757987934903548e-05,
      "loss": 0.9575,
      "step": 674
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.7572684340984526e-05,
      "loss": 0.931,
      "step": 675
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.756547910433568e-05,
      "loss": 0.8957,
      "step": 676
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.755826364176188e-05,
      "loss": 0.8972,
      "step": 677
    },
    {
      "epoch": 0.52,
      "learning_rate": 5.755103795593983e-05,
      "loss": 0.9123,
      "step": 678
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7543802049550026e-05,
      "loss": 0.8302,
      "step": 679
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7536555925276766e-05,
      "loss": 0.8715,
      "step": 680
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.752929958580814e-05,
      "loss": 0.8265,
      "step": 681
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7522033033836004e-05,
      "loss": 0.8706,
      "step": 682
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7514756272056025e-05,
      "loss": 0.8956,
      "step": 683
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7507469303167674e-05,
      "loss": 0.9307,
      "step": 684
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7500172129874165e-05,
      "loss": 0.8777,
      "step": 685
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7492864754882527e-05,
      "loss": 0.8308,
      "step": 686
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.748554718090356e-05,
      "loss": 0.8611,
      "step": 687
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.747821941065186e-05,
      "loss": 0.8826,
      "step": 688
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.747088144684581e-05,
      "loss": 0.9537,
      "step": 689
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.7463533292207535e-05,
      "loss": 0.8979,
      "step": 690
    },
    {
      "epoch": 0.53,
      "learning_rate": 5.745617494946299e-05,
      "loss": 0.8807,
      "step": 691
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7448806421341884e-05,
      "loss": 0.8096,
      "step": 692
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.744142771057771e-05,
      "loss": 0.8452,
      "step": 693
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.743403881990773e-05,
      "loss": 0.9678,
      "step": 694
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7426639752073e-05,
      "loss": 0.8519,
      "step": 695
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.741923050981834e-05,
      "loss": 0.8548,
      "step": 696
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7411811095892344e-05,
      "loss": 0.8179,
      "step": 697
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.740438151304737e-05,
      "loss": 0.864,
      "step": 698
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.739694176403958e-05,
      "loss": 0.9448,
      "step": 699
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7389491851628865e-05,
      "loss": 0.9499,
      "step": 700
    },
    {
      "epoch": 0.54,
      "eval_loss": 0.9012778401374817,
      "eval_runtime": 14.3419,
      "eval_samples_per_second": 5.718,
      "eval_steps_per_second": 5.718,
      "step": 700
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7382031778578935e-05,
      "loss": 0.8603,
      "step": 701
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7374561547657214e-05,
      "loss": 0.8941,
      "step": 702
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7367081161634936e-05,
      "loss": 0.909,
      "step": 703
    },
    {
      "epoch": 0.54,
      "learning_rate": 5.7359590623287085e-05,
      "loss": 0.9642,
      "step": 704
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.735208993539242e-05,
      "loss": 0.9763,
      "step": 705
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7344579100733463e-05,
      "loss": 0.8517,
      "step": 706
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7337058122096474e-05,
      "loss": 0.8502,
      "step": 707
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.732952700227154e-05,
      "loss": 0.9014,
      "step": 708
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7321985744052426e-05,
      "loss": 0.9876,
      "step": 709
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.731443435023673e-05,
      "loss": 0.8273,
      "step": 710
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7306872823625776e-05,
      "loss": 0.8698,
      "step": 711
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7299301167024636e-05,
      "loss": 0.9286,
      "step": 712
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.729171938324218e-05,
      "loss": 0.917,
      "step": 713
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7284127475091005e-05,
      "loss": 0.855,
      "step": 714
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.727652544538746e-05,
      "loss": 0.8091,
      "step": 715
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7268913296951664e-05,
      "loss": 0.873,
      "step": 716
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.7261291032607484e-05,
      "loss": 0.8522,
      "step": 717
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.725365865518254e-05,
      "loss": 1.0029,
      "step": 718
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.72460161675082e-05,
      "loss": 0.8087,
      "step": 719
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.72383635724196e-05,
      "loss": 0.8944,
      "step": 720
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.72307008727556e-05,
      "loss": 0.8752,
      "step": 721
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.722302807135882e-05,
      "loss": 0.8779,
      "step": 722
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.7215345171075635e-05,
      "loss": 0.9601,
      "step": 723
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.720765217475616e-05,
      "loss": 0.9212,
      "step": 724
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.719994908525424e-05,
      "loss": 0.9622,
      "step": 725
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.719223590542749e-05,
      "loss": 0.8445,
      "step": 726
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.718451263813725e-05,
      "loss": 0.862,
      "step": 727
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.717677928624862e-05,
      "loss": 0.9523,
      "step": 728
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.7169035852630415e-05,
      "loss": 0.8818,
      "step": 729
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.7161282340155227e-05,
      "loss": 0.8504,
      "step": 730
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.7153518751699345e-05,
      "loss": 0.8917,
      "step": 731
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.7145745090142826e-05,
      "loss": 0.8896,
      "step": 732
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.713796135836945e-05,
      "loss": 0.8805,
      "step": 733
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.713016755926674e-05,
      "loss": 0.8733,
      "step": 734
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.712236369572595e-05,
      "loss": 0.7904,
      "step": 735
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.711454977064205e-05,
      "loss": 0.8426,
      "step": 736
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.710672578691379e-05,
      "loss": 0.8387,
      "step": 737
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.70988917474436e-05,
      "loss": 0.8782,
      "step": 738
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.709104765513767e-05,
      "loss": 0.8335,
      "step": 739
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.708319351290591e-05,
      "loss": 0.8842,
      "step": 740
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.707532932366197e-05,
      "loss": 0.9647,
      "step": 741
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.7067455090323195e-05,
      "loss": 0.8426,
      "step": 742
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.705957081581069e-05,
      "loss": 0.7764,
      "step": 743
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.705167650304927e-05,
      "loss": 0.8897,
      "step": 744
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.7043772154967484e-05,
      "loss": 0.8388,
      "step": 745
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.7035857774497595e-05,
      "loss": 0.8251,
      "step": 746
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.702793336457558e-05,
      "loss": 0.866,
      "step": 747
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.7019998928141144e-05,
      "loss": 0.9179,
      "step": 748
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.7012054468137725e-05,
      "loss": 0.8813,
      "step": 749
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.700409998751246e-05,
      "loss": 0.8964,
      "step": 750
    },
    {
      "epoch": 0.58,
      "eval_loss": 0.8968020081520081,
      "eval_runtime": 14.3411,
      "eval_samples_per_second": 5.718,
      "eval_steps_per_second": 5.718,
      "step": 750
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.699613548921622e-05,
      "loss": 0.8096,
      "step": 751
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.698816097620357e-05,
      "loss": 0.8947,
      "step": 752
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.69801764514328e-05,
      "loss": 0.8738,
      "step": 753
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.697218191786593e-05,
