{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 59.388888888888886,
  "eval_steps": 500,
  "global_step": 420,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.17,
      "learning_rate": 5.555555555555556e-06,
      "loss": 1.7272,
      "step": 3
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.1111111111111112e-05,
      "loss": 1.9664,
      "step": 6
    },
    {
      "epoch": 1.11,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.8802,
      "step": 9
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.2222222222222223e-05,
      "loss": 1.641,
      "step": 12
    },
    {
      "epoch": 2.06,
      "learning_rate": 2.777777777777778e-05,
      "loss": 1.9065,
      "step": 15
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.5674,
      "step": 18
    },
    {
      "epoch": 2.39,
      "learning_rate": 3.888888888888889e-05,
      "loss": 1.7742,
      "step": 21
    },
    {
      "epoch": 3.17,
      "learning_rate": 4.4444444444444447e-05,
      "loss": 1.6901,
      "step": 24
    },
    {
      "epoch": 3.33,
      "learning_rate": 5e-05,
      "loss": 1.4911,
      "step": 27
    },
    {
      "epoch": 4.11,
      "learning_rate": 5.555555555555556e-05,
      "loss": 1.6228,
      "step": 30
    },
    {
      "epoch": 4.28,
      "learning_rate": 6.111111111111112e-05,
      "loss": 1.4569,
      "step": 33
    },
    {
      "epoch": 5.06,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.1288,
      "step": 36
    },
    {
      "epoch": 5.22,
      "learning_rate": 7.222222222222222e-05,
      "loss": 1.3788,
      "step": 39
    },
    {
      "epoch": 5.39,
      "learning_rate": 7.777777777777778e-05,
      "loss": 1.3019,
      "step": 42
    },
    {
      "epoch": 6.17,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.1974,
      "step": 45
    },
    {
      "epoch": 6.33,
      "learning_rate": 8.888888888888889e-05,
      "loss": 1.2544,
      "step": 48
    },
    {
      "epoch": 7.11,
      "learning_rate": 9.444444444444444e-05,
      "loss": 1.0393,
      "step": 51
    },
    {
      "epoch": 7.28,
      "learning_rate": 0.0001,
      "loss": 1.0955,
      "step": 54
    },
    {
      "epoch": 8.06,
      "learning_rate": 0.00010555555555555557,
      "loss": 0.9618,
      "step": 57
    },
    {
      "epoch": 8.22,
      "learning_rate": 0.00011111111111111112,
      "loss": 0.7707,
      "step": 60
    },
    {
      "epoch": 8.39,
      "learning_rate": 0.00011666666666666668,
      "loss": 0.7415,
      "step": 63
    },
    {
      "epoch": 9.17,
      "learning_rate": 0.00012222222222222224,
      "loss": 0.5368,
      "step": 66
    },
    {
      "epoch": 9.33,
      "learning_rate": 0.00012777777777777776,
      "loss": 0.741,
      "step": 69
    },
    {
      "epoch": 10.11,
      "learning_rate": 0.00013333333333333334,
      "loss": 0.5261,
      "step": 72
    },
    {
      "epoch": 10.28,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.5543,
      "step": 75
    },
    {
      "epoch": 11.06,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.3309,
      "step": 78
    },
    {
      "epoch": 11.22,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.3979,
      "step": 81
    },
    {
      "epoch": 11.39,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.3294,
      "step": 84
    },
    {
      "epoch": 12.17,
      "learning_rate": 0.0001611111111111111,
      "loss": 0.3013,
      "step": 87
    },
    {
      "epoch": 12.33,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.3047,
      "step": 90
    },
    {
      "epoch": 13.11,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.2221,
      "step": 93
    },
    {
      "epoch": 13.28,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.2132,
      "step": 96
    },
    {
      "epoch": 14.06,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.175,
      "step": 99
    },
    {
      "epoch": 14.22,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.1485,
      "step": 102
    },
    {
      "epoch": 14.39,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.1709,
      "step": 105
    },
    {
      "epoch": 15.17,
      "learning_rate": 0.0002,
      "loss": 0.1427,
      "step": 108
    },
    {
      "epoch": 15.33,
