{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8818342151675485,
  "eval_steps": 20,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 6.525190206840381e-06,
      "loss": 41.531,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.0642126856049071e-05,
      "loss": 10.8605,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.3050380413680763e-05,
      "loss": 1.7384,
      "step": 9
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.475906350525776e-05,
      "loss": 0.9315,
      "step": 12
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.6084421077509477e-05,
      "loss": 0.2076,
      "step": 15
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.716731706288945e-05,
      "loss": 0.2506,
      "step": 18
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.8082892572795735e-05,
      "loss": 0.1702,
      "step": 21
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.887600015446645e-05,
      "loss": 0.0833,
      "step": 24
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9575570620521145e-05,
      "loss": 0.0791,
      "step": 27
    },
    {
      "epoch": 0.05,
      "learning_rate": 2e-05,
      "loss": 0.0734,
      "step": 30
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 0.056,
      "step": 33
    },
    {
      "epoch": 0.06,
      "learning_rate": 2e-05,
      "loss": 0.0485,
      "step": 36
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 0.0756,
      "step": 39
    },
    {
      "epoch": 0.07,
      "learning_rate": 2e-05,
      "loss": 0.094,
      "step": 42
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.1405,
      "step": 45
    },
    {
      "epoch": 0.08,
      "learning_rate": 2e-05,
      "loss": 0.5148,
      "step": 48
    },
    {
      "epoch": 0.09,
      "learning_rate": 2e-05,
      "loss": 0.2001,
      "step": 51
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.1661,
      "step": 54
    },
    {
      "epoch": 0.1,
      "learning_rate": 2e-05,
      "loss": 0.1043,
      "step": 57
    },
    {
      "epoch": 0.11,
      "learning_rate": 2e-05,
      "loss": 0.2477,
      "step": 60
    },
    {
      "epoch": 0.11,
      "learning_rate": 2e-05,
      "loss": 0.0758,
      "step": 63
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.0438,
      "step": 66
    },
    {
      "epoch": 0.12,
      "learning_rate": 2e-05,
      "loss": 0.0372,
      "step": 69
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.0585,
      "step": 72
    },
    {
      "epoch": 0.13,
      "learning_rate": 2e-05,
      "loss": 0.0903,
      "step": 75
    },
    {
      "epoch": 0.14,
      "learning_rate": 2e-05,
      "loss": 0.2207,
      "step": 78
    },
    {
      "epoch": 0.14,
      "learning_rate": 2e-05,
      "loss": 0.0605,
      "step": 81
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.0613,
      "step": 84
    },
    {
      "epoch": 0.15,
      "learning_rate": 2e-05,
      "loss": 0.054,
      "step": 87
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.0596,
      "step": 90
    },
    {
      "epoch": 0.16,
      "learning_rate": 2e-05,
      "loss": 0.0686,
      "step": 93
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 0.026,
      "step": 96
    },
    {
      "epoch": 0.17,
      "learning_rate": 2e-05,
      "loss": 0.0218,
      "step": 99
    },
    {
      "epoch": 0.18,
      "learning_rate": 2e-05,
      "loss": 0.0203,
      "step": 102
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.0218,
      "step": 105
    },
    {
      "epoch": 0.19,
      "learning_rate": 2e-05,
      "loss": 0.0364,
      "step": 108
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.0706,
      "step": 111
    },
    {
      "epoch": 0.2,
      "learning_rate": 2e-05,
      "loss": 0.03,
      "step": 114
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 0.0203,
      "step": 117
    },
    {
      "epoch": 0.21,
      "learning_rate": 2e-05,
      "loss": 0.0276,
      "step": 120
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 0.049,
      "step": 123
    },
    {
      "epoch": 0.22,
      "learning_rate": 2e-05,
      "loss": 0.0483,
      "step": 126
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.1183,
      "step": 129
    },
    {
      "epoch": 0.23,
      "learning_rate": 2e-05,
      "loss": 0.0974,
      "step": 132
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.1345,
      "step": 135
    },
    {
      "epoch": 0.24,
      "learning_rate": 2e-05,
      "loss": 0.0615,
      "step": 138
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.0288,
      "step": 141
    },
    {
      "epoch": 0.25,
      "learning_rate": 2e-05,
      "loss": 0.0245,
      "step": 144
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.0336,
      "step": 147
    },
    {
      "epoch": 0.26,
      "learning_rate": 2e-05,
      "loss": 0.0255,
      "step": 150
    },
    {
      "epoch": 0.27,
      "learning_rate": 2e-05,
      "loss": 0.0384,
      "step": 153
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 0.0218,
      "step": 156
    },
    {
      "epoch": 0.28,
      "learning_rate": 2e-05,
      "loss": 0.0153,
      "step": 159
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 0.0135,
