{
  "best_metric": 0.6451979106514778,
  "best_model_checkpoint": "./runtime-masked/bert_uncased_L-2_H-768_A-12-mlm-multi-emails-hq/checkpoint-705",
  "epoch": 4.994708994708994,
  "global_step": 705,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.4999999999999998e-05,
      "loss": 3.2694,
      "step": 3
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9999999999999996e-05,
      "loss": 3.2366,
      "step": 6
    },
    {
      "epoch": 0.06,
      "learning_rate": 7.5e-05,
      "loss": 3.2013,
      "step": 9
    },
    {
      "epoch": 0.08,
      "learning_rate": 9.999999999999999e-05,
      "loss": 3.0257,
      "step": 12
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.000125,
      "loss": 3.0287,
      "step": 15
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00015,
      "loss": 2.9585,
      "step": 18
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.000175,
      "loss": 2.8967,
      "step": 21
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019999999999999998,
      "loss": 2.7588,
      "step": 24
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.000225,
      "loss": 2.7953,
      "step": 27
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00025,
      "loss": 2.752,
      "step": 30
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00027499999999999996,
      "loss": 2.6644,
      "step": 33
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.0003,
      "loss": 2.736,
      "step": 36
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00029998511516242686,
      "loss": 2.5937,
      "step": 39
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00029994046360381946,
      "loss": 2.6411,
      "step": 42
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0002998660541859271,
      "loss": 2.587,
      "step": 45
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.0002997619016763776,
      "loss": 2.5726,
      "step": 48
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.000299628026745747,
      "loss": 2.5472,
      "step": 51
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.0002994644559634565,
      "loss": 2.5179,
      "step": 54
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.00029927122179249977,
      "loss": 2.4876,
      "step": 57
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00029904836258300014,
      "loss": 2.5026,
      "step": 60
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.0002987959225645994,
      "loss": 2.4842,
      "step": 63
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00029851395183767983,
      "loss": 2.442,
      "step": 66
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00029820250636342104,
      "loss": 2.4273,
      "step": 69
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00029786164795269374,
      "loss": 2.4646,
      "step": 72
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00029749144425379216,
      "loss": 2.3918,
      "step": 75
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.0002970919687390088,
      "loss": 2.4216,
      "step": 78
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00029666330069005225,
      "loss": 2.3679,
      "step": 81
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.000296205525182313,
      "loss": 2.4738,
      "step": 84
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00029571873306797876,
      "loss": 2.4424,
      "step": 87
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.0002952030209580035,
      "loss": 2.4183,
      "step": 90
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00029465849120293385,
      "loss": 2.368,
      "step": 93
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.0002940852518725959,
