{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 664,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2.8347554024716023e-06,
      "loss": 0.8007,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 5.6695108049432045e-06,
      "loss": 0.6499,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 7.327736414105801e-06,
      "loss": 0.553,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.504266207414806e-06,
      "loss": 0.5237,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 9.41685361360415e-06,
      "loss": 0.5046,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.0162491816577402e-05,
      "loss": 0.4709,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.0792919934429639e-05,
      "loss": 0.4447,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.1339021609886409e-05,
      "loss": 0.4447,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.1820717425739998e-05,
      "loss": 0.4335,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.225160901607575e-05,
      "loss": 0.4261,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2641397872884761e-05,
      "loss": 0.4484,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.2997247219049005e-05,
      "loss": 0.4257,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.3324596884992558e-05,
      "loss": 0.4204,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.362767533690124e-05,
      "loss": 0.4223,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.3909834625238347e-05,
      "loss": 0.421,
      "step": 30
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.4173777012358013e-05,
      "loss": 0.4087,
      "step": 32
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.4421712774107928e-05,
      "loss": 0.3996,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.4655472828211601e-05,
      "loss": 0.4163,
      "step": 36
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.4876590870513565e-05,
      "loss": 0.3931,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.5086364418547353e-05,
      "loss": 0.3902,
      "step": 40
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.5285900946063837e-05,
      "loss": 0.3775,
      "step": 42
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.547615327535636e-05,
      "loss": 0.384,
      "step": 44
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.5657947095819226e-05,
      "loss": 0.3891,
      "step": 46
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.583200262152061e-05,
      "loss": 0.3965,
      "step": 48
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.5998951824736692e-05,
      "loss": 0.385,
      "step": 50
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.615935228746416e-05,
      "loss": 0.3821,
      "step": 52
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.6313698437374197e-05,
      "loss": 0.3772,
      "step": 54
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.6462430739372846e-05,
      "loss": 0.3771,
      "step": 56
    },
    {
      "epoch": 0.17,
      "learning_rate": 1.6605943273513858e-05,
      "loss": 0.3998,
      "step": 58
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.674459002770995e-05,
      "loss": 0.3811,
      "step": 60
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.6878690158245678e-05,
      "loss": 0.3877,
      "step": 62
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.700853241482961e-05,
      "loss": 0.3871,
      "step": 64
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.713437888451896e-05,
      "loss": 0.3932,
      "step": 66
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.725646817657953e-05,
      "loss": 0.3849,
      "step": 68
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7375018145562187e-05,
      "loss": 0.3922,
      "step": 70
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7490228230683203e-05,
      "loss": 0.3654,
      "step": 72
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.760228147461214e-05,
      "loss": 0.3612,
      "step": 74
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7711346272985167e-05,
      "loss": 0.3807,
      "step": 76
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7817577896626754e-05,
      "loss": 0.357,
      "step": 78
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.792111982101895e-05,
      "loss": 0.3771,
      "step": 80
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.802210489158528e-05,
      "loss": 0.3793,
      "step": 82
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.812065634853544e-05,
      "loss": 0.3694,
      "step": 84
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.8216888731104615e-05,
      "loss": 0.3754,
      "step": 86
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8310908677827968e-05,
      "loss": 0.3613,
      "step": 88
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.8402815636872544e-05,
      "loss": 0.3479,
      "step": 90
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.849270249829083e-05,
      "loss": 0.3606,
      "step": 92
    },
    {
      "epoch": 0.28,
      "learning_rate": 1.8580656158273317e-05,
      "loss": 0.374,
      "step": 94
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.866675802399221e-05,