      "loss": 0.8185,
      "step": 754
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.696417737846869e-05,
      "loss": 0.8905,
      "step": 755
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.695616283621049e-05,
      "loss": 0.8541,
      "step": 756
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.6948138294064484e-05,
      "loss": 1.0064,
      "step": 757
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.694010375500752e-05,
      "loss": 0.8539,
      "step": 758
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.693205922202016e-05,
      "loss": 0.9046,
      "step": 759
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.692400469808668e-05,
      "loss": 0.8888,
      "step": 760
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.6915940186195044e-05,
      "loss": 0.8379,
      "step": 761
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.6907865689336936e-05,
      "loss": 0.8347,
      "step": 762
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.6899781210507754e-05,
      "loss": 0.9094,
      "step": 763
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.6891686752706556e-05,
      "loss": 0.9074,
      "step": 764
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.688358231893615e-05,
      "loss": 0.8133,
      "step": 765
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.687546791220303e-05,
      "loss": 0.9195,
      "step": 766
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.686734353551737e-05,
      "loss": 0.8915,
      "step": 767
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.685920919189307e-05,
      "loss": 0.8723,
      "step": 768
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.685106488434771e-05,
      "loss": 0.8626,
      "step": 769
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.684291061590258e-05,
      "loss": 0.8588,
      "step": 770
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.683474638958264e-05,
      "loss": 0.8745,
      "step": 771
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.6826572208416576e-05,
      "loss": 0.9324,
      "step": 772
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.681838807543675e-05,
      "loss": 0.8791,
      "step": 773
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.681019399367921e-05,
      "loss": 0.8418,
      "step": 774
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.680198996618371e-05,
      "loss": 0.8458,
      "step": 775
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.6793775995993676e-05,
      "loss": 0.8241,
      "step": 776
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.678555208615626e-05,
      "loss": 0.9038,
      "step": 777
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.677731823972223e-05,
      "loss": 0.7262,
      "step": 778
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.676907445974612e-05,
      "loss": 0.8631,
      "step": 779
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.676082074928609e-05,
      "loss": 0.943,
      "step": 780
    },
    {
      "epoch": 0.6,
      "learning_rate": 5.675255711140402e-05,
      "loss": 0.857,
      "step": 781
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.674428354916547e-05,
      "loss": 0.8835,
      "step": 782
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.673600006563964e-05,
      "loss": 0.8119,
      "step": 783
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.672770666389946e-05,
      "loss": 0.8788,
      "step": 784
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6719403347021524e-05,
      "loss": 0.8798,
      "step": 785
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6711090118086096e-05,
      "loss": 0.9142,
      "step": 786
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.670276698017714e-05,
      "loss": 0.863,
      "step": 787
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.669443393638223e-05,
      "loss": 0.9426,
      "step": 788
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.668609098979271e-05,
      "loss": 0.9019,
      "step": 789
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6677738143503534e-05,
      "loss": 0.8161,
      "step": 790
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6669375400613355e-05,
      "loss": 0.9096,
      "step": 791
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.666100276422446e-05,
      "loss": 0.9592,
      "step": 792
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6652620237442866e-05,
      "loss": 0.8469,
      "step": 793
    },
    {
      "epoch": 0.61,
      "learning_rate": 5.6644227823378207e-05,
      "loss": 0.9142,
      "step": 794
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.663582552514381e-05,
      "loss": 0.8349,
      "step": 795
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.662741334585666e-05,
      "loss": 0.9619,
      "step": 796
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.661899128863742e-05,
      "loss": 0.8727,
      "step": 797
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.6610559356610396e-05,
      "loss": 0.9841,
      "step": 798
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.660211755290357e-05,
      "loss": 0.8318,
      "step": 799
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.6593665880648606e-05,
      "loss": 0.8897,
      "step": 800
    },
    {
      "epoch": 0.62,
      "eval_loss": 0.8941949009895325,
      "eval_runtime": 14.3548,
      "eval_samples_per_second": 5.712,
      "eval_steps_per_second": 5.712,
      "step": 800
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.6585204342980783e-05,
      "loss": 0.8329,
      "step": 801
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.6576732943039074e-05,
      "loss": 0.8769,
      "step": 802
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.65682516839661e-05,
      "loss": 0.8992,
      "step": 803
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.6559760568908145e-05,
      "loss": 0.8372,
      "step": 804
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.655125960101515e-05,
      "loss": 0.8693,
      "step": 805
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.65427487834407e-05,
      "loss": 0.8151,
      "step": 806
    },
    {
      "epoch": 0.62,
      "learning_rate": 5.653422811934204e-05,
      "loss": 0.8688,
      "step": 807
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.652569761188006e-05,
      "loss": 0.952,
      "step": 808
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.651715726421933e-05,
      "loss": 0.8595,
      "step": 809
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.6508607079528034e-05,
      "loss": 0.8442,
      "step": 810
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.6500047060978024e-05,
      "loss": 0.9144,
      "step": 811
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.6491477211744796e-05,
      "loss": 0.9222,
      "step": 812
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.64828975350075e-05,
      "loss": 0.8602,
      "step": 813
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.647430803394893e-05,
      "loss": 0.9584,
      "step": 814
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.646570871175551e-05,
      "loss": 0.9033,
      "step": 815
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.645709957161732e-05,
      "loss": 0.9517,
      "step": 816
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.644848061672809e-05,
      "loss": 0.8506,
      "step": 817
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.643985185028516e-05,
      "loss": 0.874,
      "step": 818
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.643121327548956e-05,
      "loss": 0.9528,
      "step": 819
    },
    {
      "epoch": 0.63,
      "learning_rate": 5.6422564895545904e-05,
      "loss": 0.843,
      "step": 820
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.6413906713662475e-05,
      "loss": 0.8059,
      "step": 821
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.64052387330512e-05,
      "loss": 0.8422,
      "step": 822
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.6396560956927604e-05,
      "loss": 0.9148,
      "step": 823
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.638787338851088e-05,
      "loss": 0.8774,
      "step": 824
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.6379176031023854e-05,
      "loss": 0.939,
      "step": 825
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.6370468887692945e-05,
      "loss": 0.8618,
      "step": 826
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.636175196174825e-05,
      "loss": 0.891,
      "step": 827
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.635302525642348e-05,
      "loss": 0.8987,
      "step": 828
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.634428877495595e-05,
      "loss": 0.9016,
      "step": 829
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.6335542520586617e-05,
      "loss": 0.8609,
      "step": 830
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.632678649656009e-05,
      "loss": 0.8138,
      "step": 831
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.631802070612455e-05,
      "loss": 0.8953,
      "step": 832
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.630924515253185e-05,
      "loss": 0.8122,
      "step": 833
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.630045983903743e-05,
      "loss": 0.9477,
      "step": 834
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.629166476890038e-05,
      "loss": 0.8222,
      "step": 835