      "loss": 2.3876,
      "step": 96
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.00029348341673464726,
      "loss": 2.3105,
      "step": 99
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00029285310523199823,
      "loss": 2.3397,
      "step": 102
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0002921944424591067,
      "loss": 2.3759,
      "step": 105
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0002915075591371512,
      "loss": 2.4231,
      "step": 108
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.0002907925915880874,
      "loss": 2.3697,
      "step": 111
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00029004968170759317,
      "loss": 2.309,
      "step": 114
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.0002892789769369072,
      "loss": 2.2677,
      "step": 117
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.00028848063023356724,
      "loss": 2.3125,
      "step": 120
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0002876548000410533,
      "loss": 2.3249,
      "step": 123
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.0002868016502573425,
      "loss": 2.276,
      "step": 126
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.0002859213502023809,
      "loss": 2.3264,
      "step": 129
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.0002850140745844796,
      "loss": 2.2838,
      "step": 132
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.0002840800034656413,
      "loss": 2.268,
      "step": 135
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0002831193222258246,
      "loss": 2.2771,
      "step": 138
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00028213222152615234,
      "loss": 2.3053,
      "step": 141
    },
    {
      "epoch": 0.99,
      "eval_accuracy": 0.6064227132633339,
      "eval_loss": 2.1757757663726807,
      "eval_runtime": 10.2199,
      "eval_samples_per_second": 197.361,
      "eval_steps_per_second": 98.729,
      "step": 141
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.0002811188972710721,
      "loss": 2.7816,
      "step": 144
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00028007955056947675,
      "loss": 2.2354,
      "step": 147
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00027901438769479056,
      "loss": 2.2302,
      "step": 150
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.0002779236200440321,
      "loss": 2.2056,
      "step": 153
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00027680746409585865,
      "loss": 2.2774,
      "step": 156
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00027566614136760364,
      "loss": 2.2402,
      "step": 159
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.0002744998783713127,
      "loss": 2.2697,
      "step": 162
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00027330890656878943,
      "loss": 2.2966,
      "step": 165
    },
    {
      "epoch": 1.19,
      "learning_rate": 0.0002720934623256582,
      "loss": 2.2673,
      "step": 168
    },
    {
      "epoch": 1.21,
      "learning_rate": 0.00027085378686445433,
      "loss": 2.2083,
      "step": 171
    },
    {
      "epoch": 1.23,
      "learning_rate": 0.0002695901262167495,
      "loss": 2.1908,
      "step": 174
    },
    {
      "epoch": 1.25,
      "learning_rate": 0.0002683027311743236,
      "loss": 2.1983,
      "step": 177
    },
    {
      "epoch": 1.28,
      "learning_rate": 0.00026699185723939124,
      "loss": 2.1856,
      "step": 180
    },
    {
      "epoch": 1.3,
      "learning_rate": 0.0002656577645738938,
      "loss": 2.232,
      "step": 183
    },
    {
      "epoch": 1.32,