      "loss": 0.3794,
      "step": 96
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.8751084466387678e-05,
      "loss": 0.3545,
      "step": 98
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.88337072272083e-05,
      "loss": 0.3767,
      "step": 100
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.8914693785742126e-05,
      "loss": 0.3766,
      "step": 102
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.899410768993576e-05,
      "loss": 0.363,
      "step": 104
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.9072008855972226e-05,
      "loss": 0.3742,
      "step": 106
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.91484538398458e-05,
      "loss": 0.3649,
      "step": 108
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.922349608401731e-05,
      "loss": 0.3768,
      "step": 110
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9297186141844446e-05,
      "loss": 0.3702,
      "step": 112
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.9369571882147768e-05,
      "loss": 0.3567,
      "step": 114
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.944069867598546e-05,
      "loss": 0.3682,
      "step": 116
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9510609567462104e-05,
      "loss": 0.3748,
      "step": 118
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.9579345430181553e-05,
      "loss": 0.3548,
      "step": 120
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9646945110768043e-05,
      "loss": 0.3495,
      "step": 122
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.9713445560717278e-05,
      "loss": 0.3584,
      "step": 124
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.977888195769804e-05,
      "loss": 0.3729,
      "step": 126
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.9843287817301215e-05,
      "loss": 0.3598,
      "step": 128
    },
    {
      "epoch": 0.39,
      "learning_rate": 1.99066950961251e-05,
      "loss": 0.3806,
      "step": 130
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.9969134286990563e-05,
      "loss": 0.3419,
      "step": 132
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.3531,
      "step": 134
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.3563,
      "step": 136
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.3623,
      "step": 138
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.3661,
      "step": 140
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.3496,
      "step": 142
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.3607,
      "step": 144
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.3496,
      "step": 146
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.3709,
      "step": 148
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.3473,
      "step": 150
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.3781,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.3534,
      "step": 154
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.3645,
      "step": 156
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.3506,
      "step": 158
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.3483,
      "step": 160
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.3523,
      "step": 162
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.3791,
      "step": 164
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.3667,
      "step": 166
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.3578,
      "step": 168
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.3547,
      "step": 170
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.3576,
      "step": 172
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.3221,
      "step": 174
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.3512,
      "step": 176
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.3474,
      "step": 178
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.3816,
      "step": 180
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.3482,
      "step": 182
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.3663,
      "step": 184
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.3549,
      "step": 186
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.3389,
      "step": 188
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.3543,
      "step": 190
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.3492,
      "step": 192
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.3515,
      "step": 194
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.3474,
      "step": 196
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.349,
      "step": 198
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.3488,
      "step": 200
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.3352,
      "step": 202
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.3305,
      "step": 204
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 0.3491,
      "step": 206
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.3646,
      "step": 208
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.3487,
      "step": 210