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.628285994538338e-05,
      "loss": 0.9617,
      "step": 836
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.627404537175275e-05,
      "loss": 0.865,
      "step": 837
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.626522105127842e-05,
      "loss": 0.7969,
      "step": 838
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6256386987233936e-05,
      "loss": 0.9645,
      "step": 839
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.624754318289645e-05,
      "loss": 0.8427,
      "step": 840
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6238689641546736e-05,
      "loss": 0.831,
      "step": 841
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.6229826366469183e-05,
      "loss": 0.8311,
      "step": 842
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.622095336095179e-05,
      "loss": 0.9052,
      "step": 843
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.621207062828616e-05,
      "loss": 0.9529,
      "step": 844
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.62031781717675e-05,
      "loss": 0.8941,
      "step": 845
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.619427599469464e-05,
      "loss": 0.8498,
      "step": 846
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.618536410037002e-05,
      "loss": 0.8236,
      "step": 847
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6176442492099635e-05,
      "loss": 0.9967,
      "step": 848
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.616751117319315e-05,
      "loss": 0.9366,
      "step": 849
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.61585701469638e-05,
      "loss": 0.9187,
      "step": 850
    },
    {
      "epoch": 0.66,
      "eval_loss": 0.8949863910675049,
      "eval_runtime": 14.3422,
      "eval_samples_per_second": 5.717,
      "eval_steps_per_second": 5.717,
      "step": 850
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.614961941672842e-05,
      "loss": 0.8379,
      "step": 851
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.614065898580745e-05,
      "loss": 0.9213,
      "step": 852
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6131688857524925e-05,
      "loss": 0.8992,
      "step": 853
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.6122709035208485e-05,
      "loss": 0.904,
      "step": 854
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.611371952218936e-05,
      "loss": 0.8267,
      "step": 855
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.610472032180237e-05,
      "loss": 0.904,
      "step": 856
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.609571143738595e-05,
      "loss": 0.8653,
      "step": 857
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.60866928722821e-05,
      "loss": 0.9218,
      "step": 858
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.607766462983642e-05,
      "loss": 0.9337,
      "step": 859
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.6068626713398116e-05,
      "loss": 0.8817,
      "step": 860
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.6059579126319965e-05,
      "loss": 0.8493,
      "step": 861
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.605052187195834e-05,
      "loss": 0.8802,
      "step": 862
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.604145495367318e-05,
      "loss": 0.8963,
      "step": 863
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.603237837482805e-05,
      "loss": 0.9126,
      "step": 864
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.602329213879007e-05,
      "loss": 0.9063,
      "step": 865
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.601419624892994e-05,
      "loss": 0.8126,
      "step": 866
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.6005090708621946e-05,
      "loss": 0.8346,
      "step": 867
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.5995975521243966e-05,
      "loss": 0.8174,
      "step": 868
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.598685069017745e-05,
      "loss": 0.8269,
      "step": 869
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.5977716218807416e-05,
      "loss": 0.8838,
      "step": 870
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.596857211052245e-05,
      "loss": 0.9552,
      "step": 871
    },
    {
      "epoch": 0.67,
      "learning_rate": 5.5959418368714764e-05,
      "loss": 0.8258,
      "step": 872
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.5950254996780084e-05,
      "loss": 0.8131,
      "step": 873
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.594108199811774e-05,
      "loss": 0.9021,
      "step": 874
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.593189937613062e-05,
      "loss": 0.8106,
      "step": 875
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.592270713422519e-05,
      "loss": 0.7695,
      "step": 876
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.5913505275811485e-05,
      "loss": 0.9251,
      "step": 877
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.5904293804303097e-05,
      "loss": 0.8606,
      "step": 878
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.58950727231172e-05,
      "loss": 0.8502,
      "step": 879
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.588584203567453e-05,
      "loss": 0.8431,
      "step": 880
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.5876601745399364e-05,
      "loss": 0.8561,
      "step": 881
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.586735185571957e-05,
      "loss": 0.8766,
      "step": 882
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.585809237006657e-05,
      "loss": 0.8661,
      "step": 883
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.584882329187534e-05,
      "loss": 0.8532,
      "step": 884
    },
    {
      "epoch": 0.68,
      "learning_rate": 5.58395446245844e-05,
      "loss": 0.861,
      "step": 885
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.5830256371635874e-05,
      "loss": 0.9342,
      "step": 886
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.582095853647538e-05,
      "loss": 0.9382,
      "step": 887
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.581165112255215e-05,
      "loss": 0.8305,
      "step": 888
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.580233413331891e-05,
      "loss": 0.7964,
      "step": 889
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.579300757223199e-05,
      "loss": 0.8303,
      "step": 890
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.578367144275126e-05,
      "loss": 0.8899,
      "step": 891
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.5774325748340104e-05,
      "loss": 0.8736,
      "step": 892
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.57649704924655e-05,
      "loss": 0.9197,
      "step": 893
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.575560567859795e-05,
      "loss": 0.8775,
      "step": 894
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.5746231310211495e-05,
      "loss": 0.8338,
      "step": 895
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.5736847390783746e-05,
      "loss": 0.8329,
      "step": 896
    },
    {
      "epoch": 0.69,
      "learning_rate": 5.572745392379583e-05,
      "loss": 0.7831,
      "step": 897
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5718050912732435e-05,
      "loss": 0.795,
      "step": 898
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.570863836108178e-05,
      "loss": 0.9468,
      "step": 899
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5699216272335615e-05,
      "loss": 0.7855,
      "step": 900
    },
    {
      "epoch": 0.7,
      "eval_loss": 0.8913570046424866,
      "eval_runtime": 14.3474,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 900
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.568978464998925e-05,
      "loss": 0.7732,
      "step": 901
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.568034349754152e-05,
      "loss": 0.9285,
      "step": 902
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5670892818494795e-05,
      "loss": 0.8993,
      "step": 903
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.566143261635497e-05,
      "loss": 0.9271,
      "step": 904
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5651962894631494e-05,
      "loss": 0.884,
      "step": 905
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.564248365683733e-05,
      "loss": 0.8917,
      "step": 906
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5632994906488986e-05,
      "loss": 0.8178,
      "step": 907
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.562349664710646e-05,
      "loss": 0.8853,
      "step": 908
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.5613988882213357e-05,
      "loss": 0.905,
      "step": 909
    },
    {
      "epoch": 0.7,
      "learning_rate": 5.560447161533671e-05,
      "loss": 0.882,
      "step": 910
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.559494485000715e-05,
      "loss": 0.9204,
      "step": 911
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.55854085897588e-05,
      "loss": 0.9245,
      "step": 912
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.557586283812932e-05,
      "loss": 0.9107,
      "step": 913
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.556630759865987e-05,
      "loss": 0.899,
      "step": 914
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.555674287489516e-05,
      "loss": 0.8228,
      "step": 915