      "learning_rate": 0.00026430071794786644,
      "loss": 2.2705,
      "step": 186
    },
    {
      "epoch": 1.34,
      "learning_rate": 0.00026292098668689043,
      "loss": 2.1916,
      "step": 189
    },
    {
      "epoch": 1.36,
      "learning_rate": 0.00026151884461864214,
      "loss": 2.2189,
      "step": 192
    },
    {
      "epoch": 1.38,
      "learning_rate": 0.0002600945700185474,
      "loss": 2.2082,
      "step": 195
    },
    {
      "epoch": 1.4,
      "learning_rate": 0.0002586484455545538,
      "loss": 2.1623,
      "step": 198
    },
    {
      "epoch": 1.42,
      "learning_rate": 0.00025718075823103165,
      "loss": 2.1774,
      "step": 201
    },
    {
      "epoch": 1.44,
      "learning_rate": 0.0002556917993318131,
      "loss": 2.1522,
      "step": 204
    },
    {
      "epoch": 1.47,
      "learning_rate": 0.000254181864362383,
      "loss": 2.1744,
      "step": 207
    },
    {
      "epoch": 1.49,
      "learning_rate": 0.0002526512529912317,
      "loss": 2.2299,
      "step": 210
    },
    {
      "epoch": 1.51,
      "learning_rate": 0.00025110026899038105,
      "loss": 2.2391,
      "step": 213
    },
    {
      "epoch": 1.53,
      "learning_rate": 0.00024952922017509687,
      "loss": 2.1867,
      "step": 216
    },
    {
      "epoch": 1.55,
      "learning_rate": 0.00024793841834279824,
      "loss": 2.2197,
      "step": 219
    },
    {
      "epoch": 1.57,
      "learning_rate": 0.00024632817921117696,
      "loss": 2.1504,
      "step": 222
    },
    {
      "epoch": 1.59,
      "learning_rate": 0.0002446988223555388,
      "loss": 2.1684,
      "step": 225
    },
    {
      "epoch": 1.61,
      "learning_rate": 0.00024305067114537896,
      "loss": 2.1997,
      "step": 228
    },
    {
      "epoch": 1.63,
      "learning_rate": 0.0002413840526802049,
      "loss": 2.1836,
      "step": 231
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.00023969929772461865,
      "loss": 2.1628,
      "step": 234
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.0002379967406426717,
      "loss": 2.1886,
      "step": 237
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00023627671933150574,
      "loss": 2.1225,
      "step": 240
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00023453957515429192,
      "loss": 2.2524,
      "step": 243
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.0002327856528724825,
      "loss": 2.1975,
      "step": 246
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00023101530057738793,
      "loss": 2.1573,
      "step": 249
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00022922886962109296,
      "loss": 2.0817,
      "step": 252
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00022742671454672588,
      "loss": 2.1674,
      "step": 255
    },
    {
      "epoch": 1.83,
      "learning_rate": 0.00022560919301809414,
      "loss": 2.131,
      "step": 258
    },
    {
      "epoch": 1.85,
      "learning_rate": 0.00022377666574870103,
      "loss": 2.1338,
      "step": 261
    },
    {
      "epoch": 1.87,
      "learning_rate": 0.00022192949643015655,
      "loss": 2.1217,
      "step": 264
    },
    {
      "epoch": 1.89,
      "learning_rate": 0.00022006805165999764,
      "loss": 2.1887,
      "step": 267
    },
    {
      "epoch": 1.91,
      "learning_rate": 0.00021819270086893185,
      "loss": 2.1461,
      "step": 270
    },
    {
      "epoch": 1.93,
      "learning_rate": 0.00021630381624751795,
      "loss": 2.0757,
      "step": 273
    },
    {
      "epoch": 1.95,
      "learning_rate": 0.00021440177267229984,
      "loss": 2.1336,
      "step": 276
    },
    {
      "epoch": 1.97,
