{
  "best_metric": 1.0956162214279175,
  "best_model_checkpoint": "/exports/eddie/scratch/s1970716/models/summarization/longt5_xl_gov_bp_5/checkpoint-409",
  "epoch": 4.985679917516325,
  "eval_steps": 500,
  "global_step": 680,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.001,
      "loss": 2.8578,
      "step": 2
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.001,
      "loss": 2.5483,
      "step": 4
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.001,
      "loss": 2.5567,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.001,
      "loss": 2.2472,
      "step": 8
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.001,
      "loss": 2.6838,
      "step": 10
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.001,
      "loss": 1.913,
      "step": 12
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.001,
      "loss": 1.7027,
      "step": 14
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.001,
      "loss": 1.8552,
      "step": 16
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.001,
      "loss": 1.7768,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.001,
      "loss": 1.6651,
      "step": 20
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.001,
      "loss": 1.7347,
      "step": 22
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.001,
      "loss": 1.8688,
      "step": 24
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.001,
      "loss": 1.7518,
      "step": 26
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.001,
      "loss": 2.2375,
      "step": 28
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.001,
      "loss": 1.8573,
      "step": 30
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.001,
      "loss": 1.9004,
      "step": 32
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.001,
      "loss": 1.7522,
      "step": 34
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.001,
      "loss": 1.6239,
      "step": 36
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.001,
      "loss": 1.7933,
      "step": 38
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.001,
      "loss": 1.7567,
      "step": 40
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.001,
      "loss": 1.5474,
      "step": 42
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.001,
      "loss": 1.5337,
      "step": 44
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.001,
      "loss": 1.4789,
      "step": 46
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.001,
      "loss": 1.5511,
      "step": 48
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.001,
      "loss": 1.6554,
      "step": 50
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.001,
      "loss": 1.788,
      "step": 52
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.001,
      "loss": 1.5203,
      "step": 54
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.001,
      "loss": 1.7213,
      "step": 56
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.001,
      "loss": 1.7086,
      "step": 58
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.001,
      "loss": 1.5924,
      "step": 60
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.001,
      "loss": 1.5697,
      "step": 62
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.001,
      "loss": 1.5098,
      "step": 64
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.001,
      "loss": 1.4718,
      "step": 66
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.001,
      "loss": 1.4245,
      "step": 68
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.001,
      "loss": 1.465,
      "step": 70
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.001,
      "loss": 1.4338,
      "step": 72
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.001,
      "loss": 1.4323,
      "step": 74
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.001,
      "loss": 1.4446,
      "step": 76
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.001,
      "loss": 1.3731,
      "step": 78
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.001,
      "loss": 1.3275,
      "step": 80
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.001,
      "loss": 1.3541,
      "step": 82
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.001,
      "loss": 1.3533,
      "step": 84
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.001,
      "loss": 1.3351,
      "step": 86
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.001,
      "loss": 1.3132,
      "step": 88