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.554716867038339e-05,
      "loss": 0.8602,
      "step": 916
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.553758498867628e-05,
      "loss": 0.9472,
      "step": 917
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.55279918333291e-05,
      "loss": 0.8463,
      "step": 918
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.551838920790059e-05,
      "loss": 0.8159,
      "step": 919
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.550877711595302e-05,
      "loss": 0.8532,
      "step": 920
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.5499155561052184e-05,
      "loss": 0.852,
      "step": 921
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.548952454676737e-05,
      "loss": 0.9073,
      "step": 922
    },
    {
      "epoch": 0.71,
      "learning_rate": 5.5479884076671376e-05,
      "loss": 0.8982,
      "step": 923
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.547023415434053e-05,
      "loss": 0.9325,
      "step": 924
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5460574783354634e-05,
      "loss": 0.9771,
      "step": 925
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.545090596729702e-05,
      "loss": 0.8209,
      "step": 926
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5441227709754495e-05,
      "loss": 0.8407,
      "step": 927
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5431540014317414e-05,
      "loss": 0.8746,
      "step": 928
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5421842884579594e-05,
      "loss": 0.8438,
      "step": 929
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.541213632413836e-05,
      "loss": 0.9129,
      "step": 930
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.540242033659456e-05,
      "loss": 0.8874,
      "step": 931
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5392694925552494e-05,
      "loss": 0.898,
      "step": 932
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5382960094619996e-05,
      "loss": 0.8126,
      "step": 933
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.537321584740839e-05,
      "loss": 0.9165,
      "step": 934
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5363462187532467e-05,
      "loss": 0.863,
      "step": 935
    },
    {
      "epoch": 0.72,
      "learning_rate": 5.5353699118610534e-05,
      "loss": 0.8454,
      "step": 936
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.534392664426439e-05,
      "loss": 0.9201,
      "step": 937
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.5334144768119316e-05,
      "loss": 0.8392,
      "step": 938
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.532435349380407e-05,
      "loss": 0.9189,
      "step": 939
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.531455282495091e-05,
      "loss": 0.8695,
      "step": 940
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.530474276519557e-05,
      "loss": 1.0612,
      "step": 941
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.5294923318177296e-05,
      "loss": 0.8439,
      "step": 942
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.528509448753877e-05,
      "loss": 0.8951,
      "step": 943
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.527525627692618e-05,
      "loss": 0.8056,
      "step": 944
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.5265408689989207e-05,
      "loss": 0.8821,
      "step": 945
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.525555173038098e-05,
      "loss": 0.8263,
      "step": 946
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.524568540175813e-05,
      "loss": 0.9063,
      "step": 947
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.5235809707780767e-05,
      "loss": 0.822,
      "step": 948
    },
    {
      "epoch": 0.73,
      "learning_rate": 5.522592465211244e-05,
      "loss": 0.8603,
      "step": 949
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.521603023842019e-05,
      "loss": 0.8748,
      "step": 950
    },
    {
      "epoch": 0.74,
      "eval_loss": 0.8888280391693115,
      "eval_runtime": 14.3504,
      "eval_samples_per_second": 5.714,
      "eval_steps_per_second": 5.714,
      "step": 950
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.520612647037456e-05,
      "loss": 0.925,
      "step": 951
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.519621335164951e-05,
      "loss": 0.8473,
      "step": 952
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.518629088592251e-05,
      "loss": 0.8636,
      "step": 953
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.517635907687448e-05,
      "loss": 0.829,
      "step": 954
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.5166417928189804e-05,
      "loss": 0.8522,
      "step": 955
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.515646744355635e-05,
      "loss": 0.9416,
      "step": 956
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.51465076266654e-05,
      "loss": 0.9227,
      "step": 957
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.513653848121177e-05,
      "loss": 0.885,
      "step": 958
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.5126560010893676e-05,
      "loss": 0.8619,
      "step": 959
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.511657221941283e-05,
      "loss": 0.9174,
      "step": 960
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.5106575110474384e-05,
      "loss": 0.8525,
      "step": 961
    },
    {
      "epoch": 0.74,
      "learning_rate": 5.509656868778695e-05,
      "loss": 0.8293,
      "step": 962
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.5086552955062585e-05,
      "loss": 0.905,
      "step": 963
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.507652791601683e-05,
      "loss": 0.8448,
      "step": 964
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.506649357436866e-05,
      "loss": 0.9456,
      "step": 965
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.505644993384047e-05,
      "loss": 0.8988,
      "step": 966
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.5046396998158165e-05,
      "loss": 0.8796,
      "step": 967
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.5036334771051056e-05,
      "loss": 0.8541,
      "step": 968
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.5026263256251906e-05,
      "loss": 0.9154,
      "step": 969
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.501618245749694e-05,
      "loss": 0.9356,
      "step": 970
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.5006092378525824e-05,
      "loss": 0.9185,
      "step": 971
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.499599302308163e-05,
      "loss": 0.8636,
      "step": 972
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.498588439491093e-05,
      "loss": 0.8768,
      "step": 973
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.49757664977637e-05,
      "loss": 0.8873,
      "step": 974
    },
    {
      "epoch": 0.75,
      "learning_rate": 5.496563933539336e-05,
      "loss": 0.8334,
      "step": 975
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.4955502911556764e-05,
      "loss": 0.7884,
      "step": 976
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.4945357230014216e-05,
      "loss": 0.8446,
      "step": 977
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.493520229452943e-05,
      "loss": 0.8913,
      "step": 978
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.4925038108869576e-05,
      "loss": 0.8677,
      "step": 979
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.491486467680525e-05,
      "loss": 0.9592,
      "step": 980
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.490468200211047e-05,
      "loss": 0.8444,
      "step": 981
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.489449008856268e-05,
      "loss": 0.962,
      "step": 982
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.488428893994278e-05,
      "loss": 0.8356,
      "step": 983
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.4874078560035054e-05,
      "loss": 0.8641,
      "step": 984
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.486385895262725e-05,
      "loss": 0.7904,
      "step": 985
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.48536301215105e-05,
      "loss": 0.8758,
      "step": 986
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.4843392070479405e-05,
      "loss": 0.8741,
      "step": 987
    },
    {
      "epoch": 0.76,
      "learning_rate": 5.483314480333193e-05,
      "loss": 0.8517,
      "step": 988
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.4822888323869506e-05,
      "loss": 0.9177,
      "step": 989
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.481262263589696e-05,
      "loss": 0.8776,
      "step": 990
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.480234774322254e-05,
      "loss": 0.9352,
      "step": 991
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.4792063649657905e-05,
      "loss": 0.8994,
      "step": 992
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.478177035901814e-05,
      "loss": 0.8878,
      "step": 993
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.4771467875121724e-05,
      "loss": 0.8775,
      "step": 994
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.476115620179054e-05,
      "loss": 0.8977,
      "step": 995
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.475083534284993e-05,
      "loss": 1.0301,
      "step": 996
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.4740505302128564e-05,