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.3524,
      "step": 212
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.3748,
      "step": 214
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.3571,
      "step": 216
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.3761,
      "step": 218
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.3586,
      "step": 220
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.3596,
      "step": 222
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.3572,
      "step": 224
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.3458,
      "step": 226
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.3365,
      "step": 228
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.3512,
      "step": 230
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.35,
      "step": 232
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.3686,
      "step": 234
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.3427,
      "step": 236
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.3291,
      "step": 238
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.3486,
      "step": 240
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.3393,
      "step": 242
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.3567,
      "step": 244
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.3416,
      "step": 246
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.3506,
      "step": 248
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.3403,
      "step": 250
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.3536,
      "step": 252
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.3515,
      "step": 254
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.3577,
      "step": 256
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.3412,
      "step": 258
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.3422,
      "step": 260
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.3413,
      "step": 262
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.3219,
      "step": 264
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.3416,
      "step": 266
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.3615,
      "step": 268
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.3479,
      "step": 270
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.3506,
      "step": 272
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.3477,
      "step": 274
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.3612,
      "step": 276
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.3618,
      "step": 278
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.3427,
      "step": 280
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.3492,
      "step": 282
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.3191,
      "step": 284
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.3429,
      "step": 286
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.3377,
      "step": 288
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.3404,
      "step": 290
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.3311,
      "step": 292
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.3406,
      "step": 294
    },
    {
      "epoch": 0.89,
      "learning_rate": 2e-05,
      "loss": 0.3499,
      "step": 296
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.3452,
      "step": 298
    },
    {
      "epoch": 0.9,
      "learning_rate": 2e-05,
      "loss": 0.3483,
      "step": 300
    },
    {
      "epoch": 0.91,
      "learning_rate": 2e-05,
      "loss": 0.3513,
      "step": 302
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 0.3082,
      "step": 304
    },
    {
      "epoch": 0.92,
      "learning_rate": 2e-05,
      "loss": 0.3401,
      "step": 306
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.3345,
      "step": 308
    },
    {
      "epoch": 0.93,
      "learning_rate": 2e-05,
      "loss": 0.3387,
      "step": 310
    },
    {
      "epoch": 0.94,
      "learning_rate": 2e-05,
      "loss": 0.3428,
      "step": 312
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 0.3451,
      "step": 314
    },
    {
      "epoch": 0.95,
      "learning_rate": 2e-05,
      "loss": 0.3438,
      "step": 316
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.3402,
      "step": 318
    },
    {
      "epoch": 0.96,
      "learning_rate": 2e-05,
      "loss": 0.3523,
      "step": 320
    },
    {
      "epoch": 0.97,
      "learning_rate": 2e-05,
      "loss": 0.3252,
      "step": 322
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.3417,
      "step": 324
    },
    {
      "epoch": 0.98,
      "learning_rate": 2e-05,
      "loss": 0.3582,
      "step": 326
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 0.3352,
      "step": 328
    },
    {
      "epoch": 0.99,
      "learning_rate": 2e-05,
      "loss": 0.3348,
      "step": 330
    },
    {
      "epoch": 1.0,
      "learning_rate": 2e-05,
      "loss": 0.3502,
      "step": 332
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 0.3353,
      "step": 334
    },
    {
      "epoch": 1.01,
      "learning_rate": 2e-05,
      "loss": 0.3185,