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.001,
      "loss": 1.3448,
      "step": 90
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.001,
      "loss": 1.3142,
      "step": 92
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.001,
      "loss": 1.3081,
      "step": 94
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.001,
      "loss": 1.3302,
      "step": 96
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.001,
      "loss": 1.3195,
      "step": 98
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.001,
      "loss": 1.2944,
      "step": 100
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.001,
      "loss": 1.2982,
      "step": 102
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.001,
      "loss": 1.3171,
      "step": 104
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.001,
      "loss": 1.2697,
      "step": 106
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.001,
      "loss": 1.3157,
      "step": 108
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.001,
      "loss": 1.3377,
      "step": 110
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.001,
      "loss": 1.3173,
      "step": 112
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.001,
      "loss": 1.2956,
      "step": 114
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.001,
      "loss": 1.2563,
      "step": 116
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.001,
      "loss": 1.2771,
      "step": 118
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.001,
      "loss": 1.2524,
      "step": 120
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.001,
      "loss": 1.3304,
      "step": 122
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.001,
      "loss": 1.3573,
      "step": 124
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.001,
      "loss": 1.3259,
      "step": 126
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.001,
      "loss": 1.3305,
      "step": 128
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.001,
      "loss": 1.3584,
      "step": 130
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.001,
      "loss": 1.3212,
      "step": 132
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.001,
      "loss": 1.309,
      "step": 134
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.001,
      "loss": 1.2876,
      "step": 136
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.148115634918213,
      "eval_runtime": 353.1241,
      "eval_samples_per_second": 2.753,
      "eval_steps_per_second": 1.376,
      "step": 136
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.001,
      "loss": 1.2155,
      "step": 138
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.001,
      "loss": 1.2231,
      "step": 140
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.001,
      "loss": 1.1799,
      "step": 142
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.001,
      "loss": 1.1672,
      "step": 144
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.001,
      "loss": 1.2073,
      "step": 146
    },
    {
      "epoch": 1.09,
      "learning_rate": 0.001,
      "loss": 1.1873,
      "step": 148
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.001,
      "loss": 1.1876,
      "step": 150
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.001,
      "loss": 1.1727,
      "step": 152
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.001,
      "loss": 1.1803,
      "step": 154
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.001,
      "loss": 1.1526,
      "step": 156
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.001,
      "loss": 1.1728,
      "step": 158
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.001,
      "loss": 1.1553,
      "step": 160
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.001,
      "loss": 1.1832,
      "step": 162
    },
    {
      "epoch": 1.2,
      "learning_rate": 0.001,
      "loss": 1.1887,
      "step": 164
    },
    {
      "epoch": 1.22,
      "learning_rate": 0.001,
      "loss": 1.187,
      "step": 166
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.001,
      "loss": 1.1592,
      "step": 168
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.001,
      "loss": 1.1693,
      "step": 170
    },
    {
      "epoch": 1.26,
      "learning_rate": 0.001,
      "loss": 1.1904,
      "step": 172
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.001,
      "loss": 1.1659,
      "step": 174
    },
    {
      "epoch": 1.29,
      "learning_rate": 0.001,