      "learning_rate": 0.0002124869476314064,
      "loss": 2.133,
      "step": 279
    },
    {
      "epoch": 1.99,
      "learning_rate": 0.0002105597211496339,
      "loss": 2.1556,
      "step": 282
    },
    {
      "epoch": 1.99,
      "eval_accuracy": 0.6236541534592513,
      "eval_loss": 2.058671236038208,
      "eval_runtime": 10.2746,
      "eval_samples_per_second": 196.309,
      "eval_steps_per_second": 98.203,
      "step": 282
    },
    {
      "epoch": 2.02,
      "learning_rate": 0.0002086204757130243,
      "loss": 2.6096,
      "step": 285
    },
    {
      "epoch": 2.04,
      "learning_rate": 0.0002066695961929554,
      "loss": 2.1364,
      "step": 288
    },
    {
      "epoch": 2.06,
      "learning_rate": 0.00020470746976975762,
      "loss": 2.0328,
      "step": 291
    },
    {
      "epoch": 2.08,
      "learning_rate": 0.00020273448585587248,
      "loss": 2.1069,
      "step": 294
    },
    {
      "epoch": 2.11,
      "learning_rate": 0.00020075103601856773,
      "loss": 2.1156,
      "step": 297
    },
    {
      "epoch": 2.13,
      "learning_rate": 0.00019875751390222566,
      "loss": 2.0617,
      "step": 300
    },
    {
      "epoch": 2.15,
      "learning_rate": 0.0001967543151502182,
      "loss": 2.1158,
      "step": 303
    },
    {
      "epoch": 2.17,
      "learning_rate": 0.00019474183732638608,
      "loss": 2.0996,
      "step": 306
    },
    {
      "epoch": 2.19,
      "learning_rate": 0.00019272047983613628,
      "loss": 2.1118,
      "step": 309
    },
    {
      "epoch": 2.21,
      "learning_rate": 0.00019069064384717442,
      "loss": 2.0661,
      "step": 312
    },
    {
      "epoch": 2.23,
      "learning_rate": 0.0001886527322098871,
      "loss": 2.0963,
      "step": 315
    },
    {
      "epoch": 2.25,
      "learning_rate": 0.00018660714937739043,
      "loss": 2.039,
      "step": 318
    },
    {
      "epoch": 2.28,
      "learning_rate": 0.00018455430132526047,
      "loss": 2.1014,
      "step": 321
    },
    {
      "epoch": 2.3,
      "learning_rate": 0.00018249459547096147,
      "loss": 2.1209,
      "step": 324
    },
    {
      "epoch": 2.32,
      "learning_rate": 0.00018042844059298798,
      "loss": 2.0982,
      "step": 327
    },
    {
      "epoch": 2.34,
      "learning_rate": 0.00017835624674973673,
      "loss": 2.0784,
      "step": 330
    },
    {
      "epoch": 2.36,
      "learning_rate": 0.00017627842519812485,
      "loss": 2.0276,
      "step": 333
    },
    {
      "epoch": 2.38,
      "learning_rate": 0.0001741953883119696,
      "loss": 2.0388,
      "step": 336
    },
    {
      "epoch": 2.4,
      "learning_rate": 0.00017210754950014714,
      "loss": 2.0352,
      "step": 339
    },
    {
      "epoch": 2.42,
      "learning_rate": 0.00017001532312454533,
      "loss": 2.0596,
      "step": 342
    },
    {
      "epoch": 2.44,
      "learning_rate": 0.00016791912441782778,
      "loss": 2.0419,
      "step": 345
    },
    {
      "epoch": 2.47,
      "learning_rate": 0.00016581936940102474,
      "loss": 2.1015,
      "step": 348
    },
    {
      "epoch": 2.49,
      "learning_rate": 0.00016371647480096783,
      "loss": 2.0491,
      "step": 351
    },
    {
      "epoch": 2.51,
      "learning_rate": 0.00016161085796758442,
      "loss": 2.0816,
      "step": 354
    },
    {
      "epoch": 2.53,
      "learning_rate": 0.00015950293679106852,
      "loss": 2.0958,
      "step": 357
    },
    {
      "epoch": 2.55,
      "learning_rate": 0.00015739312961894465,
      "loss": 2.084,
      "step": 360
    },
    {
      "epoch": 2.57,
      "learning_rate": 0.00015528185517304027,
      "loss": 2.0794,
      "step": 363
    },