      "loss": 0.9255,
      "step": 997
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.47301660834586e-05,
      "loss": 0.8594,
      "step": 998
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.471981769067554e-05,
      "loss": 0.8798,
      "step": 999
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.470946012761832e-05,
      "loss": 0.8359,
      "step": 1000
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.8880231380462646,
      "eval_runtime": 14.3483,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 1000
    },
    {
      "epoch": 0.77,
      "learning_rate": 5.469909339812927e-05,
      "loss": 0.8456,
      "step": 1001
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.468871750605412e-05,
      "loss": 0.8645,
      "step": 1002
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.467833245524199e-05,
      "loss": 0.9429,
      "step": 1003
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4667938249545416e-05,
      "loss": 0.976,
      "step": 1004
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4657534892820326e-05,
      "loss": 0.8414,
      "step": 1005
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4647122388926034e-05,
      "loss": 0.8938,
      "step": 1006
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.463670074172524e-05,
      "loss": 0.8265,
      "step": 1007
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4626269955084066e-05,
      "loss": 0.9194,
      "step": 1008
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4615830032871995e-05,
      "loss": 0.889,
      "step": 1009
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.46053809789619e-05,
      "loss": 0.918,
      "step": 1010
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.459492279723007e-05,
      "loss": 0.8926,
      "step": 1011
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.458445549155615e-05,
      "loss": 0.8545,
      "step": 1012
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.457397906582318e-05,
      "loss": 0.8266,
      "step": 1013
    },
    {
      "epoch": 0.78,
      "learning_rate": 5.4563493523917594e-05,
      "loss": 0.8977,
      "step": 1014
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.455299886972919e-05,
      "loss": 0.8406,
      "step": 1015
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.454249510715115e-05,
      "loss": 0.8098,
      "step": 1016
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4531982240080054e-05,
      "loss": 0.893,
      "step": 1017
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.452146027241583e-05,
      "loss": 0.8664,
      "step": 1018
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4510929208061805e-05,
      "loss": 0.8563,
      "step": 1019
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4500389050924665e-05,
      "loss": 0.9148,
      "step": 1020
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.448983980491448e-05,
      "loss": 0.8875,
      "step": 1021
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4479281473944695e-05,
      "loss": 0.9022,
      "step": 1022
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.446871406193211e-05,
      "loss": 0.9037,
      "step": 1023
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4458137572796904e-05,
      "loss": 0.898,
      "step": 1024
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4447552010462624e-05,
      "loss": 0.8346,
      "step": 1025
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.4436957378856184e-05,
      "loss": 0.8174,
      "step": 1026
    },
    {
      "epoch": 0.79,
      "learning_rate": 5.442635368190784e-05,
      "loss": 0.7377,
      "step": 1027
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.441574092355126e-05,
      "loss": 0.8535,
      "step": 1028
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.440511910772342e-05,
      "loss": 0.8878,
      "step": 1029
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.4394488238364676e-05,
      "loss": 0.8778,
      "step": 1030
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.4383848319418764e-05,
      "loss": 0.9867,
      "step": 1031
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.4373199354832754e-05,
      "loss": 0.7847,
      "step": 1032
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.436254134855707e-05,
      "loss": 0.8753,
      "step": 1033
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.4351874304545505e-05,
      "loss": 0.8297,
      "step": 1034
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.434119822675519e-05,
      "loss": 0.8327,
      "step": 1035
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.433051311914661e-05,
      "loss": 0.8878,
      "step": 1036
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.431981898568361e-05,
      "loss": 0.9493,
      "step": 1037
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.430911583033339e-05,
      "loss": 0.8616,
      "step": 1038
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.429840365706645e-05,
      "loss": 0.8094,
      "step": 1039
    },
    {
      "epoch": 0.8,
      "learning_rate": 5.42876824698567e-05,
      "loss": 0.7852,
      "step": 1040
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.427695227268135e-05,
      "loss": 0.8982,
      "step": 1041
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.426621306952097e-05,
      "loss": 0.8993,
      "step": 1042
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.425546486435945e-05,
      "loss": 0.7602,
      "step": 1043
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.424470766118406e-05,
      "loss": 0.8864,
      "step": 1044
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.423394146398537e-05,
      "loss": 0.9181,
      "step": 1045
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.42231662767573e-05,
      "loss": 0.8539,
      "step": 1046
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.4212382103497106e-05,
      "loss": 0.8353,
      "step": 1047
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.4201588948205395e-05,
      "loss": 0.9303,
      "step": 1048
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.419078681488606e-05,
      "loss": 0.8489,
      "step": 1049
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.4179975707546365e-05,
      "loss": 0.9785,
      "step": 1050
    },
    {
      "epoch": 0.81,
      "eval_loss": 0.8838340640068054,
      "eval_runtime": 14.349,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 1050
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.416915563019689e-05,
      "loss": 1.0054,
      "step": 1051
    },
    {
      "epoch": 0.81,
      "learning_rate": 5.415832658685154e-05,
      "loss": 0.916,
      "step": 1052
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.414748858152755e-05,
      "loss": 0.8414,
      "step": 1053
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.413664161824549e-05,
      "loss": 0.7944,
      "step": 1054
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.412578570102923e-05,
      "loss": 0.8821,
      "step": 1055
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.411492083390598e-05,
      "loss": 0.8735,
      "step": 1056
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.410404702090625e-05,
      "loss": 0.9337,
      "step": 1057
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.4093164266063905e-05,
      "loss": 0.8168,
      "step": 1058
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.4082272573416076e-05,
      "loss": 0.9905,
      "step": 1059
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.407137194700326e-05,
      "loss": 0.895,
      "step": 1060
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.406046239086924e-05,
      "loss": 0.8701,
      "step": 1061
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.404954390906112e-05,
      "loss": 0.8583,
      "step": 1062
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.403861650562931e-05,
      "loss": 0.8807,
      "step": 1063
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.402768018462754e-05,
      "loss": 0.8533,
      "step": 1064
    },
    {
      "epoch": 0.82,
      "learning_rate": 5.4016734950112825e-05,
      "loss": 0.9211,
      "step": 1065
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.400578080614552e-05,
      "loss": 0.8886,
      "step": 1066
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.3994817756789244e-05,
      "loss": 0.8251,
      "step": 1067
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.398384580611097e-05,
      "loss": 0.9983,
      "step": 1068
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.397286495818093e-05,
      "loss": 0.9099,
      "step": 1069
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.3961875217072685e-05,
      "loss": 1.0173,
      "step": 1070
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.395087658686307e-05,
      "loss": 0.8843,
      "step": 1071
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.393986907163224e-05,
      "loss": 1.0166,
      "step": 1072
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.3928852675463625e-05,
      "loss": 0.8313,
      "step": 1073
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.391782740244397e-05,
      "loss": 0.8441,
      "step": 1074
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.3906793256663314e-05,
      "loss": 0.8513,
      "step": 1075
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.389575024221496e-05,
      "loss": 0.9339,
      "step": 1076
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.388469836319553e-05,
