{
  "best_metric": 1.9499354362487793,
  "best_model_checkpoint": "output/john-lennon/checkpoint-506",
  "epoch": 2.0,
  "global_step": 506,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 0.00013706782378281954,
      "loss": 3.1396,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.0001366718044768288,
      "loss": 2.944,
      "step": 10
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.00013601346815589937,
      "loss": 2.9219,
      "step": 15
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00013509535174144625,
      "loss": 2.7004,
      "step": 20
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00013392099322631472,
      "loss": 2.7631,
      "step": 25
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.0001324949180410046,
      "loss": 2.7551,
      "step": 30
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.0001308226216147698,
      "loss": 2.7797,
      "step": 35
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001289105481987947,
      "loss": 2.8361,
      "step": 40
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.0001267660660330529,
      "loss": 2.7943,
      "step": 45
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00012439743895254382,
      "loss": 2.64,
      "step": 50
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.0001218137945423232,
      "loss": 2.5387,
      "step": 55
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00011902508896404359,
      "loss": 2.693,
      "step": 60
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001160420685895466,
      "loss": 2.9437,
      "step": 65
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.0001128762285893533,
      "loss": 2.5893,
      "step": 70
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00010953976863563352,
      "loss": 2.5721,
      "step": 75
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00010604554589035391,
      "loss": 2.5719,
      "step": 80
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00010240702545976687,
      "loss": 2.757,
      "step": 85
    },
    {
      "epoch": 0.36,
      "learning_rate": 9.863822850616538e-05,
      "loss": 2.3807,
      "step": 90
    },
    {
      "epoch": 0.38,
      "learning_rate": 9.475367821685696e-05,
      "loss": 2.2877,
      "step": 95
    },
    {
      "epoch": 0.4,
      "learning_rate": 9.076834383856722e-05,
      "loss": 2.4833,
      "step": 100
    },
    {
      "epoch": 0.42,
      "learning_rate": 8.669758299293816e-05,
      "loss": 2.5693,
      "step": 105
    },
    {
      "epoch": 0.43,
      "learning_rate": 8.255708249541069e-05,
      "loss": 2.4457,
      "step": 110
    },
    {
      "epoch": 0.45,
      "learning_rate": 7.836279790554737e-05,
      "loss": 2.5813,
      "step": 115
    },
    {
      "epoch": 0.47,
      "learning_rate": 7.413089204174082e-05,
      "loss": 2.3967,
      "step": 120
    },
    {
      "epoch": 0.49,
      "learning_rate": 6.987767269724301e-05,
      "loss": 2.4554,
      "step": 125
    },
    {
      "epoch": 0.51,
      "learning_rate": 6.561952979752895e-05,
      "loss": 2.5141,
      "step": 130
    },
    {
      "epoch": 0.53,
      "learning_rate": 6.137287224116132e-05,
      "loss": 2.6133,
      "step": 135
    },
    {
      "epoch": 0.55,
      "learning_rate": 5.715406466754129e-05,
      "loss": 2.5404,
      "step": 140
    },
    {
      "epoch": 0.57,
      "learning_rate": 5.297936439521389e-05,
      "loss": 2.3175,
      "step": 145
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.8864858773737654e-05,
      "loss": 2.4477,
      "step": 150
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.482640319053576e-05,
      "loss": 2.424,
      "step": 155
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.0879559971621006e-05,
      "loss": 2.6316,
      "step": 160
    },
    {
      "epoch": 0.65,
      "learning_rate": 3.703953841164296e-05,
      "loss": 2.3138,
      "step": 165
    },
    {
      "epoch": 0.67,
      "learning_rate": 3.33211361643535e-05,
      "loss": 2.2384,
      "step": 170
    },
    {
      "epoch": 0.69,
      "learning_rate": 2.973868221934456e-05,
      "loss": 2.1915,
      "step": 175
    },
