{
  "best_metric": 3.417607307434082,
  "best_model_checkpoint": "output/snoop-dogg/checkpoint-538",
  "epoch": 1.0,
  "global_step": 538,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 0.00013717076261874923,
      "loss": 4.1063,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 0.00013708307539699282,
      "loss": 4.1679,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.00013693701307947525,
      "loss": 4.0154,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001367327001699768,
      "loss": 3.9048,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00013647031082518634,
      "loss": 3.9959,
      "step": 25
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013615006870624992,
      "loss": 3.8299,
      "step": 30
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013577224678812164,
      "loss": 3.7535,
      "step": 35
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.00013533716712687914,
      "loss": 3.7139,
      "step": 40
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001348452005852027,
      "loss": 3.5272,
      "step": 45
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.00013429676651625084,
      "loss": 3.9259,
      "step": 50
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.0001336923324062034,
      "loss": 3.646,
      "step": 55
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00013303241347577507,
      "loss": 3.7353,
      "step": 60
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00013231757224104065,
      "loss": 3.7269,
      "step": 65
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.0001315484180339451,
      "loss": 3.6971,
      "step": 70
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001307256064829081,
      "loss": 3.6029,
      "step": 75
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.00012984983895396502,
      "loss": 3.6687,
      "step": 80
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00012892186195292147,
      "loss": 3.5599,
      "step": 85
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00012794246648903024,
      "loss": 3.4859,
      "step": 90
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00012691248740073373,
      "loss": 3.7556,
      "step": 95
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00012583280264404602,
      "loss": 3.6952,
      "step": 100
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012470433254418178,
      "loss": 3.7874,
      "step": 105
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012352803901106928,
      "loss": 3.6861,
      "step": 110
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00012230492471941668,
      "loss": 3.7332,
      "step": 115
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00012103603225403036,
      "loss": 3.6027,
      "step": 120
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00011972244322111374,
      "loss": 3.6728,
      "step": 125
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011836527732630418,
      "loss": 3.6239,
      "step": 130
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00011696569142023398,
      "loss": 3.6474,
      "step": 135
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00011552487851242871,
      "loss": 3.6182,
      "step": 140
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00011404406675438398,
      "loss": 3.6673,
      "step": 145
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00011252451839268661,
      "loss": 3.6792,
      "step": 150
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00011096752869307368,
      "loss": 3.7147,
      "step": 155
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.0001093744248363455,
      "loss": 3.7344,
      "step": 160
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001077465647870744,
      "loss": 3.672,
      "step": 165
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.0001060853361360733,
      "loss": 3.5366,
      "step": 170
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00010439215491761087,
      "loss": 3.7628,
      "step": 175
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00010266846440238127,
      "loss": 3.4477,
      "step": 180
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010091573386725777,
      "loss": 3.641,
      "step": 185
    },
    {
      "epoch": 0.35,
      "learning_rate": 9.913545734287838e-05,
      "loss": 3.5141,
      "step": 190
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.732915234013161e-05,
      "loss": 3.7305,
      "step": 195
    },
    {
      "epoch": 0.37,
      "learning_rate": 9.549835855662742e-05,
      "loss": 3.5619,
      "step": 200
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.364463656425613e-05,
      "loss": 3.4244,
      "step": 205
    },
    {
      "epoch": 0.39,
      "learning_rate": 9.176956647895434e-05,
      "loss": 3.5957,
      "step": 210
    },
    {
      "epoch": 0.4,
      "learning_rate": 8.987474661381113e-05,
      "loss": 3.579,
      "step": 215
    },
    {
      "epoch": 0.41,
      "learning_rate": 8.79617921166632e-05,
      "loss": 3.4737,
      "step": 220
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.603233359333994e-05,
      "loss": 3.5314,
      "step": 225
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.408801571773217e-05,
      "loss": 3.6413,
      "step": 230
    },
    {
      "epoch": 0.44,
      "learning_rate": 8.213049582986904e-05,
      "loss": 3.616,
      "step": 235
    },
    {
      "epoch": 0.45,
      "learning_rate": 8.016144252319865e-05,
      "loss": 3.6094,
      "step": 240
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.818253422227576e-05,
      "loss": 3.4714,
      "step": 245
    },
    {
      "epoch": 0.46,
      "learning_rate": 7.619545775206993e-05,
      "loss": 3.6148,
      "step": 250
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.420190690011274e-05,
      "loss": 3.393,
      "step": 255
    },
    {
      "epoch": 0.48,
      "learning_rate": 7.220358097271036e-05,
      "loss": 3.7299,
      "step": 260
    },
    {
      "epoch": 0.49,
      "learning_rate": 7.02021833464518e-05,
      "loss": 3.5671,
      "step": 265
    },
    {
      "epoch": 0.5,
      "learning_rate": 6.819942001624763e-05,
      "loss": 3.5912,
      "step": 270
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.619699814113692e-05,
      "loss": 3.4808,
      "step": 275
    },
    {