      "loss": 0.8151,
      "step": 1077
    },
    {
      "epoch": 0.83,
      "learning_rate": 5.387363762370491e-05,
      "loss": 0.8495,
      "step": 1078
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.3862568027846304e-05,
      "loss": 0.9172,
      "step": 1079
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.385148957972617e-05,
      "loss": 0.8647,
      "step": 1080
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.384040228345427e-05,
      "loss": 0.8994,
      "step": 1081
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.3829306143143634e-05,
      "loss": 0.8578,
      "step": 1082
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.38182011629106e-05,
      "loss": 0.8323,
      "step": 1083
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.3807087346874743e-05,
      "loss": 1.0322,
      "step": 1084
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.379596469915895e-05,
      "loss": 0.8803,
      "step": 1085
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.378483322388937e-05,
      "loss": 0.9787,
      "step": 1086
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.3773692925195435e-05,
      "loss": 0.9307,
      "step": 1087
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.376254380720984e-05,
      "loss": 0.8441,
      "step": 1088
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.375138587406855e-05,
      "loss": 0.8948,
      "step": 1089
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.3740219129910835e-05,
      "loss": 0.8514,
      "step": 1090
    },
    {
      "epoch": 0.84,
      "learning_rate": 5.372904357887918e-05,
      "loss": 0.8839,
      "step": 1091
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.371785922511936e-05,
      "loss": 0.8411,
      "step": 1092
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.370666607278043e-05,
      "loss": 0.8117,
      "step": 1093
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.36954641260147e-05,
      "loss": 0.8656,
      "step": 1094
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.3684253388977724e-05,
      "loss": 0.8813,
      "step": 1095
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.3673033865828354e-05,
      "loss": 0.8953,
      "step": 1096
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.366180556072866e-05,
      "loss": 0.8153,
      "step": 1097
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.365056847784399e-05,
      "loss": 0.9304,
      "step": 1098
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.363932262134297e-05,
      "loss": 0.9051,
      "step": 1099
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.362806799539744e-05,
      "loss": 0.7917,
      "step": 1100
    },
    {
      "epoch": 0.85,
      "eval_loss": 0.8823765516281128,
      "eval_runtime": 14.3449,
      "eval_samples_per_second": 5.716,
      "eval_steps_per_second": 5.716,
      "step": 1100
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.361680460418252e-05,
      "loss": 0.8093,
      "step": 1101
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.360553245187656e-05,
      "loss": 0.8427,
      "step": 1102
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.3594251542661194e-05,
      "loss": 0.8185,
      "step": 1103
    },
    {
      "epoch": 0.85,
      "learning_rate": 5.358296188072126e-05,
      "loss": 0.8468,
      "step": 1104
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.3571663470244896e-05,
      "loss": 0.8316,
      "step": 1105
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.356035631542344e-05,
      "loss": 0.9634,
      "step": 1106
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.3549040420451476e-05,
      "loss": 0.8637,
      "step": 1107
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.353771578952688e-05,
      "loss": 0.8595,
      "step": 1108
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.35263824268507e-05,
      "loss": 0.9663,
      "step": 1109
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.351504033662728e-05,
      "loss": 0.9065,
      "step": 1110
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.350368952306417e-05,
      "loss": 0.9395,
      "step": 1111
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.349232999037216e-05,
      "loss": 0.849,
      "step": 1112
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.3480961742765284e-05,
      "loss": 0.8452,
      "step": 1113
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.346958478446081e-05,
      "loss": 0.8252,
      "step": 1114
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.3458199119679216e-05,
      "loss": 0.861,
      "step": 1115
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.344680475264423e-05,
      "loss": 0.8347,
      "step": 1116
    },
    {
      "epoch": 0.86,
      "learning_rate": 5.343540168758282e-05,
      "loss": 0.76,
      "step": 1117
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.342398992872514e-05,
      "loss": 0.8713,
      "step": 1118
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.341256948030461e-05,
      "loss": 0.845,
      "step": 1119
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.3401140346557854e-05,
      "loss": 0.8518,
      "step": 1120
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.338970253172471e-05,
      "loss": 1.0125,
      "step": 1121
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.337825604004826e-05,
      "loss": 0.9063,
      "step": 1122
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.336680087577479e-05,
      "loss": 0.7845,
      "step": 1123
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.3355337043153796e-05,
      "loss": 0.8583,
      "step": 1124
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.334386454643801e-05,
      "loss": 0.8584,
      "step": 1125
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.333238338988336e-05,
      "loss": 0.8493,
      "step": 1126
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.3320893577749e-05,
      "loss": 0.9009,
      "step": 1127
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.330939511429729e-05,
      "loss": 0.8671,
      "step": 1128
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.329788800379378e-05,
      "loss": 0.9104,
      "step": 1129
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.328637225050727e-05,
      "loss": 0.8349,
      "step": 1130
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.327484785870973e-05,
      "loss": 0.8712,
      "step": 1131
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.326331483267635e-05,
      "loss": 0.8756,
      "step": 1132
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.3251773176685506e-05,
      "loss": 0.9156,
      "step": 1133
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.3240222895018806e-05,
      "loss": 0.8102,
      "step": 1134
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.322866399196104e-05,
      "loss": 0.9215,
      "step": 1135
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.321709647180018e-05,
      "loss": 0.8451,
      "step": 1136
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.3205520338827435e-05,
      "loss": 0.809,
      "step": 1137
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.319393559733718e-05,
      "loss": 0.808,
      "step": 1138
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.318234225162697e-05,
      "loss": 0.7634,
      "step": 1139
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.317074030599758e-05,
      "loss": 0.8315,
      "step": 1140
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.315912976475298e-05,
      "loss": 0.8239,
      "step": 1141
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.314751063220032e-05,
      "loss": 0.9905,
      "step": 1142
    },
    {
      "epoch": 0.88,
      "learning_rate": 5.313588291264991e-05,
      "loss": 0.8341,
      "step": 1143
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.312424661041528e-05,
      "loss": 0.8208,
      "step": 1144
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.311260172981312e-05,
      "loss": 0.9058,
      "step": 1145
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.3100948275163325e-05,
      "loss": 0.8294,
      "step": 1146
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.3089286250788975e-05,
      "loss": 0.8013,
      "step": 1147
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.307761566101629e-05,
      "loss": 0.8528,
      "step": 1148
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.306593651017469e-05,
      "loss": 0.9322,
      "step": 1149
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.305424880259679e-05,
      "loss": 0.8404,
      "step": 1150
    },
    {
      "epoch": 0.89,
      "eval_loss": 0.8795799016952515,
      "eval_runtime": 14.3398,
      "eval_samples_per_second": 5.718,
      "eval_steps_per_second": 5.718,
      "step": 1150
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.304255254261834e-05,
      "loss": 0.8116,
      "step": 1151
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.303084773457831e-05,
      "loss": 0.8656,
      "step": 1152
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.30191343828188e-05,
      "loss": 0.8394,
      "step": 1153
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.3007412491685085e-05,
      "loss": 0.8543,
      "step": 1154
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.299568206552564e-05,
      "loss": 0.8538,
      "step": 1155
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.298394310869207e-05,