      "step": 162
    },
    {
      "epoch": 0.29,
      "learning_rate": 2e-05,
      "loss": 0.0169,
      "step": 165
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.0269,
      "step": 168
    },
    {
      "epoch": 0.3,
      "learning_rate": 2e-05,
      "loss": 0.0371,
      "step": 171
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.025,
      "step": 174
    },
    {
      "epoch": 0.31,
      "learning_rate": 2e-05,
      "loss": 0.0232,
      "step": 177
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 0.0205,
      "step": 180
    },
    {
      "epoch": 0.32,
      "learning_rate": 2e-05,
      "loss": 0.0193,
      "step": 183
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.0302,
      "step": 186
    },
    {
      "epoch": 0.33,
      "learning_rate": 2e-05,
      "loss": 0.0203,
      "step": 189
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 0.0293,
      "step": 192
    },
    {
      "epoch": 0.34,
      "learning_rate": 2e-05,
      "loss": 0.0295,
      "step": 195
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.0279,
      "step": 198
    },
    {
      "epoch": 0.35,
      "learning_rate": 2e-05,
      "loss": 0.0298,
      "step": 201
    },
    {
      "epoch": 0.36,
      "learning_rate": 2e-05,
      "loss": 0.0265,
      "step": 204
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.0225,
      "step": 207
    },
    {
      "epoch": 0.37,
      "learning_rate": 2e-05,
      "loss": 0.0205,
      "step": 210
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 0.0265,
      "step": 213
    },
    {
      "epoch": 0.38,
      "learning_rate": 2e-05,
      "loss": 0.0544,
      "step": 216
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.0458,
      "step": 219
    },
    {
      "epoch": 0.39,
      "learning_rate": 2e-05,
      "loss": 0.1028,
      "step": 222
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.0814,
      "step": 225
    },
    {
      "epoch": 0.4,
      "learning_rate": 2e-05,
      "loss": 0.1324,
      "step": 228
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.0441,
      "step": 231
    },
    {
      "epoch": 0.41,
      "learning_rate": 2e-05,
      "loss": 0.027,
      "step": 234
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.0178,
      "step": 237
    },
    {
      "epoch": 0.42,
      "learning_rate": 2e-05,
      "loss": 0.0338,
      "step": 240
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.0224,
      "step": 243
    },
    {
      "epoch": 0.43,
      "learning_rate": 2e-05,
      "loss": 0.0248,
      "step": 246
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.0316,
      "step": 249
    },
    {
      "epoch": 0.44,
      "learning_rate": 2e-05,
      "loss": 0.0984,
      "step": 252
    },
    {
      "epoch": 0.45,
      "learning_rate": 2e-05,
      "loss": 0.0492,
      "step": 255
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.1069,
      "step": 258
    },
    {
      "epoch": 0.46,
      "learning_rate": 2e-05,
      "loss": 0.0448,
      "step": 261
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.0413,
      "step": 264
    },
    {
      "epoch": 0.47,
      "learning_rate": 2e-05,
      "loss": 0.0974,
      "step": 267
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.0446,
      "step": 270
    },
    {
      "epoch": 0.48,
      "learning_rate": 2e-05,
      "loss": 0.0449,
      "step": 273
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.0155,
      "step": 276
    },
    {
      "epoch": 0.49,
      "learning_rate": 2e-05,
      "loss": 0.0256,
      "step": 279
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.0154,
      "step": 282
    },
    {
      "epoch": 0.5,
      "learning_rate": 2e-05,
      "loss": 0.0232,
      "step": 285
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.0154,
      "step": 288
    },
    {
      "epoch": 0.51,
      "learning_rate": 2e-05,
      "loss": 0.0201,
      "step": 291
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.0188,
      "step": 294
    },
    {
      "epoch": 0.52,
      "learning_rate": 2e-05,
      "loss": 0.0148,
      "step": 297
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.0189,
      "step": 300
    },
    {
      "epoch": 0.53,
      "learning_rate": 2e-05,
      "loss": 0.0166,
      "step": 303
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.0164,
      "step": 306
    },
    {
      "epoch": 0.54,
      "learning_rate": 2e-05,
      "loss": 0.0197,
      "step": 309
    },
    {
      "epoch": 0.55,
      "learning_rate": 2e-05,
      "loss": 0.0168,
      "step": 312
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.0198,
      "step": 315
    },
    {
      "epoch": 0.56,
      "learning_rate": 2e-05,
      "loss": 0.0137,
      "step": 318
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.0202,
      "step": 321
    },
    {
      "epoch": 0.57,
      "learning_rate": 2e-05,
      "loss": 0.0137,
      "step": 324
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.0218,
      "step": 327
    },
    {
      "epoch": 0.58,
      "learning_rate": 2e-05,
      "loss": 0.0155,
      "step": 330
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.0235,
      "step": 333
    },