    {
      "epoch": 0.71,
      "learning_rate": 2.6305981684799012e-05,
      "loss": 2.4846,
      "step": 180
    },
    {
      "epoch": 0.73,
      "learning_rate": 2.303626258903672e-05,
      "loss": 2.1743,
      "step": 185
    },
    {
      "epoch": 0.75,
      "learning_rate": 1.99421249058571e-05,
      "loss": 2.2715,
      "step": 190
    },
    {
      "epoch": 0.77,
      "learning_rate": 1.703549200011139e-05,
      "loss": 2.4405,
      "step": 195
    },
    {
      "epoch": 0.79,
      "learning_rate": 1.4327564680610529e-05,
      "loss": 2.2981,
      "step": 200
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.1828778037427104e-05,
      "loss": 2.3665,
      "step": 205
    },
    {
      "epoch": 0.83,
      "learning_rate": 9.548761229920845e-06,
      "loss": 2.1714,
      "step": 210
    },
    {
      "epoch": 0.85,
      "learning_rate": 7.496300380445175e-06,
      "loss": 2.5874,
      "step": 215
    },
    {
      "epoch": 0.87,
      "learning_rate": 5.679304716725937e-06,
      "loss": 2.416,
      "step": 220
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.104776093383014e-06,
      "loss": 2.2762,
      "step": 225
    },
    {
      "epoch": 0.91,
      "learning_rate": 2.778782010045488e-06,
      "loss": 2.3586,
      "step": 230
    },
    {
      "epoch": 0.93,
      "learning_rate": 1.7064322300351674e-06,
      "loss": 2.2319,
      "step": 235
    },
    {
      "epoch": 0.95,
      "learning_rate": 8.918590897198837e-07,
      "loss": 2.479,
      "step": 240
    },
    {
      "epoch": 0.97,
      "learning_rate": 3.382015744146126e-07,
      "loss": 2.2518,
      "step": 245
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.7593222194759165e-08,
      "loss": 2.0598,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.1660313606262207,
      "eval_runtime": 15.7786,
      "eval_samples_per_second": 20.724,
      "eval_steps_per_second": 2.598,
      "step": 253
    },
    {
      "epoch": 1.01,
      "learning_rate": 2.1153902234600496e-08,
      "loss": 2.2301,
      "step": 255
    },
    {
      "epoch": 1.03,
      "learning_rate": 2.589854993532899e-07,
      "loss": 2.306,
      "step": 260
    },
    {
      "epoch": 1.05,
      "learning_rate": 7.601715213982628e-07,
      "loss": 2.2196,
      "step": 265
    },
    {
      "epoch": 1.07,
      "learning_rate": 1.522780630978913e-06,
      "loss": 2.4015,
      "step": 270
    },
    {
      "epoch": 1.09,
      "learning_rate": 2.5438740879409643e-06,
      "loss": 2.1129,
      "step": 275
    },
    {
      "epoch": 1.11,
      "learning_rate": 3.819517073901653e-06,
      "loss": 2.0746,
      "step": 280
    },
    {
      "epoch": 1.13,
      "learning_rate": 5.344793855206241e-06,
      "loss": 2.1512,
      "step": 285
    },
    {
      "epoch": 1.15,
      "learning_rate": 7.1138267258749755e-06,
      "loss": 2.1905,
      "step": 290
    },
    {
      "epoch": 1.17,
      "learning_rate": 9.119798657543025e-06,
      "loss": 2.3491,
      "step": 295
    },
    {
      "epoch": 1.19,
      "learning_rate": 1.1354979569111356e-05,
      "loss": 2.17,
      "step": 300
    },
    {
      "epoch": 1.21,
      "learning_rate": 1.3810756114877161e-05,
      "loss": 2.0833,
      "step": 305
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.647766487635476e-05,
      "loss": 2.1924,
      "step": 310
    },
    {
      "epoch": 1.25,
      "learning_rate": 1.9345428829880624e-05,
      "loss": 2.1825,
      "step": 315
    },
    {
      "epoch": 1.26,
      "learning_rate": 2.240299694947395e-05,
      "loss": 2.1866,
      "step": 320
    },
    {
      "epoch": 1.28,
      "learning_rate": 2.5638586792341077e-05,
      "loss": 2.2806,
      "step": 325
    },
    {
      "epoch": 1.3,
      "learning_rate": 2.9039729902920112e-05,
      "loss": 2.0872,
      "step": 330
    },
    {
      "epoch": 1.32,
      "learning_rate": 3.2593319860498214e-05,
      "loss": 2.2949,
      "step": 335
    },
    {
      "epoch": 1.34,
      "learning_rate": 3.628566278525032e-05,
      "loss": 2.1108,
      "step": 340
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.0102530108070535e-05,