      "loss": 0.8461,
      "step": 1156
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.297219562553917e-05,
      "loss": 0.9063,
      "step": 1157
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.296043962042487e-05,
      "loss": 0.8471,
      "step": 1158
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.294867509771029e-05,
      "loss": 0.9213,
      "step": 1159
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.293690206175968e-05,
      "loss": 0.8441,
      "step": 1160
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2925120516940495e-05,
      "loss": 0.8693,
      "step": 1161
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.29133304676233e-05,
      "loss": 0.8417,
      "step": 1162
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.290153191818183e-05,
      "loss": 0.8573,
      "step": 1163
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2889724872992984e-05,
      "loss": 0.8977,
      "step": 1164
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.287790933643679e-05,
      "loss": 0.8754,
      "step": 1165
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2866085312896455e-05,
      "loss": 0.8506,
      "step": 1166
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2854252806758315e-05,
      "loss": 0.8955,
      "step": 1167
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.284241182241186e-05,
      "loss": 0.8315,
      "step": 1168
    },
    {
      "epoch": 0.9,
      "learning_rate": 5.2830562364249705e-05,
      "loss": 0.9084,
      "step": 1169
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.281870443666764e-05,
      "loss": 0.8364,
      "step": 1170
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.280683804406459e-05,
      "loss": 0.8322,
      "step": 1171
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.2794963190842605e-05,
      "loss": 0.9101,
      "step": 1172
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.278307988140688e-05,
      "loss": 0.839,
      "step": 1173
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.277118812016575e-05,
      "loss": 0.7663,
      "step": 1174
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.275928791153069e-05,
      "loss": 0.9053,
      "step": 1175
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.2747379259916293e-05,
      "loss": 0.8727,
      "step": 1176
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.27354621697403e-05,
      "loss": 0.8697,
      "step": 1177
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.272353664542358e-05,
      "loss": 0.9178,
      "step": 1178
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.271160269139011e-05,
      "loss": 0.8797,
      "step": 1179
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.2699660312067026e-05,
      "loss": 0.8795,
      "step": 1180
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.268770951188458e-05,
      "loss": 0.9538,
      "step": 1181
    },
    {
      "epoch": 0.91,
      "learning_rate": 5.2675750295276124e-05,
      "loss": 0.8571,
      "step": 1182
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.2663782666678165e-05,
      "loss": 0.7752,
      "step": 1183
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.265180663053032e-05,
      "loss": 0.8515,
      "step": 1184
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.263982219127531e-05,
      "loss": 0.9467,
      "step": 1185
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.262782935335898e-05,
      "loss": 0.8506,
      "step": 1186
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.261582812123031e-05,
      "loss": 0.9126,
      "step": 1187
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.260381849934138e-05,
      "loss": 0.8524,
      "step": 1188
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.2591800492147366e-05,
      "loss": 0.9179,
      "step": 1189
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.2579774104106587e-05,
      "loss": 0.8502,
      "step": 1190
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.256773933968044e-05,
      "loss": 0.8448,
      "step": 1191
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.2555696203333455e-05,
      "loss": 0.776,
      "step": 1192
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.254364469953325e-05,
      "loss": 0.8378,
      "step": 1193
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.2531584832750555e-05,
      "loss": 0.8589,
      "step": 1194
    },
    {
      "epoch": 0.92,
      "learning_rate": 5.251951660745921e-05,
      "loss": 0.8958,
      "step": 1195
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.2507440028136125e-05,
      "loss": 0.8813,
      "step": 1196
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.249535509926135e-05,
      "loss": 0.8846,
      "step": 1197
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.248326182531801e-05,
      "loss": 0.86,
      "step": 1198
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.247116021079231e-05,
      "loss": 0.8941,
      "step": 1199
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.245905026017361e-05,
      "loss": 0.881,
      "step": 1200
    },
    {
      "epoch": 0.93,
      "eval_loss": 0.87925785779953,
      "eval_runtime": 14.3586,
      "eval_samples_per_second": 5.711,
      "eval_steps_per_second": 5.711,
      "step": 1200
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.244693197795427e-05,
      "loss": 0.8463,
      "step": 1201
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.243480536862983e-05,
      "loss": 0.8611,
      "step": 1202
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.242267043669886e-05,
      "loss": 0.9424,
      "step": 1203
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.2410527186663046e-05,
      "loss": 0.8505,
      "step": 1204
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.239837562302715e-05,
      "loss": 0.8556,
      "step": 1205
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.238621575029902e-05,
      "loss": 0.9157,
      "step": 1206
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.2374047572989585e-05,
      "loss": 0.8603,
      "step": 1207
    },
    {
      "epoch": 0.93,
      "learning_rate": 5.2361871095612854e-05,
      "loss": 0.8713,
      "step": 1208
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.234968632268592e-05,
      "loss": 0.866,
      "step": 1209
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.2337493258728944e-05,
      "loss": 0.8145,
      "step": 1210
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.2325291908265177e-05,
      "loss": 0.8519,
      "step": 1211
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.2313082275820934e-05,
      "loss": 0.8288,
      "step": 1212
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.230086436592559e-05,
      "loss": 0.8545,
      "step": 1213
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.228863818311163e-05,
      "loss": 0.9122,
      "step": 1214
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.2276403731914564e-05,
      "loss": 0.8539,
      "step": 1215
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.2264161016873e-05,
      "loss": 0.7631,
      "step": 1216
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.225191004252858e-05,
      "loss": 0.8867,
      "step": 1217
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.223965081342606e-05,
      "loss": 0.9395,
      "step": 1218
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.222738333411321e-05,
      "loss": 0.8129,
      "step": 1219
    },
    {
      "epoch": 0.94,
      "learning_rate": 5.221510760914088e-05,
      "loss": 0.823,
      "step": 1220
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.220282364306297e-05,
      "loss": 0.8681,
      "step": 1221
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.2190531440436464e-05,
      "loss": 0.829,
      "step": 1222
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.2178231005821365e-05,
      "loss": 0.837,
      "step": 1223
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.216592234378076e-05,
      "loss": 0.8937,
      "step": 1224
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.2153605458880765e-05,
      "loss": 0.8753,
      "step": 1225
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.214128035569056e-05,
      "loss": 0.8563,
      "step": 1226
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.212894703878237e-05,
      "loss": 0.8824,
      "step": 1227
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.211660551273147e-05,
      "loss": 0.8809,
      "step": 1228
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.210425578211617e-05,
      "loss": 0.9764,
      "step": 1229
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.209189785151784e-05,
      "loss": 0.8432,
      "step": 1230
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.207953172552088e-05,
      "loss": 0.8064,
      "step": 1231
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.2067157408712734e-05,
      "loss": 0.7645,
      "step": 1232
    },
    {
      "epoch": 0.95,
      "learning_rate": 5.205477490568388e-05,
      "loss": 0.891,
      "step": 1233
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.204238422102784e-05,
      "loss": 0.7995,
      "step": 1234
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.2029985359341165e-05,
      "loss": 0.8309,
      "step": 1235
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.201757832522345e-05,
      "loss": 1.0696,
      "step": 1236
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.200516312327731e-05,
