{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 337,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.1866,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 0.0003,
      "loss": 0.053,
      "step": 4
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 0.0263,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.0003,
      "loss": 0.1589,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0003,
      "loss": 0.0704,
      "step": 10
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.0318,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0003,
      "loss": 0.0791,
      "step": 14
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.0714,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.0003,
      "loss": 0.0499,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0003,
      "loss": 0.0049,
      "step": 20
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.0506,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0003,
      "loss": 0.0434,
      "step": 24
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.1014,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0003,
      "loss": 0.0529,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.0705,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0003,
      "loss": 0.0224,
      "step": 32
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0003,
      "loss": 0.049,
      "step": 34
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.0215,
      "step": 36
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.0003,
      "loss": 0.0754,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0389,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0003,
      "loss": 0.0603,
      "step": 42
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0003,
      "loss": 0.0015,
      "step": 44
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.0278,
      "step": 46
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0003,
      "loss": 0.0276,
      "step": 48
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.0755,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0003,
      "loss": 0.1843,
      "step": 52
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0003,
      "loss": 0.0774,
      "step": 54
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.0199,
      "step": 56
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.0003,
      "loss": 0.0398,
      "step": 58
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.0516,
      "step": 60
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0003,
      "loss": 0.0978,
      "step": 62
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.0003,
      "loss": 0.093,
      "step": 64
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.1345,
      "step": 66
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0003,
      "loss": 0.0659,
      "step": 68
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.0441,
      "step": 70
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.0003,
      "loss": 0.0187,
      "step": 72
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0003,
      "loss": 0.031,
      "step": 74
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0327,
      "step": 76
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.0003,
      "loss": 0.0611,
      "step": 78
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.0082,
      "step": 80
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0003,
      "loss": 0.0121,
      "step": 82
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 0.0487,
      "step": 84
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.079,
      "step": 86
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0003,
      "loss": 0.0936,
      "step": 88
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.0177,
      "step": 90
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.0003,
      "loss": 0.0494,
      "step": 92
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.0457,
      "step": 94
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0003,
      "loss": 0.0279,
      "step": 96
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0003,
      "loss": 0.0402,
      "step": 98
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.0064,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0003,
      "loss": 0.1038,
      "step": 102
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.0054,
      "step": 104
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0003,
      "loss": 0.0111,
      "step": 106
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0003,
      "loss": 0.0421,
      "step": 108
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.0517,
      "step": 110
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0003,
      "loss": 0.0842,
      "step": 112
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0411,
      "step": 114
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0003,
      "loss": 0.0025,
      "step": 116
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.0003,
      "loss": 0.0255,
      "step": 118
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.0098,
      "step": 120
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0003,
      "loss": 0.0699,
      "step": 122
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.019,
      "step": 124
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.0003,
      "loss": 0.0487,
      "step": 126
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0003,
      "loss": 0.007,
      "step": 128
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.013,
      "step": 130
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.0003,
      "loss": 0.0349,
      "step": 132
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.0315,
      "step": 134
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0003,
      "loss": 0.0174,
      "step": 136
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.0003,
      "loss": 0.0006,
      "step": 138
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.0017,
      "step": 140
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0003,
      "loss": 0.0869,
      "step": 142
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.0286,
      "step": 144
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.0003,
      "loss": 0.0161,
      "step": 146
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0003,
      "loss": 0.2254,
      "step": 148
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0103,
      "step": 150
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0003,
      "loss": 0.0099,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0245,
      "step": 154
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0003,
      "loss": 0.0286,
      "step": 156
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.0743,
      "step": 158
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.0003,
      "loss": 0.0021,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0003,
      "loss": 0.0262,
      "step": 162
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.0121,
      "step": 164
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.0003,
      "loss": 0.2051,
      "step": 166
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.0168,
      "step": 168
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0003,
      "loss": 0.0036,
      "step": 170
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0003,
      "loss": 0.0387,
      "step": 172
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.0997,