      "epoch": 0.52,
      "learning_rate": 6.419662458910188e-05,
      "loss": 3.5158,
      "step": 280
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.220000448213035e-05,
      "loss": 3.4962,
      "step": 285
    },
    {
      "epoch": 0.54,
      "learning_rate": 6.020883974276696e-05,
      "loss": 3.5426,
      "step": 290
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.822482764339123e-05,
      "loss": 3.4774,
      "step": 295
    },
    {
      "epoch": 0.56,
      "learning_rate": 5.6249659359459626e-05,
      "loss": 3.6775,
      "step": 300
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.4285018527944484e-05,
      "loss": 3.4415,
      "step": 305
    },
    {
      "epoch": 0.58,
      "learning_rate": 5.233257981219891e-05,
      "loss": 3.2558,
      "step": 310
    },
    {
      "epoch": 0.59,
      "learning_rate": 5.0394007474470735e-05,
      "loss": 3.4333,
      "step": 315
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.8470953957282466e-05,
      "loss": 3.4511,
      "step": 320
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.656505847488621e-05,
      "loss": 3.439,
      "step": 325
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.4677945615994564e-05,
      "loss": 3.5292,
      "step": 330
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.281122395897837e-05,
      "loss": 3.5033,
      "step": 335
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.096648470071148e-05,
      "loss": 3.4235,
      "step": 340
    },
    {
      "epoch": 0.64,
      "learning_rate": 3.914530030023193e-05,
      "loss": 3.4522,
      "step": 345
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.734922313837482e-05,
      "loss": 3.4705,
      "step": 350
    },
    {
      "epoch": 0.66,
      "learning_rate": 3.5579784194520246e-05,
      "loss": 3.5511,
      "step": 355
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.383849174158367e-05,
      "loss": 3.3867,
      "step": 360
    },
    {
      "epoch": 0.68,
      "learning_rate": 3.2126830060361513e-05,
      "loss": 3.6066,
      "step": 365
    },
    {
      "epoch": 0.69,
      "learning_rate": 3.044625817432741e-05,
      "loss": 3.3799,
      "step": 370
    },
    {
      "epoch": 0.7,
      "learning_rate": 2.879820860595807e-05,
      "loss": 3.3825,
      "step": 375
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.718408615564853e-05,
      "loss": 3.4277,
      "step": 380
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.560526670425788e-05,
      "loss": 3.6353,
      "step": 385
    },
    {
      "epoch": 0.72,
      "learning_rate": 2.4063096040305828e-05,
      "loss": 3.388,
      "step": 390
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.2558888712820237e-05,
      "loss": 3.4079,
      "step": 395
    },
    {
      "epoch": 0.74,
      "learning_rate": 2.1093926910813165e-05,
      "loss": 3.6123,
      "step": 400
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.966945937034066e-05,
      "loss": 3.4731,
      "step": 405
    },
    {
      "epoch": 0.76,
      "learning_rate": 1.828670031007799e-05,
      "loss": 3.6209,
      "step": 410
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.694682839631735e-05,
      "loss": 3.6534,
      "step": 415
    },
    {
      "epoch": 0.78,
      "learning_rate": 1.5650985738270693e-05,
      "loss": 3.5689,
      "step": 420
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4400276914533763e-05,
      "loss": 3.5702,
      "step": 425
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.319576803154135e-05,
      "loss": 3.4445,
      "step": 430
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.2038485814816265e-05,
      "loss": 3.3746,
      "step": 435
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.092941673378663e-05,
      "loss": 3.5187,
      "step": 440
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.869506160917616e-06,
      "loss": 3.4482,
      "step": 445
    },
    {
      "epoch": 0.84,
      "learning_rate": 8.859657565874292e-06,
      "loss": 3.5279,
      "step": 450
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.900731745402374e-06,
      "loss": 3.4626,
      "step": 455
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.9935460895836276e-06,
      "loss": 3.6454,
      "step": 460
    },
    {
      "epoch": 0.86,
      "learning_rate": 6.138873885091061e-06,
      "loss": 3.4554,
      "step": 465
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.3374436560379995e-06,
      "loss": 3.4318,
      "step": 470
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.589938542982855e-06,
      "loss": 3.5353,
      "step": 475
    },
    {
      "epoch": 0.89,
      "learning_rate": 3.896995720618831e-06,
      "loss": 3.3728,
      "step": 480
    },
    {
      "epoch": 0.9,
      "learning_rate": 3.2592058546451155e-06,
      "loss": 3.5394,
      "step": 485
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.677112598282391e-06,
      "loss": 3.4868,
      "step": 490
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.1512121288618626e-06,
      "loss": 3.3146,
      "step": 495
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.6819527248827737e-06,
      "loss": 3.286,
      "step": 500
    },
    {
      "epoch": 0.94,
      "learning_rate": 1.269734383899055e-06,
      "loss": 3.3572,
      "step": 505
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.149084815606564e-07,
      "loss": 3.4358,
      "step": 510
    },
    {
      "epoch": 0.96,
      "learning_rate": 6.177774721003861e-07,
      "loss": 3.404,
      "step": 515
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.7859463052128633e-07,
      "loss": 3.4824,
      "step": 520
    },
    {
      "epoch": 0.98,
      "learning_rate": 1.9756383670464207e-07,
      "loss": 3.3723,
      "step": 525
    },
    {
      "epoch": 0.99,
      "learning_rate": 7.483940162237093e-08,
      "loss": 3.4703,
      "step": 530
    },
    {
      "epoch": 0.99,
      "learning_rate": 1.0525935802102593e-08,
      "loss": 3.3436,
      "step": 535
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.417607307434082,
      "eval_runtime": 34.9657,
      "eval_samples_per_second": 21.535,
      "eval_steps_per_second": 2.717,
      "step": 538
    }
  ],
  "max_steps": 538,
  "num_train_epochs": 1,
  "total_flos": 561908514816000.0,
  "trial_name": null,
  "trial_params": null
}