      "learning_rate": 0.00019938271604938272,
      "loss": 0.1162,
      "step": 111
    },
    {
      "epoch": 16.11,
      "learning_rate": 0.00019876543209876543,
      "loss": 0.1075,
      "step": 114
    },
    {
      "epoch": 16.28,
      "learning_rate": 0.00019814814814814814,
      "loss": 0.0965,
      "step": 117
    },
    {
      "epoch": 17.06,
      "learning_rate": 0.00019753086419753085,
      "loss": 0.0955,
      "step": 120
    },
    {
      "epoch": 17.22,
      "learning_rate": 0.0001969135802469136,
      "loss": 0.0706,
      "step": 123
    },
    {
      "epoch": 17.39,
      "learning_rate": 0.0001962962962962963,
      "loss": 0.0645,
      "step": 126
    },
    {
      "epoch": 18.17,
      "learning_rate": 0.000195679012345679,
      "loss": 0.042,
      "step": 129
    },
    {
      "epoch": 18.33,
      "learning_rate": 0.00019506172839506175,
      "loss": 0.0479,
      "step": 132
    },
    {
      "epoch": 19.11,
      "learning_rate": 0.00019444444444444446,
      "loss": 0.0258,
      "step": 135
    },
    {
      "epoch": 19.28,
      "learning_rate": 0.00019382716049382717,
      "loss": 0.0426,
      "step": 138
    },
    {
      "epoch": 20.06,
      "learning_rate": 0.00019320987654320988,
      "loss": 0.0314,
      "step": 141
    },
    {
      "epoch": 20.22,
      "learning_rate": 0.0001925925925925926,
      "loss": 0.0235,
      "step": 144
    },
    {
      "epoch": 20.39,
      "learning_rate": 0.00019197530864197533,
      "loss": 0.0359,
      "step": 147
    },
    {
      "epoch": 21.17,
      "learning_rate": 0.00019135802469135804,
      "loss": 0.0218,
      "step": 150
    },
    {
      "epoch": 21.33,
      "learning_rate": 0.00019074074074074075,
      "loss": 0.0279,
      "step": 153
    },
    {
      "epoch": 22.11,
      "learning_rate": 0.00019012345679012346,
      "loss": 0.019,
      "step": 156
    },
    {
      "epoch": 22.28,
      "learning_rate": 0.00018950617283950617,
      "loss": 0.0212,
      "step": 159
    },
    {
      "epoch": 23.06,
      "learning_rate": 0.00018888888888888888,
      "loss": 0.0201,
      "step": 162
    },
    {
      "epoch": 23.22,
      "learning_rate": 0.0001882716049382716,
      "loss": 0.0133,
      "step": 165
    },
    {
      "epoch": 23.39,
      "learning_rate": 0.00018765432098765433,
      "loss": 0.0194,
      "step": 168
    },
    {
      "epoch": 24.17,
      "learning_rate": 0.00018703703703703704,
      "loss": 0.0143,
      "step": 171
    },
    {
      "epoch": 24.33,
      "learning_rate": 0.00018641975308641978,
      "loss": 0.0118,
      "step": 174
    },
    {
      "epoch": 25.11,
      "learning_rate": 0.0001858024691358025,
      "loss": 0.0135,
      "step": 177
    },
    {
      "epoch": 25.28,
      "learning_rate": 0.0001851851851851852,
      "loss": 0.0105,
      "step": 180
    },
    {
      "epoch": 26.06,
      "learning_rate": 0.00018456790123456791,
      "loss": 0.0125,
      "step": 183
    },
    {
      "epoch": 26.22,
      "learning_rate": 0.00018395061728395062,
      "loss": 0.012,
      "step": 186
    },
    {
      "epoch": 26.39,
      "learning_rate": 0.00018333333333333334,
      "loss": 0.012,
      "step": 189
    },
    {
      "epoch": 27.17,
      "learning_rate": 0.00018271604938271605,
      "loss": 0.0114,
      "step": 192
    },
    {
      "epoch": 27.33,
      "learning_rate": 0.00018209876543209878,
      "loss": 0.0105,
      "step": 195
    },
    {
      "epoch": 28.11,
      "learning_rate": 0.0001814814814814815,
      "loss": 0.0115,
      "step": 198
    },
    {
      "epoch": 28.28,
      "learning_rate": 0.0001808641975308642,
      "loss": 0.0077,
      "step": 201
    },
    {
      "epoch": 29.06,
      "learning_rate": 0.00018024691358024692,
      "loss": 0.0116,
      "step": 204
    },
    {
      "epoch": 29.22,
      "learning_rate": 0.00017962962962962963,
      "loss": 0.0092,
      "step": 207
    },
    {
      "epoch": 29.39,
      "learning_rate": 0.00017901234567901234,
      "loss": 0.0105,
      "step": 210
    },
    {
      "epoch": 30.17,
      "learning_rate": 0.00017839506172839508,
      "loss": 0.0113,
      "step": 213
    },
    {
      "epoch": 30.33,
