{
  "best_metric": 0.4552081823348999,
  "best_model_checkpoint": "output/eminem/checkpoint-916",
  "epoch": 2.0,
  "global_step": 916,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 1.1101848202700968e-05,
      "loss": 0.9307,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.2436573272248617e-05,
      "loss": 0.927,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.3839120682350837e-05,
      "loss": 0.8453,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.530779673208073e-05,
      "loss": 0.7711,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 1.6840827864285403e-05,
      "loss": 0.7411,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.8436362807313432e-05,
      "loss": 0.718,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 2.0092474810601945e-05,
      "loss": 0.8948,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 2.1807163971388184e-05,
      "loss": 0.8375,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 2.3578359649769493e-05,
      "loss": 0.8776,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 2.5403922969198425e-05,
      "loss": 0.8974,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 2.7281649399354026e-05,
      "loss": 0.9192,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 2.9209271418307854e-05,
      "loss": 0.8816,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 3.1184461250772885e-05,
      "loss": 0.8526,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 3.320483367908558e-05,
      "loss": 0.9859,
      "step": 70
    },
    {
      "epoch": 0.17,
      "learning_rate": 3.526794892356815e-05,
      "loss": 0.8333,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 3.737131558879495e-05,
      "loss": 0.8473,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 3.951239367215769e-05,
      "loss": 0.7829,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.16885976311532e-05,
      "loss": 0.8359,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.3897299505656445e-05,
      "loss": 0.8274,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.613583209140736e-05,
      "loss": 0.8593,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.8401492160915815e-05,
      "loss": 0.8646,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 5.0691543727833204e-05,
      "loss": 0.8086,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 5.300322135089945e-05,
      "loss": 0.8503,
      "step": 115
    },
    {
      "epoch": 0.27,
      "learning_rate": 5.533373347347659e-05,
      "loss": 0.8456,
      "step": 120
    },
    {
      "epoch": 0.28,
      "learning_rate": 5.768026579458521e-05,
      "loss": 0.8796,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 6.0039984667423376e-05,
      "loss": 0.9052,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 6.241004052126484e-05,
      "loss": 0.8889,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 6.478757130255232e-05,
      "loss": 0.7601,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 6.716970593108191e-05,
      "loss": 0.9798,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 6.955356776710577e-05,
      "loss": 0.8511,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 7.19362780851133e-05,
      "loss": 0.707,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 7.431495955014867e-05,
      "loss": 0.8309,
      "step": 160
    },
    {
      "epoch": 0.37,
      "learning_rate": 7.668673969246653e-05,
      "loss": 0.9937,
      "step": 165
    },
    {
      "epoch": 0.38,
      "learning_rate": 7.904875437627569e-05,
      "loss": 0.8724,
      "step": 170
    },
    {
      "epoch": 0.39,
      "learning_rate": 8.139815125844789e-05,
      "loss": 0.8768,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.373209323297431e-05,
      "loss": 0.8486,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.604776185702375e-05,
      "loss": 0.8148,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.834236075446345e-05,
      "loss": 0.7431,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 9.061311899273227e-05,
      "loss": 1.0625,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 9.285729442898867e-05,
      "loss": 0.9774,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 9.507217702149242e-05,