      "loss": 0.8111,
      "step": 1237
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.199273975810839e-05,
      "loss": 0.8308,
      "step": 1238
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.198030823432537e-05,
      "loss": 0.8864,
      "step": 1239
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.196786855653996e-05,
      "loss": 0.8606,
      "step": 1240
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.195542072936688e-05,
      "loss": 0.797,
      "step": 1241
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.194296475742389e-05,
      "loss": 0.8634,
      "step": 1242
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.193050064533176e-05,
      "loss": 0.8548,
      "step": 1243
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.191802839771428e-05,
      "loss": 0.8668,
      "step": 1244
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.1905548019198264e-05,
      "loss": 0.8793,
      "step": 1245
    },
    {
      "epoch": 0.96,
      "learning_rate": 5.189305951441353e-05,
      "loss": 0.8059,
      "step": 1246
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.188056288799294e-05,
      "loss": 0.8551,
      "step": 1247
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.186805814457233e-05,
      "loss": 0.8569,
      "step": 1248
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.1855545288790586e-05,
      "loss": 0.8936,
      "step": 1249
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.184302432528956e-05,
      "loss": 0.925,
      "step": 1250
    },
    {
      "epoch": 0.97,
      "eval_loss": 0.8768937587738037,
      "eval_runtime": 14.3545,
      "eval_samples_per_second": 5.712,
      "eval_steps_per_second": 5.712,
      "step": 1250
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.1830495258714156e-05,
      "loss": 0.79,
      "step": 1251
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.181795809371225e-05,
      "loss": 0.8115,
      "step": 1252
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.180541283493474e-05,
      "loss": 0.8788,
      "step": 1253
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.179285948703552e-05,
      "loss": 0.8397,
      "step": 1254
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.178029805467149e-05,
      "loss": 0.8189,
      "step": 1255
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.1767728542502545e-05,
      "loss": 0.9749,
      "step": 1256
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.1755150955191586e-05,
      "loss": 0.8964,
      "step": 1257
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.174256529740449e-05,
      "loss": 0.8835,
      "step": 1258
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.172997157381014e-05,
      "loss": 0.7787,
      "step": 1259
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.171736978908042e-05,
      "loss": 0.9683,
      "step": 1260
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.1704759947890185e-05,
      "loss": 0.906,
      "step": 1261
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.16921420549173e-05,
      "loss": 0.8747,
      "step": 1262
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.167951611484259e-05,
      "loss": 0.7947,
      "step": 1263
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.16668821323499e-05,
      "loss": 0.8383,
      "step": 1264
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.1654240112126034e-05,
      "loss": 0.8896,
      "step": 1265
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.164159005886078e-05,
      "loss": 0.8375,
      "step": 1266
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.162893197724692e-05,
      "loss": 0.8575,
      "step": 1267
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.1616265871980175e-05,
      "loss": 0.8488,
      "step": 1268
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.16035917477593e-05,
      "loss": 0.8398,
      "step": 1269
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.159090960928599e-05,
      "loss": 0.8146,
      "step": 1270
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.157821946126491e-05,
      "loss": 0.9755,
      "step": 1271
    },
    {
      "epoch": 0.98,
      "learning_rate": 5.156552130840372e-05,
      "loss": 0.9845,
      "step": 1272
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.1552815155413015e-05,
      "loss": 0.8869,
      "step": 1273
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.154010100700639e-05,
      "loss": 0.8351,
      "step": 1274
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.152737886790041e-05,
      "loss": 0.8805,
      "step": 1275
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.151464874281455e-05,
      "loss": 0.9241,
      "step": 1276
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.150191063647132e-05,
      "loss": 0.8213,
      "step": 1277
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.148916455359613e-05,
      "loss": 0.828,
      "step": 1278
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.14764104989174e-05,
      "loss": 0.8004,
      "step": 1279
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.1463648477166474e-05,
      "loss": 0.7979,
      "step": 1280
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.145087849307765e-05,
      "loss": 0.771,
      "step": 1281
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.14381005513882e-05,
      "loss": 0.9042,
      "step": 1282
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.142531465683834e-05,
      "loss": 0.7922,
      "step": 1283
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.141252081417123e-05,
      "loss": 0.827,
      "step": 1284
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.139971902813297e-05,
      "loss": 0.8541,
      "step": 1285
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.138690930347265e-05,
      "loss": 0.9865,
      "step": 1286
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.137409164494225e-05,
      "loss": 0.885,
      "step": 1287
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.136126605729673e-05,
      "loss": 0.8943,
      "step": 1288
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.134843254529397e-05,
      "loss": 0.8419,
      "step": 1289
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1335591113694806e-05,
      "loss": 0.8346,
      "step": 1290
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1322741767263e-05,
      "loss": 0.8761,
      "step": 1291
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1309884510765256e-05,
      "loss": 0.8206,
      "step": 1292
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.129701934897121e-05,
      "loss": 0.8221,
      "step": 1293
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1284146286653444e-05,
      "loss": 0.8702,
      "step": 1294
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.127126532858745e-05,
      "loss": 0.8543,
      "step": 1295
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1258376479551645e-05,
      "loss": 0.8241,
      "step": 1296
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.12454797443274e-05,
      "loss": 0.8338,
      "step": 1297
    },
    {
      "epoch": 1.0,
      "learning_rate": 5.1232575127699005e-05,
      "loss": 1.1177,
      "step": 1298
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.1219662634453654e-05,
      "loss": 0.8439,
      "step": 1299
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.120674226938148e-05,
      "loss": 0.8789,
      "step": 1300
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.8753229975700378,
      "eval_runtime": 14.3493,
      "eval_samples_per_second": 5.715,
      "eval_steps_per_second": 5.715,
      "step": 1300
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.119381403727554e-05,
      "loss": 0.8942,
      "step": 1301
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.118087794293178e-05,
      "loss": 0.9067,
      "step": 1302
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.1167933991149104e-05,
      "loss": 0.8373,
      "step": 1303
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.11549821867293e-05,
      "loss": 0.8963,
      "step": 1304
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.114202253447708e-05,
      "loss": 0.8233,
      "step": 1305
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.112905503920007e-05,
      "loss": 0.8927,
      "step": 1306
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.11160797057088e-05,
      "loss": 0.7887,
      "step": 1307
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.110309653881672e-05,
      "loss": 0.8514,
      "step": 1308
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.109010554334016e-05,
      "loss": 0.8772,
      "step": 1309
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.107710672409838e-05,
      "loss": 0.829,
      "step": 1310
    },
    {
      "epoch": 1.01,
      "learning_rate": 5.106410008591354e-05,
      "loss": 0.8759,
      "step": 1311
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.105108563361068e-05,
      "loss": 1.0493,
      "step": 1312
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.103806337201776e-05,
      "loss": 0.8611,
      "step": 1313
    },
    {
      "epoch": 1.02,
      "learning_rate": 5.102503330596562e-05,
      "loss": 0.8037,
      "step": 1314
    }
  ],
  "logging_steps": 1,
  "max_steps": 5168,
  "num_train_epochs": 4,
  "save_steps": 500,
  "total_flos": 3.9533226379444224e+17,
  "trial_name": null,
  "trial_params": null
}