      "learning_rate": 0.00017777777777777779,
      "loss": 0.0094,
      "step": 216
    },
    {
      "epoch": 31.11,
      "learning_rate": 0.00017716049382716052,
      "loss": 0.0092,
      "step": 219
    },
    {
      "epoch": 31.28,
      "learning_rate": 0.00017654320987654323,
      "loss": 0.0079,
      "step": 222
    },
    {
      "epoch": 32.06,
      "learning_rate": 0.00017592592592592595,
      "loss": 0.0089,
      "step": 225
    },
    {
      "epoch": 32.22,
      "learning_rate": 0.00017530864197530866,
      "loss": 0.0085,
      "step": 228
    },
    {
      "epoch": 32.39,
      "learning_rate": 0.00017469135802469137,
      "loss": 0.0081,
      "step": 231
    },
    {
      "epoch": 33.17,
      "learning_rate": 0.00017407407407407408,
      "loss": 0.0076,
      "step": 234
    },
    {
      "epoch": 33.33,
      "learning_rate": 0.0001734567901234568,
      "loss": 0.0059,
      "step": 237
    },
    {
      "epoch": 34.11,
      "learning_rate": 0.0001728395061728395,
      "loss": 0.0078,
      "step": 240
    },
    {
      "epoch": 34.28,
      "learning_rate": 0.00017222222222222224,
      "loss": 0.0039,
      "step": 243
    },
    {
      "epoch": 35.06,
      "learning_rate": 0.00017160493827160495,
      "loss": 0.0078,
      "step": 246
    },
    {
      "epoch": 35.22,
      "learning_rate": 0.00017098765432098766,
      "loss": 0.0041,
      "step": 249
    },
    {
      "epoch": 35.39,
      "learning_rate": 0.00017037037037037037,
      "loss": 0.0061,
      "step": 252
    },
    {
      "epoch": 36.17,
      "learning_rate": 0.00016975308641975308,
      "loss": 0.0039,
      "step": 255
    },
    {
      "epoch": 36.33,
      "learning_rate": 0.00016913580246913582,
      "loss": 0.007,
      "step": 258
    },
    {
      "epoch": 37.11,
      "learning_rate": 0.00016851851851851853,
      "loss": 0.0049,
      "step": 261
    },
    {
      "epoch": 37.28,
      "learning_rate": 0.00016790123456790124,
      "loss": 0.005,
      "step": 264
    },
    {
      "epoch": 38.06,
      "learning_rate": 0.00016728395061728398,
      "loss": 0.0074,
      "step": 267
    },
    {
      "epoch": 38.22,
      "learning_rate": 0.0001666666666666667,
      "loss": 0.0035,
      "step": 270
    },
    {
      "epoch": 38.39,
      "learning_rate": 0.0001660493827160494,
      "loss": 0.0067,
      "step": 273
    },
    {
      "epoch": 39.17,
      "learning_rate": 0.0001654320987654321,
      "loss": 0.0061,
      "step": 276
    },
    {
      "epoch": 39.33,
      "learning_rate": 0.00016481481481481482,
      "loss": 0.0047,
      "step": 279
    },
    {
      "epoch": 40.11,
      "learning_rate": 0.00016419753086419753,
      "loss": 0.0035,
      "step": 282
    },
    {
      "epoch": 40.28,
      "learning_rate": 0.00016358024691358024,
      "loss": 0.0072,
      "step": 285
    },
    {
      "epoch": 41.06,
      "learning_rate": 0.00016296296296296295,
      "loss": 0.0044,
      "step": 288
    },
    {
      "epoch": 41.22,
      "learning_rate": 0.0001623456790123457,
      "loss": 0.0031,
      "step": 291
    },
    {
      "epoch": 41.39,
      "learning_rate": 0.0001617283950617284,
      "loss": 0.0047,
      "step": 294
    },
    {
      "epoch": 42.17,
      "learning_rate": 0.0001611111111111111,
      "loss": 0.004,
      "step": 297
    },
    {
      "epoch": 42.33,
      "learning_rate": 0.00016049382716049385,
      "loss": 0.0048,
      "step": 300
    },
    {
      "epoch": 43.11,
      "learning_rate": 0.00015987654320987656,
      "loss": 0.0028,
      "step": 303
    },
    {
      "epoch": 43.28,
      "learning_rate": 0.00015925925925925927,
      "loss": 0.0043,
      "step": 306
    },
    {
      "epoch": 44.06,
      "learning_rate": 0.00015864197530864198,
      "loss": 0.0037,
      "step": 309
    },
    {
      "epoch": 44.22,
      "learning_rate": 0.0001580246913580247,
      "loss": 0.0032,
      "step": 312
    },
    {
      "epoch": 44.39,
      "learning_rate": 0.00015740740740740743,
      "loss": 0.0045,
      "step": 315
    },
    {
      "epoch": 45.17,
      "learning_rate": 0.00015679012345679014,
      "loss": 0.0041,
      "step": 318
    },
    {
      "epoch": 45.33,