      "loss": 1.1391,
      "step": 176
    },
    {
      "epoch": 1.31,
      "learning_rate": 0.001,
      "loss": 1.1822,
      "step": 178
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.001,
      "loss": 1.1617,
      "step": 180
    },
    {
      "epoch": 1.33,
      "learning_rate": 0.001,
      "loss": 1.1636,
      "step": 182
    },
    {
      "epoch": 1.35,
      "learning_rate": 0.001,
      "loss": 1.1786,
      "step": 184
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.001,
      "loss": 1.1496,
      "step": 186
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.001,
      "loss": 1.1584,
      "step": 188
    },
    {
      "epoch": 1.39,
      "learning_rate": 0.001,
      "loss": 1.1707,
      "step": 190
    },
    {
      "epoch": 1.41,
      "learning_rate": 0.001,
      "loss": 1.1772,
      "step": 192
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.001,
      "loss": 1.1532,
      "step": 194
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.001,
      "loss": 1.1526,
      "step": 196
    },
    {
      "epoch": 1.45,
      "learning_rate": 0.001,
      "loss": 1.1405,
      "step": 198
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.001,
      "loss": 1.161,
      "step": 200
    },
    {
      "epoch": 1.48,
      "learning_rate": 0.001,
      "loss": 1.1521,
      "step": 202
    },
    {
      "epoch": 1.5,
      "learning_rate": 0.001,
      "loss": 1.1638,
      "step": 204
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.001,
      "loss": 1.1305,
      "step": 206
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.001,
      "loss": 1.1575,
      "step": 208
    },
    {
      "epoch": 1.54,
      "learning_rate": 0.001,
      "loss": 1.1253,
      "step": 210
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.001,
      "loss": 1.1308,
      "step": 212
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.001,
      "loss": 1.157,
      "step": 214
    },
    {
      "epoch": 1.58,
      "learning_rate": 0.001,
      "loss": 1.1414,
      "step": 216
    },
    {
      "epoch": 1.6,
      "learning_rate": 0.001,
      "loss": 1.1456,
      "step": 218
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.001,
      "loss": 1.1817,
      "step": 220
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.001,
      "loss": 1.1481,
      "step": 222
    },
    {
      "epoch": 1.64,
      "learning_rate": 0.001,
      "loss": 1.1167,
      "step": 224
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.001,
      "loss": 1.1674,
      "step": 226
    },
    {
      "epoch": 1.67,
      "learning_rate": 0.001,
      "loss": 1.1737,
      "step": 228
    },
    {
      "epoch": 1.69,
      "learning_rate": 0.001,
      "loss": 1.1665,
      "step": 230
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.001,
      "loss": 1.1381,
      "step": 232
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.001,
      "loss": 1.1193,
      "step": 234
    },
    {
      "epoch": 1.73,
      "learning_rate": 0.001,
      "loss": 1.1513,
      "step": 236
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.001,
      "loss": 1.17,
      "step": 238
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.001,
      "loss": 1.1522,
      "step": 240
    },
    {
      "epoch": 1.77,
      "learning_rate": 0.001,
      "loss": 1.1529,
      "step": 242
    },
    {
      "epoch": 1.79,
      "learning_rate": 0.001,
      "loss": 1.1661,
      "step": 244
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.001,
      "loss": 1.1428,
      "step": 246
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.001,
      "loss": 1.1597,
      "step": 248
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.001,
      "loss": 1.134,
      "step": 250
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.001,
      "loss": 1.1325,
      "step": 252
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.001,
      "loss": 1.1357,
      "step": 254
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.001,
      "loss": 1.1416,
      "step": 256
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.001,
      "loss": 1.1114,
      "step": 258
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.001,
      "loss": 1.1535,
      "step": 260
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.001,
      "loss": 1.1139,
      "step": 262
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.001,
      "loss": 1.1103,
      "step": 264
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.001,