      "step": 174
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.0052,
      "step": 178
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0003,
      "loss": 0.0348,
      "step": 180
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0003,
      "loss": 0.0576,
      "step": 182
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0118,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0003,
      "loss": 0.0363,
      "step": 186
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.0017,
      "step": 188
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0003,
      "loss": 0.1263,
      "step": 190
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0003,
      "loss": 0.0255,
      "step": 192
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.0549,
      "step": 194
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0003,
      "loss": 0.0002,
      "step": 196
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.1491,
      "step": 198
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0003,
      "loss": 0.2058,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 202
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0192,
      "step": 204
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.0003,
      "loss": 0.0078,
      "step": 206
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.2119,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0003,
      "loss": 0.0177,
      "step": 210
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0003,
      "loss": 0.0516,
      "step": 212
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.0271,
      "step": 214
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0003,
      "loss": 0.017,
      "step": 216
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0553,
      "step": 218
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.0003,
      "loss": 0.0442,
      "step": 220
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0178,
      "step": 222
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0003,
      "loss": 0.0023,
      "step": 224
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0003,
      "loss": 0.07,
      "step": 226
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.0321,
      "step": 228
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0003,
      "loss": 0.0216,
      "step": 230
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0011,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0003,
      "loss": 0.0029,
      "step": 234
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0003,
      "loss": 0.1031,
      "step": 236
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.0213,
      "step": 238
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0003,
      "loss": 0.0561,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0003,
      "step": 242
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0003,
      "loss": 0.0297,
      "step": 244
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.0003,
      "loss": 0.0205,
      "step": 246
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.006,
      "step": 248
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0003,
      "loss": 0.0204,
      "step": 250
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0982,
      "step": 252
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0003,
      "loss": 0.0796,
      "step": 254
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0003,
      "loss": 0.041,
      "step": 256
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0007,
      "step": 258
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0003,
      "loss": 0.0579,
      "step": 260
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0562,
      "step": 262
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0003,
      "loss": 0.0017,
      "step": 264
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.0003,
      "loss": 0.0653,
      "step": 266
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.0429,
      "step": 268
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0003,
      "loss": 0.0493,
      "step": 270
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.0382,
      "step": 272
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.0003,
      "loss": 0.0004,
      "step": 274
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0167,
      "step": 276
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0003,
      "loss": 0.0051,
      "step": 278
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0003,
      "loss": 0.0014,
      "step": 280
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.0605,
      "step": 282
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0003,
      "loss": 0.02,
      "step": 284
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.0134,
      "step": 286
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0003,
      "loss": 0.1659,
      "step": 288
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0003,
      "loss": 0.0209,
      "step": 290
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.0522,
      "step": 292
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0003,
      "loss": 0.0081,
      "step": 294
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.049,
      "step": 296
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0003,
      "loss": 0.0507,
      "step": 298
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0003,
      "loss": 0.1571,
      "step": 300
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.0097,
      "step": 302
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0003,
      "loss": 0.0172,
      "step": 304
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.0119,
      "step": 306
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0003,
      "loss": 0.0023,
      "step": 308
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.0003,
      "loss": 0.0687,
      "step": 310
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0678,
      "step": 312
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0003,
      "loss": 0.0591,
      "step": 314
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.0315,
      "step": 316
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.0003,
      "loss": 0.02,
      "step": 318
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0003,
      "loss": 0.0177,
      "step": 320
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.0031,
      "step": 322
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0003,
      "loss": 0.05,
      "step": 324
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.0564,
      "step": 326
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0003,
      "loss": 0.0868,
      "step": 328
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0003,
      "loss": 0.0279,
      "step": 330
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.1276,
      "step": 332
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0003,
      "loss": 0.0092,
      "step": 334
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0003,
      "loss": 0.0034,
      "step": 336
    },
    {
      "epoch": 1.0,
      "step": 337,
      "total_flos": 631174056056082.0,
      "train_loss": 0.04601551576511304,
      "train_runtime": 391.6583,
      "train_samples_per_second": 27.491,
      "train_steps_per_second": 0.86
    }
  ],
  "logging_steps": 2,
  "max_steps": 337,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 631174056056082.0,
  "trial_name": null,
  "trial_params": null
}