    {
      "epoch": 2.59,
      "learning_rate": 0.00015316953246638482,
      "loss": 2.0948,
      "step": 366
    },
    {
      "epoch": 2.61,
      "learning_rate": 0.00015105658072005004,
      "loss": 2.0494,
      "step": 369
    },
    {
      "epoch": 2.63,
      "learning_rate": 0.00014894341927994994,
      "loss": 2.0161,
      "step": 372
    },
    {
      "epoch": 2.66,
      "learning_rate": 0.0001468304675336152,
      "loss": 2.0325,
      "step": 375
    },
    {
      "epoch": 2.68,
      "learning_rate": 0.00014471814482695968,
      "loss": 2.0537,
      "step": 378
    },
    {
      "epoch": 2.7,
      "learning_rate": 0.00014260687038105532,
      "loss": 2.0511,
      "step": 381
    },
    {
      "epoch": 2.72,
      "learning_rate": 0.00014049706320893148,
      "loss": 2.069,
      "step": 384
    },
    {
      "epoch": 2.74,
      "learning_rate": 0.0001383891420324156,
      "loss": 2.0702,
      "step": 387
    },
    {
      "epoch": 2.76,
      "learning_rate": 0.00013628352519903214,
      "loss": 2.0198,
      "step": 390
    },
    {
      "epoch": 2.78,
      "learning_rate": 0.00013418063059897524,
      "loss": 2.0515,
      "step": 393
    },
    {
      "epoch": 2.8,
      "learning_rate": 0.0001320808755821722,
      "loss": 2.0652,
      "step": 396
    },
    {
      "epoch": 2.83,
      "learning_rate": 0.00012998467687545465,
      "loss": 2.0401,
      "step": 399
    },
    {
      "epoch": 2.85,
      "learning_rate": 0.00012789245049985284,
      "loss": 1.9955,
      "step": 402
    },
    {
      "epoch": 2.87,
      "learning_rate": 0.00012580461168803036,
      "loss": 1.9932,
      "step": 405
    },
    {
      "epoch": 2.89,
      "learning_rate": 0.00012372157480187513,
      "loss": 1.9957,
      "step": 408
    },
    {
      "epoch": 2.91,
      "learning_rate": 0.00012164375325026323,
      "loss": 2.0278,
      "step": 411
    },
    {
      "epoch": 2.93,
      "learning_rate": 0.00011957155940701203,
      "loss": 2.0055,
      "step": 414
    },
    {
      "epoch": 2.95,
      "learning_rate": 0.00011750540452903852,
      "loss": 2.1282,
      "step": 417
    },
    {
      "epoch": 2.97,
      "learning_rate": 0.00011544569867473953,
      "loss": 2.0752,
      "step": 420
    },
    {
      "epoch": 2.99,
      "learning_rate": 0.00011339285062260957,
      "loss": 2.0616,
      "step": 423
    },
    {
      "epoch": 2.99,
      "eval_accuracy": 0.6354889456059845,
      "eval_loss": 1.9779837131500244,
      "eval_runtime": 10.2076,
      "eval_samples_per_second": 197.597,
      "eval_steps_per_second": 98.848,
      "step": 423
    },
    {
      "epoch": 3.02,
      "learning_rate": 0.00011134726779011288,
      "loss": 2.5405,
      "step": 426
    },
    {
      "epoch": 3.04,
      "learning_rate": 0.00010930935615282558,
      "loss": 2.0141,
      "step": 429
    },
    {
      "epoch": 3.06,
      "learning_rate": 0.00010727952016386371,
      "loss": 2.039,
      "step": 432
    },
    {
      "epoch": 3.08,
      "learning_rate": 0.00010525816267361396,
      "loss": 2.0632,
      "step": 435
    },
    {
      "epoch": 3.11,
      "learning_rate": 0.00010324568484978182,
      "loss": 1.9622,
      "step": 438
    },
    {
      "epoch": 3.13,
      "learning_rate": 0.00010124248609777434,
      "loss": 2.0226,
      "step": 441
    },
    {
      "epoch": 3.15,
      "learning_rate": 9.924896398143224e-05,
      "loss": 2.0174,
      "step": 444
    },
    {
      "epoch": 3.17,
      "learning_rate": 9.726551414412753e-05,
      "loss": 1.9791,
      "step": 447
    },
    {
      "epoch": 3.19,
      "learning_rate": 9.529253023024234e-05,