      "loss": 1.1398,
      "step": 266
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.001,
      "loss": 1.1227,
      "step": 268
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.001,
      "loss": 1.1387,
      "step": 270
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.001,
      "loss": 1.1337,
      "step": 272
    },
    {
      "epoch": 1.99,
      "eval_loss": 1.1011404991149902,
      "eval_runtime": 352.3991,
      "eval_samples_per_second": 2.758,
      "eval_steps_per_second": 1.379,
      "step": 272
    },
    {
      "epoch": 2.01,
      "learning_rate": 0.001,
      "loss": 1.0784,
      "step": 274
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.001,
      "loss": 0.9727,
      "step": 276
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.001,
      "loss": 0.9831,
      "step": 278
    },
    {
      "epoch": 2.05,
      "learning_rate": 0.001,
      "loss": 0.9878,
      "step": 280
    },
    {
      "epoch": 2.07,
      "learning_rate": 0.001,
      "loss": 0.9916,
      "step": 282
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.001,
      "loss": 0.9951,
      "step": 284
    },
    {
      "epoch": 2.1,
      "learning_rate": 0.001,
      "loss": 0.9758,
      "step": 286
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.001,
      "loss": 0.9633,
      "step": 288
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.001,
      "loss": 0.9677,
      "step": 290
    },
    {
      "epoch": 2.14,
      "learning_rate": 0.001,
      "loss": 0.9946,
      "step": 292
    },
    {
      "epoch": 2.16,
      "learning_rate": 0.001,
      "loss": 1.0038,
      "step": 294
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.001,
      "loss": 0.9954,
      "step": 296
    },
    {
      "epoch": 2.18,
      "learning_rate": 0.001,
      "loss": 0.9638,
      "step": 298
    },
    {
      "epoch": 2.2,
      "learning_rate": 0.001,
      "loss": 0.9759,
      "step": 300
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.001,
      "loss": 0.9768,
      "step": 302
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.001,
      "loss": 0.96,
      "step": 304
    },
    {
      "epoch": 2.24,
      "learning_rate": 0.001,
      "loss": 0.97,
      "step": 306
    },
    {
      "epoch": 2.26,
      "learning_rate": 0.001,
      "loss": 0.968,
      "step": 308
    },
    {
      "epoch": 2.27,
      "learning_rate": 0.001,
      "loss": 0.9946,
      "step": 310
    },
    {
      "epoch": 2.29,
      "learning_rate": 0.001,
      "loss": 0.9661,
      "step": 312
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.001,
      "loss": 0.9885,
      "step": 314
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.001,
      "loss": 0.9992,
      "step": 316
    },
    {
      "epoch": 2.33,
      "learning_rate": 0.001,
      "loss": 1.0069,
      "step": 318
    },
    {
      "epoch": 2.35,
      "learning_rate": 0.001,
      "loss": 1.0155,
      "step": 320
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.001,
      "loss": 1.0005,
      "step": 322
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.001,
      "loss": 0.9909,
      "step": 324
    },
    {
      "epoch": 2.39,
      "learning_rate": 0.001,
      "loss": 1.019,
      "step": 326
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.001,
      "loss": 0.9833,
      "step": 328
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.001,
      "loss": 0.9871,
      "step": 330
    },
    {
      "epoch": 2.43,
      "learning_rate": 0.001,
      "loss": 0.9957,
      "step": 332
    },
    {
      "epoch": 2.45,
      "learning_rate": 0.001,
      "loss": 0.9917,
      "step": 334
    },
    {
      "epoch": 2.46,
      "learning_rate": 0.001,
      "loss": 0.9838,
      "step": 336
    },
    {
      "epoch": 2.48,
      "learning_rate": 0.001,
      "loss": 1.0105,
      "step": 338
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.001,
      "loss": 0.984,
      "step": 340
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.001,
      "loss": 0.992,
      "step": 342
    },
    {
      "epoch": 2.52,
      "learning_rate": 0.001,
      "loss": 1.0061,
      "step": 344
    },
    {
      "epoch": 2.54,
      "learning_rate": 0.001,
      "loss": 0.9836,
      "step": 346
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.001,
      "loss": 0.9852,
      "step": 348
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.001,
      "loss": 0.9706,
      "step": 350
    },