      "loss": 0.9555,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 9.725509210222139e-05,
      "loss": 0.8318,
      "step": 210
    },
    {
      "epoch": 0.48,
      "learning_rate": 9.940340360677143e-05,
      "loss": 1.0049,
      "step": 215
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00010151451725763896,
      "loss": 0.9011,
      "step": 220
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00010358588369704216,
      "loss": 0.9322,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00010561500156549749,
      "loss": 0.9422,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00010759942052243423,
      "loss": 0.8211,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.0001095367442051988,
      "loss": 0.9219,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001114246331228763,
      "loss": 0.9815,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.00011326080748143405,
      "loss": 0.8863,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00011504304993677604,
      "loss": 0.9774,
      "step": 255
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.00011676920827238334,
      "loss": 0.8713,
      "step": 260
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00011843719799830738,
      "loss": 0.8571,
      "step": 265
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00012004500486837717,
      "loss": 0.7939,
      "step": 270
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00012159068731258093,
      "loss": 0.9422,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.00012307237878168492,
      "loss": 0.7881,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00012448829000125786,
      "loss": 0.9368,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00012583671113237919,
      "loss": 1.0178,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00012711601383642182,
      "loss": 0.9968,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00012832465324141612,
      "loss": 0.9213,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001294611698076205,
      "loss": 0.9773,
      "step": 305
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.0001305241910900455,
      "loss": 0.9827,
      "step": 310
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001315124333958035,
      "loss": 0.9033,
      "step": 315
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.00013242470333428216,
      "loss": 0.8958,
      "step": 320
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00013325989925826927,
      "loss": 0.9264,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00013401701259429304,
      "loss": 1.079,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001346951290605581,
      "loss": 0.9806,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00013529342977102813,
      "loss": 0.86,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.0001358111922243026,
      "loss": 1.0011,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.00013624779117609796,
      "loss": 0.9809,
      "step": 350
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00013660269939428984,
      "loss": 1.0322,
      "step": 355
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00013687548829559193,
      "loss": 0.9118,
      "step": 360
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00013706582846310632,
      "loss": 1.0066,
      "step": 365
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00013717349004412635,
      "loss": 0.8286,
      "step": 370
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00013719834302770308,
      "loss": 0.9167,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00013714035740164485,
      "loss": 1.0906,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001369996031887605,
      "loss": 0.799,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.0001367762503622993,
      "loss": 1.0021,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00013647056864069494,
      "loss": 0.8576,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00013608292716185523,
      "loss": 0.8256,
      "step": 400
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.00013561379403739408,
      "loss": 0.9425,
      "step": 405
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00013506373578734917,
