{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.983219390926041,
  "eval_steps": 500,
  "global_step": 300,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.0002,
      "loss": 2.5828,
      "step": 2
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0002,
      "loss": 2.6581,
      "step": 4
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 2.5371,
      "step": 6
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0002,
      "loss": 2.4502,
      "step": 8
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0002,
      "loss": 2.3872,
      "step": 10
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0002,
      "loss": 2.3808,
      "step": 12
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0002,
      "loss": 2.3424,
      "step": 14
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0002,
      "loss": 2.2899,
      "step": 16
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0002,
      "loss": 2.3867,
      "step": 18
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.0002,
      "loss": 1.9899,
      "step": 20
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0002,
      "loss": 2.0737,
      "step": 22
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.0002,
      "loss": 2.2409,
      "step": 24
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0002,
      "loss": 2.2095,
      "step": 26
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0002,
      "loss": 2.3744,
      "step": 28
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0002,
      "loss": 2.2856,
      "step": 30
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002,
      "loss": 2.2101,
      "step": 32
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002,
      "loss": 2.2994,
      "step": 34
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.0002,
      "loss": 2.1992,
      "step": 36
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002,
      "loss": 2.1496,
      "step": 38
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0002,
      "loss": 2.1543,
      "step": 40
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.0002,
      "loss": 2.0936,
      "step": 42
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002,
      "loss": 2.0874,
      "step": 44
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0002,
      "loss": 2.0742,
      "step": 46
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0002,
      "loss": 2.0173,
      "step": 48
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0002,
      "loss": 1.9083,
      "step": 50
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.0002,
      "loss": 2.16,
      "step": 52
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0002,
      "loss": 2.176,
      "step": 54
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.0002,
      "loss": 2.2623,
      "step": 56
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0002,
      "loss": 2.1539,
      "step": 58
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.0002,
      "loss": 2.1608,
      "step": 60
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0002,
      "loss": 2.2897,
      "step": 62
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.0002,
      "loss": 2.1425,
      "step": 64
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.0002,
      "loss": 2.2373,
      "step": 66
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002,
      "loss": 2.0494,
      "step": 68
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0002,
      "loss": 2.0225,
      "step": 70
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.0002,
      "loss": 2.1813,
      "step": 72
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002,
      "loss": 2.2155,
      "step": 74
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002,
      "loss": 2.0284,
      "step": 76
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002,
      "loss": 2.1858,
      "step": 78
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.0002,
      "loss": 2.2214,
      "step": 80
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.0002,
      "loss": 2.1439,
      "step": 82
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0002,
      "loss": 2.372,
      "step": 84
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0002,
      "loss": 2.2334,
      "step": 86
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0002,
      "loss": 2.1863,
      "step": 88
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002,
      "loss": 2.3142,
      "step": 90
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002,
      "loss": 2.0363,
      "step": 92
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002,
      "loss": 2.0347,
      "step": 94
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002,
      "loss": 2.1288,
      "step": 96
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002,
      "loss": 2.0572,
      "step": 98
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.0002,
      "loss": 2.083,
      "step": 100
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0002,
      "loss": 2.2397,
      "step": 102
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0002,
      "loss": 2.1792,
      "step": 104
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.0002,
      "loss": 2.2482,
      "step": 106
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0002,
      "loss": 2.0806,
      "step": 108
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.0002,
      "loss": 2.16,
      "step": 110
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.0002,
      "loss": 2.292,
      "step": 112
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.0002,
      "loss": 2.0676,
      "step": 114
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002,
      "loss": 2.2526,
      "step": 116
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.0002,
      "loss": 1.922,
      "step": 118
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002,
      "loss": 1.9116,
      "step": 120
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.0002,
      "loss": 1.8892,
      "step": 122
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002,
      "loss": 1.9477,
      "step": 124
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002,
      "loss": 2.0279,
      "step": 126
    },
    {
      "epoch": 1.27,
      "learning_rate": 0.0002,
      "loss": 2.2849,
      "step": 128
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.0002,
      "loss": 2.125,
      "step": 130
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.0002,
      "loss": 2.1052,
      "step": 132
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.0002,
      "loss": 2.1967,
      "step": 134
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.0002,
      "loss": 2.1822,
      "step": 136
    },
    {
      "epoch": 1.37,
      "learning_rate": 0.0002,
      "loss": 2.1636,
      "step": 138
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.0002,
      "loss": 2.1071,
      "step": 140
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.0002,
      "loss": 2.0495,
      "step": 142
    },
    {
      "epoch": 1.43,
      "learning_rate": 0.0002,
      "loss": 2.0297,
      "step": 144
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.0002,
      "loss": 2.029,
      "step": 146
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.0002,
      "loss": 2.0418,
      "step": 148
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002,
      "loss": 1.9593,
      "step": 150
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.0002,
      "loss": 2.0313,
      "step": 152