    {
      "epoch": 2.58,
      "learning_rate": 0.001,
      "loss": 0.995,
      "step": 352
    },
    {
      "epoch": 2.6,
      "learning_rate": 0.001,
      "loss": 0.9862,
      "step": 354
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.001,
      "loss": 1.0435,
      "step": 356
    },
    {
      "epoch": 2.62,
      "learning_rate": 0.001,
      "loss": 1.0267,
      "step": 358
    },
    {
      "epoch": 2.64,
      "learning_rate": 0.001,
      "loss": 0.9958,
      "step": 360
    },
    {
      "epoch": 2.65,
      "learning_rate": 0.001,
      "loss": 1.0154,
      "step": 362
    },
    {
      "epoch": 2.67,
      "learning_rate": 0.001,
      "loss": 1.0029,
      "step": 364
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.001,
      "loss": 1.0194,
      "step": 366
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.001,
      "loss": 1.0005,
      "step": 368
    },
    {
      "epoch": 2.71,
      "learning_rate": 0.001,
      "loss": 0.9939,
      "step": 370
    },
    {
      "epoch": 2.73,
      "learning_rate": 0.001,
      "loss": 0.9899,
      "step": 372
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.001,
      "loss": 1.0186,
      "step": 374
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.001,
      "loss": 0.9746,
      "step": 376
    },
    {
      "epoch": 2.77,
      "learning_rate": 0.001,
      "loss": 0.9901,
      "step": 378
    },
    {
      "epoch": 2.79,
      "learning_rate": 0.001,
      "loss": 1.0106,
      "step": 380
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.001,
      "loss": 0.9937,
      "step": 382
    },
    {
      "epoch": 2.82,
      "learning_rate": 0.001,
      "loss": 0.9936,
      "step": 384
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.001,
      "loss": 0.9904,
      "step": 386
    },
    {
      "epoch": 2.84,
      "learning_rate": 0.001,
      "loss": 0.9771,
      "step": 388
    },
    {
      "epoch": 2.86,
      "learning_rate": 0.001,
      "loss": 1.0164,
      "step": 390
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.001,
      "loss": 1.0037,
      "step": 392
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.001,
      "loss": 1.0122,
      "step": 394
    },
    {
      "epoch": 2.9,
      "learning_rate": 0.001,
      "loss": 0.9975,
      "step": 396
    },
    {
      "epoch": 2.92,
      "learning_rate": 0.001,
      "loss": 1.0082,
      "step": 398
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.001,
      "loss": 0.9972,
      "step": 400
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.001,
      "loss": 1.0087,
      "step": 402
    },
    {
      "epoch": 2.96,
      "learning_rate": 0.001,
      "loss": 0.9765,
      "step": 404
    },
    {
      "epoch": 2.98,
      "learning_rate": 0.001,
      "loss": 1.0034,
      "step": 406
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.001,
      "loss": 1.0035,
      "step": 408
    },
    {
      "epoch": 3.0,
      "eval_loss": 1.0956162214279175,
      "eval_runtime": 352.5215,
      "eval_samples_per_second": 2.757,
      "eval_steps_per_second": 1.379,
      "step": 409
    },
    {
      "epoch": 3.01,
      "learning_rate": 0.001,
      "loss": 0.9411,
      "step": 410
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.001,
      "loss": 0.8412,
      "step": 412
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.001,
      "loss": 0.8384,
      "step": 414
    },
    {
      "epoch": 3.05,
      "learning_rate": 0.001,
      "loss": 0.8179,
      "step": 416
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.001,
      "loss": 0.8384,
      "step": 418
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.001,
      "loss": 0.8292,
      "step": 420
    },
    {
      "epoch": 3.09,
      "learning_rate": 0.001,
      "loss": 0.8178,
      "step": 422
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.001,
      "loss": 0.8292,
      "step": 424
    },
    {
      "epoch": 3.12,
      "learning_rate": 0.001,
      "loss": 0.8414,
      "step": 426
    },
    {
      "epoch": 3.14,
      "learning_rate": 0.001,
      "loss": 0.8419,
      "step": 428
    },
    {
      "epoch": 3.15,
      "learning_rate": 0.001,
      "loss": 0.8247,
      "step": 430
    },
    {
      "epoch": 3.17,
      "learning_rate": 0.001,
      "loss": 0.8331,
      "step": 432
    },
    {
      "epoch": 3.18,
      "learning_rate": 0.001,
      "loss": 0.8409,
      "step": 434
    },
    {
      "epoch": 3.2,