      "loss": 2.0418,
      "step": 450
    },
    {
      "epoch": 3.21,
      "learning_rate": 9.33304038070446e-05,
      "loss": 1.9825,
      "step": 453
    },
    {
      "epoch": 3.23,
      "learning_rate": 9.137952428697568e-05,
      "loss": 2.0014,
      "step": 456
    },
    {
      "epoch": 3.25,
      "learning_rate": 8.944027885036605e-05,
      "loss": 1.9395,
      "step": 459
    },
    {
      "epoch": 3.28,
      "learning_rate": 8.751305236859359e-05,
      "loss": 2.0189,
      "step": 462
    },
    {
      "epoch": 3.3,
      "learning_rate": 8.559822732770019e-05,
      "loss": 1.9629,
      "step": 465
    },
    {
      "epoch": 3.32,
      "learning_rate": 8.3696183752482e-05,
      "loss": 2.0085,
      "step": 468
    },
    {
      "epoch": 3.34,
      "learning_rate": 8.180729913106815e-05,
      "loss": 1.9725,
      "step": 471
    },
    {
      "epoch": 3.36,
      "learning_rate": 7.993194834000229e-05,
      "loss": 1.9946,
      "step": 474
    },
    {
      "epoch": 3.38,
      "learning_rate": 7.807050356984345e-05,
      "loss": 2.0058,
      "step": 477
    },
    {
      "epoch": 3.4,
      "learning_rate": 7.622333425129895e-05,
      "loss": 2.0525,
      "step": 480
    },
    {
      "epoch": 3.42,
      "learning_rate": 7.439080698190579e-05,
      "loss": 1.9817,
      "step": 483
    },
    {
      "epoch": 3.44,
      "learning_rate": 7.25732854532741e-05,
      "loss": 2.0297,
      "step": 486
    },
    {
      "epoch": 3.47,
      "learning_rate": 7.077113037890702e-05,
      "loss": 2.0163,
      "step": 489
    },
    {
      "epoch": 3.49,
      "learning_rate": 6.898469942261206e-05,
      "loss": 2.0449,
      "step": 492
    },
    {
      "epoch": 3.51,
      "learning_rate": 6.721434712751744e-05,
      "loss": 1.9419,
      "step": 495
    },
    {
      "epoch": 3.53,
      "learning_rate": 6.546042484570807e-05,
      "loss": 2.0181,
      "step": 498
    },
    {
      "epoch": 3.55,
      "learning_rate": 6.372328066849426e-05,
      "loss": 1.9761,
      "step": 501
    },
    {
      "epoch": 3.57,
      "learning_rate": 6.200325935732827e-05,
      "loss": 1.9969,
      "step": 504
    },
    {
      "epoch": 3.59,
      "learning_rate": 6.030070227538133e-05,
      "loss": 1.9515,
      "step": 507
    },
    {
      "epoch": 3.61,
      "learning_rate": 5.8615947319795044e-05,
      "loss": 2.0222,
      "step": 510
    },
    {
      "epoch": 3.63,
      "learning_rate": 5.6949328854621045e-05,
      "loss": 2.0148,
      "step": 513
    },
    {
      "epoch": 3.66,
      "learning_rate": 5.5301177644461164e-05,
      "loss": 2.0086,
      "step": 516
    },
    {
      "epoch": 3.68,
      "learning_rate": 5.367182078882299e-05,
      "loss": 2.0048,
      "step": 519
    },
    {
      "epoch": 3.7,
      "learning_rate": 5.206158165720175e-05,
      "loss": 1.967,
      "step": 522
    },
    {
      "epoch": 3.72,
      "learning_rate": 5.04707798249031e-05,
      "loss": 1.9731,
      "step": 525
    },
    {
      "epoch": 3.74,
      "learning_rate": 4.889973100961892e-05,
      "loss": 1.961,
      "step": 528
    },
    {
      "epoch": 3.76,
      "learning_rate": 4.734874700876826e-05,
      "loss": 1.9674,
      "step": 531
    },
    {
      "epoch": 3.78,
      "learning_rate": 4.5818135637616936e-05,
      "loss": 1.9797,
      "step": 534
    },
    {
      "epoch": 3.8,
      "learning_rate": 4.430820066818692e-05,
      "loss": 2.0148,
      "step": 537
    },
    {
      "epoch": 3.83,
      "learning_rate": 4.281924176896837e-05,
      "loss": 1.9882,
      "step": 540
    },
    {
      "epoch": 3.85,
      "learning_rate": 4.13515544454462e-05,