      "learning_rate": 0.00015617283950617285,
      "loss": 0.0032,
      "step": 321
    },
    {
      "epoch": 46.11,
      "learning_rate": 0.00015555555555555556,
      "loss": 0.002,
      "step": 324
    },
    {
      "epoch": 46.28,
      "learning_rate": 0.00015493827160493827,
      "loss": 0.0038,
      "step": 327
    },
    {
      "epoch": 47.06,
      "learning_rate": 0.00015432098765432098,
      "loss": 0.0036,
      "step": 330
    },
    {
      "epoch": 47.22,
      "learning_rate": 0.0001537037037037037,
      "loss": 0.0035,
      "step": 333
    },
    {
      "epoch": 47.39,
      "learning_rate": 0.0001530864197530864,
      "loss": 0.0035,
      "step": 336
    },
    {
      "epoch": 48.17,
      "learning_rate": 0.00015246913580246914,
      "loss": 0.005,
      "step": 339
    },
    {
      "epoch": 48.33,
      "learning_rate": 0.00015185185185185185,
      "loss": 0.0019,
      "step": 342
    },
    {
      "epoch": 49.11,
      "learning_rate": 0.0001512345679012346,
      "loss": 0.0033,
      "step": 345
    },
    {
      "epoch": 49.28,
      "learning_rate": 0.0001506172839506173,
      "loss": 0.0016,
      "step": 348
    },
    {
      "epoch": 50.06,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0034,
      "step": 351
    },
    {
      "epoch": 50.22,
      "learning_rate": 0.00014938271604938272,
      "loss": 0.0028,
      "step": 354
    },
    {
      "epoch": 50.39,
      "learning_rate": 0.00014876543209876544,
      "loss": 0.0039,
      "step": 357
    },
    {
      "epoch": 51.17,
      "learning_rate": 0.00014814814814814815,
      "loss": 0.0019,
      "step": 360
    },
    {
      "epoch": 51.33,
      "learning_rate": 0.00014753086419753086,
      "loss": 0.0042,
      "step": 363
    },
    {
      "epoch": 52.11,
      "learning_rate": 0.0001469135802469136,
      "loss": 0.0016,
      "step": 366
    },
    {
      "epoch": 52.28,
      "learning_rate": 0.0001462962962962963,
      "loss": 0.0022,
      "step": 369
    },
    {
      "epoch": 53.06,
      "learning_rate": 0.00014567901234567902,
      "loss": 0.0048,
      "step": 372
    },
    {
      "epoch": 53.22,
      "learning_rate": 0.00014506172839506173,
      "loss": 0.0014,
      "step": 375
    },
    {
      "epoch": 53.39,
      "learning_rate": 0.00014444444444444444,
      "loss": 0.0026,
      "step": 378
    },
    {
      "epoch": 54.17,
      "learning_rate": 0.00014382716049382718,
      "loss": 0.0036,
      "step": 381
    },
    {
      "epoch": 54.33,
      "learning_rate": 0.00014320987654320989,
      "loss": 0.0019,
      "step": 384
    },
    {
      "epoch": 55.11,
      "learning_rate": 0.0001425925925925926,
      "loss": 0.0033,
      "step": 387
    },
    {
      "epoch": 55.28,
      "learning_rate": 0.00014197530864197534,
      "loss": 0.0012,
      "step": 390
    },
    {
      "epoch": 56.06,
      "learning_rate": 0.00014135802469135805,
      "loss": 0.0019,
      "step": 393
    },
    {
      "epoch": 56.22,
      "learning_rate": 0.00014074074074074076,
      "loss": 0.002,
      "step": 396
    },
    {
      "epoch": 56.39,
      "learning_rate": 0.00014012345679012347,
      "loss": 0.0031,
      "step": 399
    },
    {
      "epoch": 57.17,
      "learning_rate": 0.00013950617283950618,
      "loss": 0.0042,
      "step": 402
    },
    {
      "epoch": 57.33,
      "learning_rate": 0.0001388888888888889,
      "loss": 0.0008,
      "step": 405
    },
    {
      "epoch": 58.11,
      "learning_rate": 0.0001382716049382716,
      "loss": 0.0012,
      "step": 408
    },
    {
      "epoch": 58.28,
      "learning_rate": 0.0001376543209876543,
      "loss": 0.0026,
      "step": 411
    },
    {
      "epoch": 59.06,
      "learning_rate": 0.00013703703703703705,
      "loss": 0.0025,
      "step": 414
    },
    {
      "epoch": 59.22,
      "learning_rate": 0.00013641975308641976,
      "loss": 0.0026,
      "step": 417
    },
    {
      "epoch": 59.39,
      "learning_rate": 0.00013580246913580247,
      "loss": 0.0014,
      "step": 420
    }
  ],
  "logging_steps": 3,
  "max_steps": 1080,
  "num_train_epochs": 60,
  "save_steps": 500,
  "total_flos": 3.41435505180672e+16,
  "trial_name": null,
  "trial_params": null
}