      "step": 336
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.3119,
      "step": 338
    },
    {
      "epoch": 1.02,
      "learning_rate": 2e-05,
      "loss": 0.3087,
      "step": 340
    },
    {
      "epoch": 1.03,
      "learning_rate": 2e-05,
      "loss": 0.3058,
      "step": 342
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.2902,
      "step": 344
    },
    {
      "epoch": 1.04,
      "learning_rate": 2e-05,
      "loss": 0.2726,
      "step": 346
    },
    {
      "epoch": 1.05,
      "learning_rate": 2e-05,
      "loss": 0.2851,
      "step": 348
    },
    {
      "epoch": 1.05,
      "learning_rate": 2e-05,
      "loss": 0.2688,
      "step": 350
    },
    {
      "epoch": 1.06,
      "learning_rate": 2e-05,
      "loss": 0.2704,
      "step": 352
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.2833,
      "step": 354
    },
    {
      "epoch": 1.07,
      "learning_rate": 2e-05,
      "loss": 0.2721,
      "step": 356
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 0.2646,
      "step": 358
    },
    {
      "epoch": 1.08,
      "learning_rate": 2e-05,
      "loss": 0.2722,
      "step": 360
    },
    {
      "epoch": 1.09,
      "learning_rate": 2e-05,
      "loss": 0.2765,
      "step": 362
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.2665,
      "step": 364
    },
    {
      "epoch": 1.1,
      "learning_rate": 2e-05,
      "loss": 0.2549,
      "step": 366
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.2596,
      "step": 368
    },
    {
      "epoch": 1.11,
      "learning_rate": 2e-05,
      "loss": 0.2546,
      "step": 370
    },
    {
      "epoch": 1.12,
      "learning_rate": 2e-05,
      "loss": 0.2492,
      "step": 372
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.242,
      "step": 374
    },
    {
      "epoch": 1.13,
      "learning_rate": 2e-05,
      "loss": 0.2478,
      "step": 376
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.2518,
      "step": 378
    },
    {
      "epoch": 1.14,
      "learning_rate": 2e-05,
      "loss": 0.2561,
      "step": 380
    },
    {
      "epoch": 1.15,
      "learning_rate": 2e-05,
      "loss": 0.2409,
      "step": 382
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.2472,
      "step": 384
    },
    {
      "epoch": 1.16,
      "learning_rate": 2e-05,
      "loss": 0.2388,
      "step": 386
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.2368,
      "step": 388
    },
    {
      "epoch": 1.17,
      "learning_rate": 2e-05,
      "loss": 0.2529,
      "step": 390
    },
    {
      "epoch": 1.18,
      "learning_rate": 2e-05,
      "loss": 0.2338,
      "step": 392
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.2383,
      "step": 394
    },
    {
      "epoch": 1.19,
      "learning_rate": 2e-05,
      "loss": 0.2487,
      "step": 396
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.2543,
      "step": 398
    },
    {
      "epoch": 1.2,
      "learning_rate": 2e-05,
      "loss": 0.2434,
      "step": 400
    },
    {
      "epoch": 1.21,
      "learning_rate": 2e-05,
      "loss": 0.247,
      "step": 402
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.2271,
      "step": 404
    },
    {
      "epoch": 1.22,
      "learning_rate": 2e-05,
      "loss": 0.2239,
      "step": 406
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 0.244,
      "step": 408
    },
    {
      "epoch": 1.23,
      "learning_rate": 2e-05,
      "loss": 0.2262,
      "step": 410
    },
    {
      "epoch": 1.24,
      "learning_rate": 2e-05,
      "loss": 0.2394,
      "step": 412
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.2443,
      "step": 414
    },
    {
      "epoch": 1.25,
      "learning_rate": 2e-05,
      "loss": 0.2356,
      "step": 416
    },
    {
      "epoch": 1.26,
      "learning_rate": 2e-05,
      "loss": 0.2393,
      "step": 418
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 0.2292,
      "step": 420
    },
    {
      "epoch": 1.27,
      "learning_rate": 2e-05,
      "loss": 0.2165,
      "step": 422
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.2232,
      "step": 424
    },
    {
      "epoch": 1.28,
      "learning_rate": 2e-05,
      "loss": 0.2356,
      "step": 426
    },
    {
      "epoch": 1.29,
      "learning_rate": 2e-05,
      "loss": 0.241,
      "step": 428
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.2268,
      "step": 430
    },
    {
      "epoch": 1.3,
      "learning_rate": 2e-05,
      "loss": 0.2375,
      "step": 432
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 0.2361,
      "step": 434
    },
    {
      "epoch": 1.31,
      "learning_rate": 2e-05,
      "loss": 0.2265,
      "step": 436
    },
    {
      "epoch": 1.32,
      "learning_rate": 2e-05,
      "loss": 0.2294,
      "step": 438
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.22,
      "step": 440
    },
    {
      "epoch": 1.33,
      "learning_rate": 2e-05,
      "loss": 0.2343,
      "step": 442
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 0.2351,
      "step": 444
    },
    {
      "epoch": 1.34,
      "learning_rate": 2e-05,
      "loss": 0.2165,
      "step": 446
    },