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.0002,
      "loss": 2.1371,
      "step": 154
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.0002,
      "loss": 2.0588,
      "step": 156
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.0002,
      "loss": 2.1388,
      "step": 158
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002,
      "loss": 2.1441,
      "step": 160
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.0002,
      "loss": 2.2533,
      "step": 162
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002,
      "loss": 2.2119,
      "step": 164
    },
    {
      "epoch": 1.65,
      "learning_rate": 0.0002,
      "loss": 2.1546,
      "step": 166
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.0002,
      "loss": 1.9094,
      "step": 168
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.0002,
      "loss": 1.8923,
      "step": 170
    },
    {
      "epoch": 1.71,
      "learning_rate": 0.0002,
      "loss": 2.1945,
      "step": 172
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.0002,
      "loss": 1.9362,
      "step": 174
    },
    {
      "epoch": 1.75,
      "learning_rate": 0.0002,
      "loss": 1.9729,
      "step": 176
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.0002,
      "loss": 2.1719,
      "step": 178
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.0002,
      "loss": 2.1011,
      "step": 180
    },
    {
      "epoch": 1.81,
      "learning_rate": 0.0002,
      "loss": 1.9506,
      "step": 182
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.0002,
      "loss": 2.1621,
      "step": 184
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.0002,
      "loss": 2.1376,
      "step": 186
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.0002,
      "loss": 2.0654,
      "step": 188
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.0002,
      "loss": 2.13,
      "step": 190
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.0002,
      "loss": 2.2511,
      "step": 192
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.0002,
      "loss": 2.0819,
      "step": 194
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.0002,
      "loss": 1.9898,
      "step": 196
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002,
      "loss": 2.0087,
      "step": 198
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002,
      "loss": 2.0657,
      "step": 200
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.0002,
      "loss": 1.9649,
      "step": 202
    },
    {
      "epoch": 2.03,
      "learning_rate": 0.0002,
      "loss": 2.2439,
      "step": 204
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.0002,
      "loss": 2.0759,
      "step": 206
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.0002,
      "loss": 2.0714,
      "step": 208
    },
    {
      "epoch": 2.09,
      "learning_rate": 0.0002,
      "loss": 2.0442,
      "step": 210
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.0002,
      "loss": 2.0177,
      "step": 212
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.0002,
      "loss": 2.1249,
      "step": 214
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0002,
      "loss": 2.0028,
      "step": 216
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.0002,
      "loss": 2.0526,
      "step": 218
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.0002,
      "loss": 1.9671,
      "step": 220
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.0002,
      "loss": 1.9116,
      "step": 222
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0002,
      "loss": 1.9053,
      "step": 224
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.0002,
      "loss": 1.8237,
      "step": 226
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.0002,
      "loss": 2.0919,
      "step": 228
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.0002,
      "loss": 1.9859,
      "step": 230
    },
    {
      "epoch": 2.31,
      "learning_rate": 0.0002,
      "loss": 2.0955,
      "step": 232
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.0002,
      "loss": 2.0789,
      "step": 234
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.0002,
      "loss": 2.1218,
      "step": 236
    },
    {
      "epoch": 2.37,
      "learning_rate": 0.0002,
      "loss": 2.1313,
      "step": 238
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.0002,
      "loss": 2.1044,
      "step": 240
    },
    {
      "epoch": 2.41,
      "learning_rate": 0.0002,
      "loss": 2.0011,
      "step": 242
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.0002,
      "loss": 1.8662,
      "step": 244
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.0002,
      "loss": 1.8631,
      "step": 246
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.0002,
      "loss": 2.0623,
      "step": 248
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.0002,
      "loss": 1.8474,
      "step": 250
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.0002,
      "loss": 2.0302,
      "step": 252
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.0002,
      "loss": 2.0382,
      "step": 254
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.0002,
      "loss": 2.0559,
      "step": 256
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.0002,
      "loss": 2.0959,
      "step": 258
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.0002,
      "loss": 2.0263,
      "step": 260
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.0002,
      "loss": 2.1544,
      "step": 262
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.0002,
      "loss": 2.2014,
      "step": 264
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.0002,
      "loss": 2.1269,
      "step": 266
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.0002,
      "loss": 2.0373,
      "step": 268
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.0002,
      "loss": 1.9107,
      "step": 270
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.0002,
      "loss": 1.9081,
      "step": 272
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.0002,
      "loss": 1.9295,
      "step": 274
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0002,
      "loss": 1.7845,
      "step": 276
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.0002,
      "loss": 2.0504,
      "step": 278
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.0002,
      "loss": 2.2585,
      "step": 280
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0002,
      "loss": 2.1938,
      "step": 282
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.0002,
      "loss": 2.0515,
      "step": 284
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.0002,
      "loss": 2.076,
      "step": 286
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.0002,
      "loss": 2.105,
      "step": 288
    },
    {
      "epoch": 2.88,
      "learning_rate": 0.0002,
      "loss": 2.165,
      "step": 290
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.0002,
      "loss": 2.1052,
      "step": 292
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.0002,
      "loss": 1.9451,
      "step": 294
    },
    {
      "epoch": 2.94,
      "learning_rate": 0.0002,
      "loss": 1.8612,
      "step": 296
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.0002,
      "loss": 1.8693,
      "step": 298
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.0002,
      "loss": 2.0716,
      "step": 300
    }
  ],
  "logging_steps": 2,
  "max_steps": 300,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "total_flos": 2.583887994465485e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}