      "learning_rate": 0.001,
      "loss": 0.8318,
      "step": 436
    },
    {
      "epoch": 3.21,
      "learning_rate": 0.001,
      "loss": 0.8386,
      "step": 438
    },
    {
      "epoch": 3.23,
      "learning_rate": 0.001,
      "loss": 0.8477,
      "step": 440
    },
    {
      "epoch": 3.24,
      "learning_rate": 0.001,
      "loss": 0.854,
      "step": 442
    },
    {
      "epoch": 3.26,
      "learning_rate": 0.001,
      "loss": 0.8415,
      "step": 444
    },
    {
      "epoch": 3.27,
      "learning_rate": 0.001,
      "loss": 0.8225,
      "step": 446
    },
    {
      "epoch": 3.28,
      "learning_rate": 0.001,
      "loss": 0.8555,
      "step": 448
    },
    {
      "epoch": 3.3,
      "learning_rate": 0.001,
      "loss": 0.8632,
      "step": 450
    },
    {
      "epoch": 3.31,
      "learning_rate": 0.001,
      "loss": 0.8589,
      "step": 452
    },
    {
      "epoch": 3.33,
      "learning_rate": 0.001,
      "loss": 0.8513,
      "step": 454
    },
    {
      "epoch": 3.34,
      "learning_rate": 0.001,
      "loss": 0.8552,
      "step": 456
    },
    {
      "epoch": 3.36,
      "learning_rate": 0.001,
      "loss": 0.8688,
      "step": 458
    },
    {
      "epoch": 3.37,
      "learning_rate": 0.001,
      "loss": 0.8626,
      "step": 460
    },
    {
      "epoch": 3.39,
      "learning_rate": 0.001,
      "loss": 0.8752,
      "step": 462
    },
    {
      "epoch": 3.4,
      "learning_rate": 0.001,
      "loss": 0.862,
      "step": 464
    },
    {
      "epoch": 3.42,
      "learning_rate": 0.001,
      "loss": 0.8556,
      "step": 466
    },
    {
      "epoch": 3.43,
      "learning_rate": 0.001,
      "loss": 0.8573,
      "step": 468
    },
    {
      "epoch": 3.45,
      "learning_rate": 0.001,
      "loss": 0.8427,
      "step": 470
    },
    {
      "epoch": 3.46,
      "learning_rate": 0.001,
      "loss": 0.8458,
      "step": 472
    },
    {
      "epoch": 3.48,
      "learning_rate": 0.001,
      "loss": 0.8331,
      "step": 474
    },
    {
      "epoch": 3.49,
      "learning_rate": 0.001,
      "loss": 0.8668,
      "step": 476
    },
    {
      "epoch": 3.5,
      "learning_rate": 0.001,
      "loss": 0.867,
      "step": 478
    },
    {
      "epoch": 3.52,
      "learning_rate": 0.001,
      "loss": 0.868,
      "step": 480
    },
    {
      "epoch": 3.53,
      "learning_rate": 0.001,
      "loss": 0.8517,
      "step": 482
    },
    {
      "epoch": 3.55,
      "learning_rate": 0.001,
      "loss": 0.8465,
      "step": 484
    },
    {
      "epoch": 3.56,
      "learning_rate": 0.001,
      "loss": 0.8357,
      "step": 486
    },
    {
      "epoch": 3.58,
      "learning_rate": 0.001,
      "loss": 0.8644,
      "step": 488
    },
    {
      "epoch": 3.59,
      "learning_rate": 0.001,
      "loss": 0.8644,
      "step": 490
    },
    {
      "epoch": 3.61,
      "learning_rate": 0.001,
      "loss": 0.8586,
      "step": 492
    },
    {
      "epoch": 3.62,
      "learning_rate": 0.001,
      "loss": 0.8656,
      "step": 494
    },
    {
      "epoch": 3.64,
      "learning_rate": 0.001,
      "loss": 0.8684,
      "step": 496
    },
    {
      "epoch": 3.65,
      "learning_rate": 0.001,
      "loss": 0.8689,
      "step": 498
    },
    {
      "epoch": 3.67,
      "learning_rate": 0.001,
      "loss": 0.842,
      "step": 500
    },
    {
      "epoch": 3.68,
      "learning_rate": 0.001,
      "loss": 0.8479,
      "step": 502
    },
    {
      "epoch": 3.7,
      "learning_rate": 0.001,
      "loss": 0.8677,
      "step": 504
    },
    {
      "epoch": 3.71,
      "learning_rate": 0.001,
      "loss": 0.8503,
      "step": 506
    },
    {
      "epoch": 3.72,
      "learning_rate": 0.001,
      "loss": 0.871,
      "step": 508
    },
    {
      "epoch": 3.74,
      "learning_rate": 0.001,
      "loss": 0.8539,
      "step": 510
    },
    {
      "epoch": 3.75,
      "learning_rate": 0.001,
      "loss": 0.8688,
      "step": 512
    },
    {
      "epoch": 3.77,
      "learning_rate": 0.001,
      "loss": 0.8793,
      "step": 514
    },
    {
      "epoch": 3.78,
      "learning_rate": 0.001,
      "loss": 0.8613,
      "step": 516
    },
    {
      "epoch": 3.8,
      "learning_rate": 0.001,
      "loss": 0.8755,
      "step": 518
    },
    {
      "epoch": 3.81,
      "learning_rate": 0.001,
      "loss": 0.8536,
      "step": 520
    },
    {
      "epoch": 3.83,
      "learning_rate": 0.001,
      "loss": 0.8698,
      "step": 522