    {
      "epoch": 1.35,
      "learning_rate": 2e-05,
      "loss": 0.2303,
      "step": 448
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.2304,
      "step": 450
    },
    {
      "epoch": 1.36,
      "learning_rate": 2e-05,
      "loss": 0.2137,
      "step": 452
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.2173,
      "step": 454
    },
    {
      "epoch": 1.37,
      "learning_rate": 2e-05,
      "loss": 0.2244,
      "step": 456
    },
    {
      "epoch": 1.38,
      "learning_rate": 2e-05,
      "loss": 0.2236,
      "step": 458
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.2222,
      "step": 460
    },
    {
      "epoch": 1.39,
      "learning_rate": 2e-05,
      "loss": 0.2362,
      "step": 462
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.2108,
      "step": 464
    },
    {
      "epoch": 1.4,
      "learning_rate": 2e-05,
      "loss": 0.2179,
      "step": 466
    },
    {
      "epoch": 1.41,
      "learning_rate": 2e-05,
      "loss": 0.2332,
      "step": 468
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.2297,
      "step": 470
    },
    {
      "epoch": 1.42,
      "learning_rate": 2e-05,
      "loss": 0.2302,
      "step": 472
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.222,
      "step": 474
    },
    {
      "epoch": 1.43,
      "learning_rate": 2e-05,
      "loss": 0.2193,
      "step": 476
    },
    {
      "epoch": 1.44,
      "learning_rate": 2e-05,
      "loss": 0.2145,
      "step": 478
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.2294,
      "step": 480
    },
    {
      "epoch": 1.45,
      "learning_rate": 2e-05,
      "loss": 0.2059,
      "step": 482
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.2363,
      "step": 484
    },
    {
      "epoch": 1.46,
      "learning_rate": 2e-05,
      "loss": 0.2179,
      "step": 486
    },
    {
      "epoch": 1.47,
      "learning_rate": 2e-05,
      "loss": 0.2182,
      "step": 488
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.2129,
      "step": 490
    },
    {
      "epoch": 1.48,
      "learning_rate": 2e-05,
      "loss": 0.2073,
      "step": 492
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 0.2153,
      "step": 494
    },
    {
      "epoch": 1.49,
      "learning_rate": 2e-05,
      "loss": 0.228,
      "step": 496
    },
    {
      "epoch": 1.5,
      "learning_rate": 2e-05,
      "loss": 0.228,
      "step": 498
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 0.2124,
      "step": 500
    },
    {
      "epoch": 1.51,
      "learning_rate": 2e-05,
      "loss": 0.2209,
      "step": 502
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.2139,
      "step": 504
    },
    {
      "epoch": 1.52,
      "learning_rate": 2e-05,
      "loss": 0.2028,
      "step": 506
    },
    {
      "epoch": 1.53,
      "learning_rate": 2e-05,
      "loss": 0.2094,
      "step": 508
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.2033,
      "step": 510
    },
    {
      "epoch": 1.54,
      "learning_rate": 2e-05,
      "loss": 0.2388,
      "step": 512
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.2137,
      "step": 514
    },
    {
      "epoch": 1.55,
      "learning_rate": 2e-05,
      "loss": 0.228,
      "step": 516
    },
    {
      "epoch": 1.56,
      "learning_rate": 2e-05,
      "loss": 0.2143,
      "step": 518
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.2016,
      "step": 520
    },
    {
      "epoch": 1.57,
      "learning_rate": 2e-05,
      "loss": 0.2113,
      "step": 522
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.2071,
      "step": 524
    },
    {
      "epoch": 1.58,
      "learning_rate": 2e-05,
      "loss": 0.2201,
      "step": 526
    },
    {
      "epoch": 1.59,
      "learning_rate": 2e-05,
      "loss": 0.2159,
      "step": 528
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.2143,
      "step": 530
    },
    {
      "epoch": 1.6,
      "learning_rate": 2e-05,
      "loss": 0.2124,
      "step": 532
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.2006,
      "step": 534
    },
    {
      "epoch": 1.61,
      "learning_rate": 2e-05,
      "loss": 0.2016,
      "step": 536
    },
    {
      "epoch": 1.62,
      "learning_rate": 2e-05,
      "loss": 0.2144,
      "step": 538
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.2182,
      "step": 540
    },
    {
      "epoch": 1.63,
      "learning_rate": 2e-05,
      "loss": 0.2139,
      "step": 542
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-05,
      "loss": 0.2147,
      "step": 544
    },
    {
      "epoch": 1.64,
      "learning_rate": 2e-05,
      "loss": 0.2333,
      "step": 546
    },
    {
      "epoch": 1.65,
      "learning_rate": 2e-05,
      "loss": 0.2154,
      "step": 548
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.2197,
      "step": 550
    },
    {
      "epoch": 1.66,
      "learning_rate": 2e-05,
      "loss": 0.2231,
      "step": 552
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.2266,
      "step": 554
    },
    {
      "epoch": 1.67,
      "learning_rate": 2e-05,
      "loss": 0.2207,
      "step": 556
    },
    {
      "epoch": 1.68,