    {
      "epoch": 0.59,
      "learning_rate": 2e-05,
      "loss": 0.0134,
      "step": 336
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.0217,
      "step": 339
    },
    {
      "epoch": 0.6,
      "learning_rate": 2e-05,
      "loss": 0.014,
      "step": 342
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.0201,
      "step": 345
    },
    {
      "epoch": 0.61,
      "learning_rate": 2e-05,
      "loss": 0.0139,
      "step": 348
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 0.0165,
      "step": 351
    },
    {
      "epoch": 0.62,
      "learning_rate": 2e-05,
      "loss": 0.0282,
      "step": 354
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.021,
      "step": 357
    },
    {
      "epoch": 0.63,
      "learning_rate": 2e-05,
      "loss": 0.0168,
      "step": 360
    },
    {
      "epoch": 0.64,
      "learning_rate": 2e-05,
      "loss": 0.0209,
      "step": 363
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.0195,
      "step": 366
    },
    {
      "epoch": 0.65,
      "learning_rate": 2e-05,
      "loss": 0.0193,
      "step": 369
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.0159,
      "step": 372
    },
    {
      "epoch": 0.66,
      "learning_rate": 2e-05,
      "loss": 0.0184,
      "step": 375
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.0159,
      "step": 378
    },
    {
      "epoch": 0.67,
      "learning_rate": 2e-05,
      "loss": 0.0206,
      "step": 381
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.0181,
      "step": 384
    },
    {
      "epoch": 0.68,
      "learning_rate": 2e-05,
      "loss": 0.0152,
      "step": 387
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.016,
      "step": 390
    },
    {
      "epoch": 0.69,
      "learning_rate": 2e-05,
      "loss": 0.0191,
      "step": 393
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.0152,
      "step": 396
    },
    {
      "epoch": 0.7,
      "learning_rate": 2e-05,
      "loss": 0.0151,
      "step": 399
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.0129,
      "step": 402
    },
    {
      "epoch": 0.71,
      "learning_rate": 2e-05,
      "loss": 0.0178,
      "step": 405
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.0153,
      "step": 408
    },
    {
      "epoch": 0.72,
      "learning_rate": 2e-05,
      "loss": 0.0174,
      "step": 411
    },
    {
      "epoch": 0.73,
      "learning_rate": 2e-05,
      "loss": 0.0135,
      "step": 414
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.0163,
      "step": 417
    },
    {
      "epoch": 0.74,
      "learning_rate": 2e-05,
      "loss": 0.0142,
      "step": 420
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.0151,
      "step": 423
    },
    {
      "epoch": 0.75,
      "learning_rate": 2e-05,
      "loss": 0.0115,
      "step": 426
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.0155,
      "step": 429
    },
    {
      "epoch": 0.76,
      "learning_rate": 2e-05,
      "loss": 0.0145,
      "step": 432
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.0158,
      "step": 435
    },
    {
      "epoch": 0.77,
      "learning_rate": 2e-05,
      "loss": 0.0144,
      "step": 438
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.0178,
      "step": 441
    },
    {
      "epoch": 0.78,
      "learning_rate": 2e-05,
      "loss": 0.0154,
      "step": 444
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.0202,
      "step": 447
    },
    {
      "epoch": 0.79,
      "learning_rate": 2e-05,
      "loss": 0.0132,
      "step": 450
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.0181,
      "step": 453
    },
    {
      "epoch": 0.8,
      "learning_rate": 2e-05,
      "loss": 0.0179,
      "step": 456
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.015,
      "step": 459
    },
    {
      "epoch": 0.81,
      "learning_rate": 2e-05,
      "loss": 0.0147,
      "step": 462
    },
    {
      "epoch": 0.82,
      "learning_rate": 2e-05,
      "loss": 0.0137,
      "step": 465
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.0144,
      "step": 468
    },
    {
      "epoch": 0.83,
      "learning_rate": 2e-05,
      "loss": 0.0127,
      "step": 471
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.013,
      "step": 474
    },
    {
      "epoch": 0.84,
      "learning_rate": 2e-05,
      "loss": 0.0141,
      "step": 477
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.0129,
      "step": 480
    },
    {
      "epoch": 0.85,
      "learning_rate": 2e-05,
      "loss": 0.0133,
      "step": 483
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.0104,
      "step": 486
    },
    {
      "epoch": 0.86,
      "learning_rate": 2e-05,
      "loss": 0.0132,
      "step": 489
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.0123,
      "step": 492
    },
    {
      "epoch": 0.87,
      "learning_rate": 2e-05,
      "loss": 0.0112,
      "step": 495
    },
    {
      "epoch": 0.88,
      "learning_rate": 2e-05,
      "loss": 0.013,
      "step": 498
    }
  ],
  "logging_steps": 3,
  "max_steps": 567,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "total_flos": 498838580035584.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}