      "loss": 1.9908,
      "step": 543
    },
    {
      "epoch": 3.87,
      "learning_rate": 3.990542998145262e-05,
      "loss": 1.9337,
      "step": 546
    },
    {
      "epoch": 3.89,
      "learning_rate": 3.8481155381357825e-05,
      "loss": 1.9709,
      "step": 549
    },
    {
      "epoch": 3.91,
      "learning_rate": 3.7079013313109535e-05,
      "loss": 1.9485,
      "step": 552
    },
    {
      "epoch": 3.93,
      "learning_rate": 3.569928205213354e-05,
      "loss": 1.955,
      "step": 555
    },
    {
      "epoch": 3.95,
      "learning_rate": 3.434223542610615e-05,
      "loss": 1.9797,
      "step": 558
    },
    {
      "epoch": 3.97,
      "learning_rate": 3.30081427606087e-05,
      "loss": 1.9471,
      "step": 561
    },
    {
      "epoch": 3.99,
      "learning_rate": 3.169726882567642e-05,
      "loss": 2.0084,
      "step": 564
    },
    {
      "epoch": 3.99,
      "eval_accuracy": 0.6422005133308889,
      "eval_loss": 1.9317268133163452,
      "eval_runtime": 10.2419,
      "eval_samples_per_second": 196.936,
      "eval_steps_per_second": 98.517,
      "step": 564
    },
    {
      "epoch": 4.02,
      "learning_rate": 3.0409873783250476e-05,
      "loss": 2.5298,
      "step": 567
    },
    {
      "epoch": 4.04,
      "learning_rate": 2.914621313554567e-05,
      "loss": 1.9335,
      "step": 570
    },
    {
      "epoch": 4.06,
      "learning_rate": 2.790653767434181e-05,
      "loss": 1.9663,
      "step": 573
    },
    {
      "epoch": 4.08,
      "learning_rate": 2.6691093431210596e-05,
      "loss": 1.9546,
      "step": 576
    },
    {
      "epoch": 4.11,
      "learning_rate": 2.550012162868731e-05,
      "loss": 1.9588,
      "step": 579
    },
    {
      "epoch": 4.13,
      "learning_rate": 2.4333858632396336e-05,
      "loss": 1.9079,
      "step": 582
    },
    {
      "epoch": 4.15,
      "learning_rate": 2.319253590414132e-05,
      "loss": 1.9706,
      "step": 585
    },
    {
      "epoch": 4.17,
      "learning_rate": 2.207637995596791e-05,
      "loss": 1.9244,
      "step": 588
    },
    {
      "epoch": 4.19,
      "learning_rate": 2.0985612305209404e-05,
      "loss": 1.9571,
      "step": 591
    },
    {
      "epoch": 4.21,
      "learning_rate": 1.9920449430523266e-05,
      "loss": 1.9935,
      "step": 594
    },
    {
      "epoch": 4.23,
      "learning_rate": 1.8881102728927854e-05,
      "loss": 1.965,
      "step": 597
    },
    {
      "epoch": 4.25,
      "learning_rate": 1.7867778473847695e-05,
      "loss": 1.9879,
      "step": 600
    },
    {
      "epoch": 4.28,
      "learning_rate": 1.6880677774175354e-05,
      "loss": 1.9765,
      "step": 603
    },
    {
      "epoch": 4.3,
      "learning_rate": 1.5919996534358635e-05,
      "loss": 1.9608,
      "step": 606
    },
    {
      "epoch": 4.32,
      "learning_rate": 1.4985925415520395e-05,
      "loss": 1.8867,
      "step": 609
    },
    {
      "epoch": 4.34,
      "learning_rate": 1.407864979761908e-05,
      "loss": 1.9532,
      "step": 612
    },
    {
      "epoch": 4.36,
      "learning_rate": 1.31983497426575e-05,
      "loss": 1.9672,
      "step": 615
    },
    {
      "epoch": 4.38,
      "learning_rate": 1.2345199958946673e-05,
      "loss": 1.9372,
      "step": 618
    },
    {
      "epoch": 4.4,
      "learning_rate": 1.1519369766432762e-05,
      "loss": 1.9676,
      "step": 621
    },
    {
      "epoch": 4.42,
      "learning_rate": 1.072102306309276e-05,
      "loss": 1.9726,
      "step": 624
    },
    {
      "epoch": 4.44,
      "learning_rate": 9.950318292406816e-06,
      "loss": 1.9565,
      "step": 627
    },
    {
      "epoch": 4.47,