      "learning_rate": 2e-05,
      "loss": 0.2131,
      "step": 558
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.2104,
      "step": 560
    },
    {
      "epoch": 1.69,
      "learning_rate": 2e-05,
      "loss": 0.2196,
      "step": 562
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.2138,
      "step": 564
    },
    {
      "epoch": 1.7,
      "learning_rate": 2e-05,
      "loss": 0.2285,
      "step": 566
    },
    {
      "epoch": 1.71,
      "learning_rate": 2e-05,
      "loss": 0.206,
      "step": 568
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 0.1989,
      "step": 570
    },
    {
      "epoch": 1.72,
      "learning_rate": 2e-05,
      "loss": 0.2141,
      "step": 572
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 0.2101,
      "step": 574
    },
    {
      "epoch": 1.73,
      "learning_rate": 2e-05,
      "loss": 0.2141,
      "step": 576
    },
    {
      "epoch": 1.74,
      "learning_rate": 2e-05,
      "loss": 0.206,
      "step": 578
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.2195,
      "step": 580
    },
    {
      "epoch": 1.75,
      "learning_rate": 2e-05,
      "loss": 0.2062,
      "step": 582
    },
    {
      "epoch": 1.76,
      "learning_rate": 2e-05,
      "loss": 0.2235,
      "step": 584
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.2276,
      "step": 586
    },
    {
      "epoch": 1.77,
      "learning_rate": 2e-05,
      "loss": 0.2221,
      "step": 588
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.2144,
      "step": 590
    },
    {
      "epoch": 1.78,
      "learning_rate": 2e-05,
      "loss": 0.1995,
      "step": 592
    },
    {
      "epoch": 1.79,
      "learning_rate": 2e-05,
      "loss": 0.2009,
      "step": 594
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.1959,
      "step": 596
    },
    {
      "epoch": 1.8,
      "learning_rate": 2e-05,
      "loss": 0.2062,
      "step": 598
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.2125,
      "step": 600
    },
    {
      "epoch": 1.81,
      "learning_rate": 2e-05,
      "loss": 0.2139,
      "step": 602
    },
    {
      "epoch": 1.82,
      "learning_rate": 2e-05,
      "loss": 0.2176,
      "step": 604
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.2138,
      "step": 606
    },
    {
      "epoch": 1.83,
      "learning_rate": 2e-05,
      "loss": 0.2189,
      "step": 608
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.2224,
      "step": 610
    },
    {
      "epoch": 1.84,
      "learning_rate": 2e-05,
      "loss": 0.2079,
      "step": 612
    },
    {
      "epoch": 1.85,
      "learning_rate": 2e-05,
      "loss": 0.2109,
      "step": 614
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.1944,
      "step": 616
    },
    {
      "epoch": 1.86,
      "learning_rate": 2e-05,
      "loss": 0.2156,
      "step": 618
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.2048,
      "step": 620
    },
    {
      "epoch": 1.87,
      "learning_rate": 2e-05,
      "loss": 0.2131,
      "step": 622
    },
    {
      "epoch": 1.88,
      "learning_rate": 2e-05,
      "loss": 0.1977,
      "step": 624
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.215,
      "step": 626
    },
    {
      "epoch": 1.89,
      "learning_rate": 2e-05,
      "loss": 0.2144,
      "step": 628
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.208,
      "step": 630
    },
    {
      "epoch": 1.9,
      "learning_rate": 2e-05,
      "loss": 0.2149,
      "step": 632
    },
    {
      "epoch": 1.91,
      "learning_rate": 2e-05,
      "loss": 0.2142,
      "step": 634
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 0.1788,
      "step": 636
    },
    {
      "epoch": 1.92,
      "learning_rate": 2e-05,
      "loss": 0.2131,
      "step": 638
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.2084,
      "step": 640
    },
    {
      "epoch": 1.93,
      "learning_rate": 2e-05,
      "loss": 0.1999,
      "step": 642
    },
    {
      "epoch": 1.94,
      "learning_rate": 2e-05,
      "loss": 0.2124,
      "step": 644
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 0.2114,
      "step": 646
    },
    {
      "epoch": 1.95,
      "learning_rate": 2e-05,
      "loss": 0.2137,
      "step": 648
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.2115,
      "step": 650
    },
    {
      "epoch": 1.96,
      "learning_rate": 2e-05,
      "loss": 0.2097,
      "step": 652
    },
    {
      "epoch": 1.97,
      "learning_rate": 2e-05,
      "loss": 0.199,
      "step": 654
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.2063,
      "step": 656
    },
    {
      "epoch": 1.98,
      "learning_rate": 2e-05,
      "loss": 0.2244,
      "step": 658
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 0.2029,
      "step": 660
    },
    {
      "epoch": 1.99,
      "learning_rate": 2e-05,
      "loss": 0.2079,
      "step": 662
    },
    {
      "epoch": 2.0,
      "learning_rate": 2e-05,
      "loss": 0.2054,
      "step": 664
    }
  ],
  "logging_steps": 2,
  "max_steps": 1328,
  "num_train_epochs": 4,
  "save_steps": 64.0,
  "total_flos": 95590771425280.0,
  "trial_name": null,
  "trial_params": null
}