    },
    {
      "epoch": 3.84,
      "learning_rate": 0.001,
      "loss": 0.8669,
      "step": 524
    },
    {
      "epoch": 3.86,
      "learning_rate": 0.001,
      "loss": 0.8656,
      "step": 526
    },
    {
      "epoch": 3.87,
      "learning_rate": 0.001,
      "loss": 0.8856,
      "step": 528
    },
    {
      "epoch": 3.89,
      "learning_rate": 0.001,
      "loss": 0.8686,
      "step": 530
    },
    {
      "epoch": 3.9,
      "learning_rate": 0.001,
      "loss": 0.885,
      "step": 532
    },
    {
      "epoch": 3.92,
      "learning_rate": 0.001,
      "loss": 0.8504,
      "step": 534
    },
    {
      "epoch": 3.93,
      "learning_rate": 0.001,
      "loss": 0.8708,
      "step": 536
    },
    {
      "epoch": 3.94,
      "learning_rate": 0.001,
      "loss": 0.849,
      "step": 538
    },
    {
      "epoch": 3.96,
      "learning_rate": 0.001,
      "loss": 0.8411,
      "step": 540
    },
    {
      "epoch": 3.97,
      "learning_rate": 0.001,
      "loss": 0.8842,
      "step": 542
    },
    {
      "epoch": 3.99,
      "learning_rate": 0.001,
      "loss": 0.8616,
      "step": 544
    },
    {
      "epoch": 4.0,
      "eval_loss": 1.1049234867095947,
      "eval_runtime": 352.482,
      "eval_samples_per_second": 2.758,
      "eval_steps_per_second": 1.379,
      "step": 545
    },
    {
      "epoch": 4.0,
      "learning_rate": 0.001,
      "loss": 0.8478,
      "step": 546
    },
    {
      "epoch": 4.02,
      "learning_rate": 0.001,
      "loss": 0.6919,
      "step": 548
    },
    {
      "epoch": 4.03,
      "learning_rate": 0.001,
      "loss": 0.6977,
      "step": 550
    },
    {
      "epoch": 4.05,
      "learning_rate": 0.001,
      "loss": 0.6794,
      "step": 552
    },
    {
      "epoch": 4.06,
      "learning_rate": 0.001,
      "loss": 0.7189,
      "step": 554
    },
    {
      "epoch": 4.08,
      "learning_rate": 0.001,
      "loss": 0.7166,
      "step": 556
    },
    {
      "epoch": 4.09,
      "learning_rate": 0.001,
      "loss": 0.7072,
      "step": 558
    },
    {
      "epoch": 4.11,
      "learning_rate": 0.001,
      "loss": 0.7143,
      "step": 560
    },
    {
      "epoch": 4.12,
      "learning_rate": 0.001,
      "loss": 0.7117,
      "step": 562
    },
    {
      "epoch": 4.14,
      "learning_rate": 0.001,
      "loss": 0.716,
      "step": 564
    },
    {
      "epoch": 4.15,
      "learning_rate": 0.001,
      "loss": 0.7156,
      "step": 566
    },
    {
      "epoch": 4.16,
      "learning_rate": 0.001,
      "loss": 0.7242,
      "step": 568
    },
    {
      "epoch": 4.18,
      "learning_rate": 0.001,
      "loss": 0.7128,
      "step": 570
    },
    {
      "epoch": 4.19,
      "learning_rate": 0.001,
      "loss": 0.7184,
      "step": 572
    },
    {
      "epoch": 4.21,
      "learning_rate": 0.001,
      "loss": 0.7181,
      "step": 574
    },
    {
      "epoch": 4.22,
      "learning_rate": 0.001,
      "loss": 0.7084,
      "step": 576
    },
    {
      "epoch": 4.24,
      "learning_rate": 0.001,
      "loss": 0.7332,
      "step": 578
    },
    {
      "epoch": 4.25,
      "learning_rate": 0.001,
      "loss": 0.7107,
      "step": 580
    },
    {
      "epoch": 4.27,
      "learning_rate": 0.001,
      "loss": 0.7151,
      "step": 582
    },
    {
      "epoch": 4.28,
      "learning_rate": 0.001,
      "loss": 0.7299,
      "step": 584
    },
    {
      "epoch": 4.3,
      "learning_rate": 0.001,
      "loss": 0.729,
      "step": 586
    },
    {
      "epoch": 4.31,
      "learning_rate": 0.001,
      "loss": 0.7287,
      "step": 588
    },
    {
      "epoch": 4.33,
      "learning_rate": 0.001,
      "loss": 0.7119,
      "step": 590
    },
    {
      "epoch": 4.34,
      "learning_rate": 0.001,
      "loss": 0.7246,
      "step": 592
    },
    {
      "epoch": 4.36,
      "learning_rate": 0.001,
      "loss": 0.7371,
      "step": 594
    },
    {
      "epoch": 4.37,
      "learning_rate": 0.001,
      "loss": 0.7231,
      "step": 596
    },
    {
      "epoch": 4.38,
      "learning_rate": 0.001,
      "loss": 0.723,
      "step": 598
    },
    {
      "epoch": 4.4,
      "learning_rate": 0.001,
      "loss": 0.7191,
      "step": 600
    },
    {
      "epoch": 4.41,
      "learning_rate": 0.001,
      "loss": 0.727,
      "step": 602
    },
    {
      "epoch": 4.43,
      "learning_rate": 0.001,
      "loss": 0.7337,
      "step": 604
    },
    {
      "epoch": 4.44,
      "learning_rate": 0.001,