      "learning_rate": 9.207408411912603e-06,
      "loss": 2.0322,
      "step": 630
    },
    {
      "epoch": 4.49,
      "learning_rate": 8.492440862848787e-06,
      "loss": 1.9868,
      "step": 633
    },
    {
      "epoch": 4.51,
      "learning_rate": 7.805557540893276e-06,
      "loss": 1.9788,
      "step": 636
    },
    {
      "epoch": 4.53,
      "learning_rate": 7.146894768001743e-06,
      "loss": 1.9226,
      "step": 639
    },
    {
      "epoch": 4.55,
      "learning_rate": 6.516583265352754e-06,
      "loss": 1.9214,
      "step": 642
    },
    {
      "epoch": 4.57,
      "learning_rate": 5.914748127404101e-06,
      "loss": 1.9815,
      "step": 645
    },
    {
      "epoch": 4.59,
      "learning_rate": 5.34150879706613e-06,
      "loss": 1.916,
      "step": 648
    },
    {
      "epoch": 4.61,
      "learning_rate": 4.796979041996485e-06,
      "loss": 1.9162,
      "step": 651
    },
    {
      "epoch": 4.63,
      "learning_rate": 4.2812669320212375e-06,
      "loss": 1.9955,
      "step": 654
    },
    {
      "epoch": 4.66,
      "learning_rate": 3.7944748176869766e-06,
      "loss": 1.926,
      "step": 657
    },
    {
      "epoch": 4.68,
      "learning_rate": 3.336699309947721e-06,
      "loss": 1.9637,
      "step": 660
    },
    {
      "epoch": 4.7,
      "learning_rate": 2.908031260991195e-06,
      "loss": 1.9602,
      "step": 663
    },
    {
      "epoch": 4.72,
      "learning_rate": 2.5085557462078134e-06,
      "loss": 2.0124,
      "step": 666
    },
    {
      "epoch": 4.74,
      "learning_rate": 2.1383520473062743e-06,
      "loss": 1.9393,
      "step": 669
    },
    {
      "epoch": 4.76,
      "learning_rate": 1.7974936365789116e-06,
      "loss": 1.8888,
      "step": 672
    },
    {
      "epoch": 4.78,
      "learning_rate": 1.4860481623201414e-06,
      "loss": 1.9409,
      "step": 675
    },
    {
      "epoch": 4.8,
      "learning_rate": 1.2040774354005856e-06,
      "loss": 1.9617,
      "step": 678
    },
    {
      "epoch": 4.83,
      "learning_rate": 9.516374169998508e-07,
      "loss": 1.9433,
      "step": 681
    },
    {
      "epoch": 4.85,
      "learning_rate": 7.287782075002302e-07,
      "loss": 2.0248,
      "step": 684
    },
    {
      "epoch": 4.87,
      "learning_rate": 5.355440365434893e-07,
      "loss": 1.9528,
      "step": 687
    },
    {
      "epoch": 4.89,
      "learning_rate": 3.7197325425297186e-07,
      "loss": 1.9823,
      "step": 690
    },
    {
      "epoch": 4.91,
      "learning_rate": 2.380983236223377e-07,
      "loss": 1.9716,
      "step": 693
    },
    {
      "epoch": 4.93,
      "learning_rate": 1.3394581407289996e-07,
      "loss": 1.9205,
      "step": 696
    },
    {
      "epoch": 4.95,
      "learning_rate": 5.9536396180492886e-08,
      "loss": 1.953,
      "step": 699
    },
    {
      "epoch": 4.97,
      "learning_rate": 1.4884837573087006e-08,
      "loss": 2.0213,
      "step": 702
    },
    {
      "epoch": 4.99,
      "learning_rate": 0.0,
      "loss": 1.9621,
      "step": 705
    },
    {
      "epoch": 4.99,
      "eval_accuracy": 0.6451979106514778,
      "eval_loss": 1.9133403301239014,
      "eval_runtime": 10.2297,
      "eval_samples_per_second": 197.171,
      "eval_steps_per_second": 98.634,
      "step": 705
    },
    {
      "epoch": 4.99,
      "step": 705,
      "total_flos": 4119345677467648.0,
      "train_loss": 2.1596999946215476,
      "train_runtime": 1037.2411,
      "train_samples_per_second": 87.439,
      "train_steps_per_second": 0.68
    }
  ],
  "max_steps": 705,
  "num_train_epochs": 5,
  "total_flos": 4119345677467648.0,
  "trial_name": null,
  "trial_params": null
}