      "loss": 1.1332,
      "step": 410
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00013443341665605278,
      "loss": 1.0371,
      "step": 415
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00013372359781000178,
      "loss": 0.9845,
      "step": 420
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.000132935136418682,
      "loss": 0.9044,
      "step": 425
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00013206898461945424,
      "loss": 0.9425,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.0001311261883677687,
      "loss": 0.9473,
      "step": 435
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00013010788617408173,
      "loss": 0.9766,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.0001290153077289955,
      "loss": 1.085,
      "step": 445
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00012784977241830426,
      "loss": 1.0372,
      "step": 450
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.6593805551528931,
      "eval_runtime": 29.3303,
      "eval_samples_per_second": 22.605,
      "eval_steps_per_second": 2.83,
      "step": 452
    },
    {
      "epoch": 1.01,
      "learning_rate": 0.0001266126877297192,
      "loss": 0.9529,
      "step": 455
    },
    {
      "epoch": 1.02,
      "learning_rate": 0.00012530554755319265,
      "loss": 0.8043,
      "step": 460
    },
    {
      "epoch": 1.03,
      "learning_rate": 0.0001239299303769218,
      "loss": 0.813,
      "step": 465
    },
    {
      "epoch": 1.04,
      "learning_rate": 0.00012248749738118413,
      "loss": 0.7686,
      "step": 470
    },
    {
      "epoch": 1.05,
      "learning_rate": 0.00012097999043230392,
      "loss": 0.816,
      "step": 475
    },
    {
      "epoch": 1.06,
      "learning_rate": 0.00011940922997920501,
      "loss": 0.7366,
      "step": 480
    },
    {
      "epoch": 1.07,
      "learning_rate": 0.0001177771128550507,
      "loss": 0.8555,
      "step": 485
    },
    {
      "epoch": 1.08,
      "learning_rate": 0.00011608560998665,
      "loss": 0.8056,
      "step": 490
    },
    {
      "epoch": 1.1,
      "learning_rate": 0.00011433676401438789,
      "loss": 0.8315,
      "step": 495
    },
    {
      "epoch": 1.11,
      "learning_rate": 0.00011253268682555513,
      "loss": 0.8243,
      "step": 500
    },
    {
      "epoch": 1.12,
      "learning_rate": 0.00011067555700405623,
      "loss": 0.9237,
      "step": 505
    },
    {
      "epoch": 1.13,
      "learning_rate": 0.00010876761719957537,
      "loss": 0.7665,
      "step": 510
    },
    {
      "epoch": 1.14,
      "learning_rate": 0.00010681117141937706,
      "loss": 0.8168,
      "step": 515
    },
    {
      "epoch": 1.15,
      "learning_rate": 0.00010480858224601222,
      "loss": 0.8501,
      "step": 520
    },
    {
      "epoch": 1.16,
      "learning_rate": 0.0001027622679842892,
      "loss": 0.7442,
      "step": 525
    },
    {
      "epoch": 1.17,
      "learning_rate": 0.00010067469974095542,
      "loss": 0.9166,
      "step": 530
    },
    {
      "epoch": 1.18,
      "learning_rate": 9.854839844061585e-05,
      "loss": 0.8625,
      "step": 535
    },
    {
      "epoch": 1.19,
      "learning_rate": 9.638593178149185e-05,
      "loss": 0.9546,
      "step": 540
    },
    {
      "epoch": 1.21,
      "learning_rate": 9.418991113469707e-05,
      "loss": 0.943,
      "step": 545
    },
    {
      "epoch": 1.22,
      "learning_rate": 9.196298839077406e-05,
      "loss": 0.831,
      "step": 550
    },
    {
      "epoch": 1.23,
      "learning_rate": 8.970785275730025e-05,
      "loss": 0.922,
      "step": 555
    },
    {
      "epoch": 1.24,
      "learning_rate": 8.742722751143034e-05,
      "loss": 0.9578,
      "step": 560
    },
    {
      "epoch": 1.25,
      "learning_rate": 8.512386671129642e-05,
      "loss": 0.7693,
      "step": 565
    },
    {
      "epoch": 1.26,
      "learning_rate": 8.280055187023758e-05,
      "loss": 0.917,
      "step": 570
    },
    {
      "epoch": 1.27,
      "learning_rate": 8.046008859787475e-05,
      "loss": 0.9697,
      "step": 575
    },
    {
      "epoch": 1.28,
      "learning_rate": 7.810530321208715e-05,
      "loss": 0.9031,
      "step": 580
    },
    {