      "loss": 0.7369,
      "step": 606
    },
    {
      "epoch": 4.46,
      "learning_rate": 0.001,
      "loss": 0.7233,
      "step": 608
    },
    {
      "epoch": 4.47,
      "learning_rate": 0.001,
      "loss": 0.7476,
      "step": 610
    },
    {
      "epoch": 4.49,
      "learning_rate": 0.001,
      "loss": 0.7532,
      "step": 612
    },
    {
      "epoch": 4.5,
      "learning_rate": 0.001,
      "loss": 0.7267,
      "step": 614
    },
    {
      "epoch": 4.52,
      "learning_rate": 0.001,
      "loss": 0.7454,
      "step": 616
    },
    {
      "epoch": 4.53,
      "learning_rate": 0.001,
      "loss": 0.7469,
      "step": 618
    },
    {
      "epoch": 4.55,
      "learning_rate": 0.001,
      "loss": 0.7665,
      "step": 620
    },
    {
      "epoch": 4.56,
      "learning_rate": 0.001,
      "loss": 0.746,
      "step": 622
    },
    {
      "epoch": 4.58,
      "learning_rate": 0.001,
      "loss": 0.7508,
      "step": 624
    },
    {
      "epoch": 4.59,
      "learning_rate": 0.001,
      "loss": 0.7556,
      "step": 626
    },
    {
      "epoch": 4.6,
      "learning_rate": 0.001,
      "loss": 0.7299,
      "step": 628
    },
    {
      "epoch": 4.62,
      "learning_rate": 0.001,
      "loss": 0.742,
      "step": 630
    },
    {
      "epoch": 4.63,
      "learning_rate": 0.001,
      "loss": 0.7385,
      "step": 632
    },
    {
      "epoch": 4.65,
      "learning_rate": 0.001,
      "loss": 0.7631,
      "step": 634
    },
    {
      "epoch": 4.66,
      "learning_rate": 0.001,
      "loss": 0.7479,
      "step": 636
    },
    {
      "epoch": 4.68,
      "learning_rate": 0.001,
      "loss": 0.7407,
      "step": 638
    },
    {
      "epoch": 4.69,
      "learning_rate": 0.001,
      "loss": 0.741,
      "step": 640
    },
    {
      "epoch": 4.71,
      "learning_rate": 0.001,
      "loss": 0.7488,
      "step": 642
    },
    {
      "epoch": 4.72,
      "learning_rate": 0.001,
      "loss": 0.759,
      "step": 644
    },
    {
      "epoch": 4.74,
      "learning_rate": 0.001,
      "loss": 0.7677,
      "step": 646
    },
    {
      "epoch": 4.75,
      "learning_rate": 0.001,
      "loss": 0.7351,
      "step": 648
    },
    {
      "epoch": 4.77,
      "learning_rate": 0.001,
      "loss": 0.7322,
      "step": 650
    },
    {
      "epoch": 4.78,
      "learning_rate": 0.001,
      "loss": 0.7601,
      "step": 652
    },
    {
      "epoch": 4.8,
      "learning_rate": 0.001,
      "loss": 0.7593,
      "step": 654
    },
    {
      "epoch": 4.81,
      "learning_rate": 0.001,
      "loss": 0.7376,
      "step": 656
    },
    {
      "epoch": 4.82,
      "learning_rate": 0.001,
      "loss": 0.7397,
      "step": 658
    },
    {
      "epoch": 4.84,
      "learning_rate": 0.001,
      "loss": 0.758,
      "step": 660
    },
    {
      "epoch": 4.85,
      "learning_rate": 0.001,
      "loss": 0.7425,
      "step": 662
    },
    {
      "epoch": 4.87,
      "learning_rate": 0.001,
      "loss": 0.7502,
      "step": 664
    },
    {
      "epoch": 4.88,
      "learning_rate": 0.001,
      "loss": 0.745,
      "step": 666
    },
    {
      "epoch": 4.9,
      "learning_rate": 0.001,
      "loss": 0.7474,
      "step": 668
    },
    {
      "epoch": 4.91,
      "learning_rate": 0.001,
      "loss": 0.7564,
      "step": 670
    },
    {
      "epoch": 4.93,
      "learning_rate": 0.001,
      "loss": 0.7598,
      "step": 672
    },
    {
      "epoch": 4.94,
      "learning_rate": 0.001,
      "loss": 0.7514,
      "step": 674
    },
    {
      "epoch": 4.96,
      "learning_rate": 0.001,
      "loss": 0.7568,
      "step": 676
    },
    {
      "epoch": 4.97,
      "learning_rate": 0.001,
      "loss": 0.7565,
      "step": 678
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.001,
      "loss": 0.7515,
      "step": 680
    },
    {
      "epoch": 4.99,
      "eval_loss": 1.139513373374939,
      "eval_runtime": 352.6241,
      "eval_samples_per_second": 2.756,
      "eval_steps_per_second": 1.378,
      "step": 680
    },
    {
      "epoch": 4.99,
      "step": 680,
      "total_flos": 5.939593565767631e+18,
      "train_loss": 1.064733072940041,
      "train_runtime": 117328.7303,
      "train_samples_per_second": 0.744,
      "train_steps_per_second": 0.006
    }
  ],
  "logging_steps": 2,
  "max_steps": 680,
  "num_train_epochs": 5,
  "save_steps": 500,
  "total_flos": 5.939593565767631e+18,
  "trial_name": null,
  "trial_params": null
}