      "loss": 2.2652,
      "step": 345
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.4029213400848006e-05,
      "loss": 2.1869,
      "step": 350
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.8050581055894354e-05,
      "loss": 1.8115,
      "step": 355
    },
    {
      "epoch": 1.42,
      "learning_rate": 5.215113659610952e-05,
      "loss": 2.0593,
      "step": 360
    },
    {
      "epoch": 1.44,
      "learning_rate": 5.631507839118308e-05,
      "loss": 2.315,
      "step": 365
    },
    {
      "epoch": 1.46,
      "learning_rate": 6.052636054971471e-05,
      "loss": 2.1821,
      "step": 370
    },
    {
      "epoch": 1.48,
      "learning_rate": 6.476875475260261e-05,
      "loss": 2.1544,
      "step": 375
    },
    {
      "epoch": 1.5,
      "learning_rate": 6.902591278942309e-05,
      "loss": 2.0091,
      "step": 380
    },
    {
      "epoch": 1.52,
      "learning_rate": 7.328142955681643e-05,
      "loss": 2.2613,
      "step": 385
    },
    {
      "epoch": 1.54,
      "learning_rate": 7.75189062761101e-05,
      "loss": 2.0543,
      "step": 390
    },
    {
      "epoch": 1.56,
      "learning_rate": 8.172201368657108e-05,
      "loss": 2.0958,
      "step": 395
    },
    {
      "epoch": 1.58,
      "learning_rate": 8.587455497076717e-05,
      "loss": 1.9326,
      "step": 400
    },
    {
      "epoch": 1.6,
      "learning_rate": 8.996052816955487e-05,
      "loss": 2.2574,
      "step": 405
    },
    {
      "epoch": 1.62,
      "learning_rate": 9.396418784617256e-05,
      "loss": 2.2874,
      "step": 410
    },
    {
      "epoch": 1.64,
      "learning_rate": 9.787010576181766e-05,
      "loss": 2.1276,
      "step": 415
    },
    {
      "epoch": 1.66,
      "learning_rate": 0.0001016632303288892,
      "loss": 2.0318,
      "step": 420
    },
    {
      "epoch": 1.68,
      "learning_rate": 0.00010532894461279352,
      "loss": 1.9958,
      "step": 425
    },
    {
      "epoch": 1.7,
      "learning_rate": 0.00010885312265879837,
      "loss": 2.1824,
      "step": 430
    },
    {
      "epoch": 1.72,
      "learning_rate": 0.00011222218392688076,
      "loss": 2.0295,
      "step": 435
    },
    {
      "epoch": 1.74,
      "learning_rate": 0.00011542314562479964,
      "loss": 1.9594,
      "step": 440
    },
    {
      "epoch": 1.76,
      "learning_rate": 0.00011844367273772802,
      "loss": 2.1575,
      "step": 445
    },
    {
      "epoch": 1.78,
      "learning_rate": 0.00012127212556165186,
      "loss": 2.1388,
      "step": 450
    },
    {
      "epoch": 1.8,
      "learning_rate": 0.00012389760455736598,
      "loss": 2.1449,
      "step": 455
    },
    {
      "epoch": 1.82,
      "learning_rate": 0.000126309992352219,
      "loss": 2.253,
      "step": 460
    },
    {
      "epoch": 1.84,
      "learning_rate": 0.0001284999927277534,
      "loss": 1.9017,
      "step": 465
    },
    {
      "epoch": 1.86,
      "learning_rate": 0.00013045916644299936,
      "loss": 1.9045,
      "step": 470
    },
    {
      "epoch": 1.88,
      "learning_rate": 0.00013217996375537733,
      "loss": 1.8158,
      "step": 475
    },
    {
      "epoch": 1.9,
      "learning_rate": 0.0001336557535138877,
      "loss": 2.1949,
      "step": 480
    },
    {
      "epoch": 1.92,
      "learning_rate": 0.00013488084871247707,
      "loss": 2.0855,
      "step": 485
    },
    {
      "epoch": 1.94,
      "learning_rate": 0.00013585052840510938,
      "loss": 2.3929,
      "step": 490
    },
    {
      "epoch": 1.96,
      "learning_rate": 0.00013656105589809228,
      "loss": 2.0561,
      "step": 495
    },
    {
      "epoch": 1.98,
      "learning_rate": 0.0001370096931495533,
      "loss": 1.956,
      "step": 500
    },
    {
      "epoch": 2.0,
      "learning_rate": 0.00013719471132057743,
      "loss": 1.8902,
      "step": 505
    },
    {
      "epoch": 2.0,
      "eval_loss": 1.9499354362487793,
      "eval_runtime": 15.8099,
      "eval_samples_per_second": 20.683,
      "eval_steps_per_second": 2.593,
      "step": 506
    }
  ],
  "max_steps": 506,
  "num_train_epochs": 2,
  "total_flos": 527287320576000.0,
  "trial_name": null,
  "trial_params": null
}