      "epoch": 1.29,
      "learning_rate": 7.573903932598171e-05,
      "loss": 0.9128,
      "step": 585
    },
    {
      "epoch": 1.31,
      "learning_rate": 7.336415441397694e-05,
      "loss": 0.8281,
      "step": 590
    },
    {
      "epoch": 1.32,
      "learning_rate": 7.098351636114803e-05,
      "loss": 0.8862,
      "step": 595
    },
    {
      "epoch": 1.33,
      "learning_rate": 6.860000000000023e-05,
      "loss": 0.7457,
      "step": 600
    },
    {
      "epoch": 1.34,
      "learning_rate": 6.621648363885243e-05,
      "loss": 0.8978,
      "step": 605
    },
    {
      "epoch": 1.35,
      "learning_rate": 6.383584558602354e-05,
      "loss": 0.844,
      "step": 610
    },
    {
      "epoch": 1.36,
      "learning_rate": 6.146096067401875e-05,
      "loss": 0.8293,
      "step": 615
    },
    {
      "epoch": 1.37,
      "learning_rate": 5.9094696787913304e-05,
      "loss": 0.6208,
      "step": 620
    },
    {
      "epoch": 1.38,
      "learning_rate": 5.6739911402125706e-05,
      "loss": 0.8256,
      "step": 625
    },
    {
      "epoch": 1.39,
      "learning_rate": 5.439944812976288e-05,
      "loss": 0.8516,
      "step": 630
    },
    {
      "epoch": 1.4,
      "learning_rate": 5.207613328870404e-05,
      "loss": 0.75,
      "step": 635
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.977277248857012e-05,
      "loss": 0.8606,
      "step": 640
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.749214724270019e-05,
      "loss": 0.7975,
      "step": 645
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.5237011609228214e-05,
      "loss": 0.8932,
      "step": 650
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.301008886530336e-05,
      "loss": 0.8424,
      "step": 655
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.081406821850858e-05,
      "loss": 0.8577,
      "step": 660
    },
    {
      "epoch": 1.47,
      "learning_rate": 3.865160155938634e-05,
      "loss": 0.7893,
      "step": 665
    },
    {
      "epoch": 1.48,
      "learning_rate": 3.6525300259044984e-05,
      "loss": 0.7793,
      "step": 670
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.443773201571122e-05,
      "loss": 0.8193,
      "step": 675
    },
    {
      "epoch": 1.5,
      "learning_rate": 3.239141775398985e-05,
      "loss": 0.8577,
      "step": 680
    },
    {
      "epoch": 1.52,
      "learning_rate": 3.0388828580623328e-05,
      "loss": 0.9107,
      "step": 685
    },
    {
      "epoch": 1.53,
      "learning_rate": 2.8432382800425017e-05,
      "loss": 0.8879,
      "step": 690
    },
    {
      "epoch": 1.54,
      "learning_rate": 2.6524442995945684e-05,
      "loss": 0.8339,
      "step": 695
    },
    {
      "epoch": 1.55,
      "learning_rate": 2.466731317444525e-05,
      "loss": 0.8466,
      "step": 700
    },
    {
      "epoch": 1.56,
      "learning_rate": 2.2863235985612475e-05,
      "loss": 0.7456,
      "step": 705
    },
    {
      "epoch": 1.57,
      "learning_rate": 2.111439001335175e-05,
      "loss": 0.7,
      "step": 710
    },
    {
      "epoch": 1.58,
      "learning_rate": 1.942288714494962e-05,
      "loss": 0.7208,
      "step": 715
    },
    {
      "epoch": 1.59,
      "learning_rate": 1.77907700207953e-05,
      "loss": 0.8998,
      "step": 720
    },
    {
      "epoch": 1.6,
      "learning_rate": 1.6220009567697634e-05,
      "loss": 0.8058,
      "step": 725
    },
    {
      "epoch": 1.62,
      "learning_rate": 1.471250261881617e-05,
      "loss": 0.8065,
      "step": 730
    },
    {
      "epoch": 1.63,
      "learning_rate": 1.3270069623078497e-05,
      "loss": 0.7645,
      "step": 735
    },
    {
      "epoch": 1.64,
      "learning_rate": 1.1894452446808717e-05,
      "loss": 0.8453,
      "step": 740
    },
    {
      "epoch": 1.65,
      "learning_rate": 1.0587312270281075e-05,
      "loss": 0.8016,
      "step": 745
    },
    {
      "epoch": 1.66,
      "learning_rate": 9.350227581695975e-06,
      "loss": 0.8662,
      "step": 750
    },
    {
      "epoch": 1.67,
      "learning_rate": 8.184692271005631e-06,
      "loss": 0.7792,
      "step": 755
    },
    {
      "epoch": 1.68,
      "learning_rate": 7.0921138259184885e-06,
      "loss": 0.8576,
      "step": 760
    },
    {
      "epoch": 1.69,
      "learning_rate": 6.0738116322314975e-06,
      "loss": 0.8999,
      "step": 765
    },
    {
      "epoch": 1.7,
      "learning_rate": 5.131015380545945e-06,
      "loss": 0.7444,
      "step": 770
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.264863581318154e-06,
      "loss": 0.8574,
      "step": 775
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.4764021899983686e-06,
      "loss": 0.8041,
      "step": 780
    },
    {
      "epoch": 1.74,
      "learning_rate": 2.76658334394734e-06,
      "loss": 0.9527,
      "step": 785
    },
    {
      "epoch": 1.75,
      "learning_rate": 2.1362642126509516e-06,
      "loss": 0.8828,
      "step": 790
    },
    {
      "epoch": 1.76,
      "learning_rate": 1.5862059626060031e-06,
      "loss": 0.8653,
      "step": 795
    },
    {
      "epoch": 1.77,
      "learning_rate": 1.1170728381448706e-06,
      "loss": 0.7422,
      "step": 800
    },
    {
      "epoch": 1.78,
      "learning_rate": 7.294313593051277e-07,
      "loss": 0.8688,
      "step": 805
    },
    {
      "epoch": 1.79,
      "learning_rate": 4.2374963770076367e-07,
      "loss": 0.8754,
      "step": 810
    },
    {
      "epoch": 1.8,
      "learning_rate": 2.0039681123955346e-07,
      "loss": 0.8108,
      "step": 815
    },
    {
      "epoch": 1.81,
      "learning_rate": 5.964259835515342e-08,
      "loss": 0.7736,
      "step": 820
    },
    {
      "epoch": 1.83,
      "learning_rate": 1.6569722969213219e-09,
      "loss": 0.919,
      "step": 825
    },
    {
      "epoch": 1.84,
      "learning_rate": 2.6509955873622614e-08,
      "loss": 0.9207,
      "step": 830
    },
    {
      "epoch": 1.85,
      "learning_rate": 1.34171536893634e-07,
      "loss": 0.7721,
      "step": 835
    },
    {
      "epoch": 1.86,
      "learning_rate": 3.245117044080267e-07,
      "loss": 0.9383,
      "step": 840
    },
    {
      "epoch": 1.87,
      "learning_rate": 5.973006057101013e-07,
      "loss": 0.8004,
      "step": 845
    },
    {
      "epoch": 1.88,
      "learning_rate": 9.522088239019613e-07,
      "loss": 0.8358,
      "step": 850
    },
    {
      "epoch": 1.89,
      "learning_rate": 1.388807775697303e-06,
      "loss": 0.7995,
      "step": 855
    },
    {
      "epoch": 1.9,
      "learning_rate": 1.9065702289717794e-06,
      "loss": 0.8778,
      "step": 860
    },
    {
      "epoch": 1.91,
      "learning_rate": 2.504870939441761e-06,
      "loss": 0.7698,
      "step": 865
    },
    {
      "epoch": 1.92,
      "learning_rate": 3.1829874057068102e-06,
      "loss": 0.7713,
      "step": 870
    },
    {
      "epoch": 1.94,
      "learning_rate": 3.940100741730584e-06,
      "loss": 0.7167,
      "step": 875
    },
    {
      "epoch": 1.95,
      "learning_rate": 4.775296665717651e-06,
      "loss": 0.7112,
      "step": 880
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.687566604196296e-06,
      "loss": 0.7375,
      "step": 885
    },
    {
      "epoch": 1.97,
      "learning_rate": 6.675808909954285e-06,
      "loss": 0.7607,
      "step": 890
    },
    {
      "epoch": 1.98,
      "learning_rate": 7.738830192379277e-06,
      "loss": 0.7172,
      "step": 895
    },
    {
      "epoch": 1.99,
      "learning_rate": 8.875346758583638e-06,
      "loss": 0.8977,
      "step": 900
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.6314056515693665,
      "eval_runtime": 29.5306,
      "eval_samples_per_second": 22.451,
      "eval_steps_per_second": 2.811,
      "step": 904
    },
    {
      "epoch": 1.98,
      "learning_rate": 4.5530896428035615e-05,
      "loss": 0.6893,
      "step": 905
    },
    {
      "epoch": 1.99,
      "learning_rate": 4.3329156273475095e-05,
      "loss": 0.9131,
      "step": 910
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.115713866225047e-05,
      "loss": 0.8774,
      "step": 915
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.4552081823348999,
      "eval_runtime": 27.3413,
      "eval_samples_per_second": 22.64,
      "eval_steps_per_second": 2.853,
      "step": 916
    }
  ],
  "max_steps": 1374,
  "num_train_epochs": 3,
  "total_flos": 956198191104000.0,
  "trial_name": null,
  "trial_params": null
}