{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1425801300330786,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 8.999954848325688e-06,
      "loss": 0.7277,
      "step": 10
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999819394208827e-06,
      "loss": 0.6455,
      "step": 20
    },
    {
      "epoch": 0.0,
      "learning_rate": 8.999593640367633e-06,
      "loss": 0.5428,
      "step": 30
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.9992775913324e-06,
      "loss": 0.3486,
      "step": 40
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.998871253445414e-06,
      "loss": 0.3524,
      "step": 50
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.998374634860822e-06,
      "loss": 0.2701,
      "step": 60
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.997787745544478e-06,
      "loss": 0.2106,
      "step": 70
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.997110597273727e-06,
      "loss": 0.2596,
      "step": 80
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.996343203637181e-06,
      "loss": 0.2015,
      "step": 90
    },
    {
      "epoch": 0.01,
      "learning_rate": 8.995485580034448e-06,
      "loss": 0.2462,
      "step": 100
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.99453774367581e-06,
      "loss": 0.2172,
      "step": 110
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.993499713581887e-06,
      "loss": 0.2655,
      "step": 120
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.992371510583257e-06,
      "loss": 0.1823,
      "step": 130
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.991153157320033e-06,
      "loss": 0.227,
      "step": 140
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.989844678241412e-06,
      "loss": 0.2243,
      "step": 150
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.988446099605179e-06,
      "loss": 0.1787,
      "step": 160
    },
    {
      "epoch": 0.02,
      "learning_rate": 8.986957449477188e-06,
      "loss": 0.2211,
      "step": 170
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.98537875773079e-06,
      "loss": 0.1683,
      "step": 180
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.983710056046243e-06,
      "loss": 0.1879,
      "step": 190
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.98195137791007e-06,
      "loss": 0.1809,
      "step": 200
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.980102758614384e-06,
      "loss": 0.2204,
      "step": 210
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.978164235256191e-06,
      "loss": 0.189,
      "step": 220
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.976135846736634e-06,
      "loss": 0.1389,
      "step": 230
    },
    {
      "epoch": 0.03,
      "learning_rate": 8.97401763376022e-06,
      "loss": 0.1231,
      "step": 240
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.971809638833998e-06,
      "loss": 0.2018,
      "step": 250
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.96951190626671e-06,
      "loss": 0.1271,
      "step": 260
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.967124482167896e-06,
      "loss": 0.1364,
      "step": 270
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.964647414446981e-06,
      "loss": 0.1658,
      "step": 280
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.9620807528123e-06,
      "loss": 0.1479,
      "step": 290
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.959424548770104e-06,
      "loss": 0.1353,
      "step": 300
    },
    {
      "epoch": 0.04,
      "learning_rate": 8.95667885562353e-06,
      "loss": 0.1761,
      "step": 310
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.953843728471533e-06,
      "loss": 0.1391,
      "step": 320
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.950919224207774e-06,
      "loss": 0.1776,
      "step": 330
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94790540151948e-06,
      "loss": 0.2089,
      "step": 340
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.94480232088627e-06,
      "loss": 0.1368,
      "step": 350
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.941610044578937e-06,
      "loss": 0.1501,
      "step": 360
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.938328636658202e-06,
      "loss": 0.1807,
      "step": 370
    },
    {
      "epoch": 0.05,
      "learning_rate": 8.934958162973425e-06,
      "loss": 0.13,
      "step": 380
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.931498691161287e-06,
      "loss": 0.1437,
      "step": 390
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.92795029064443e-06,
      "loss": 0.0828,
      "step": 400
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.924313032630063e-06,
      "loss": 0.1041,
      "step": 410
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.920586990108539e-06,
      "loss": 0.2663,
      "step": 420
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.916772237851882e-06,
      "loss": 0.2055,
      "step": 430
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.912868852412294e-06,
      "loss": 0.151,
      "step": 440
    },
    {
      "epoch": 0.06,
      "learning_rate": 8.908876912120614e-06,
      "loss": 0.1638,
      "step": 450
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.904796497084747e-06,
      "loss": 0.1399,
      "step": 460
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.900627689188059e-06,
      "loss": 0.1615,
      "step": 470
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.89637057208773e-06,
      "loss": 0.1209,
      "step": 480
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.892025231213077e-06,
      "loss": 0.1605,
      "step": 490
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.887591753763842e-06,
      "loss": 0.124,
      "step": 500
    },
    {
      "epoch": 0.07,
      "eval_accuracy": 0.0,
      "eval_loss": 0.13451002538204193,
      "eval_runtime": 446.6893,
      "eval_samples_per_second": 52.338,
      "eval_steps_per_second": 8.724,
      "step": 500
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.883070228708436e-06,
      "loss": 0.1045,
      "step": 510
    },
    {
      "epoch": 0.07,
      "learning_rate": 8.878460746782163e-06,
      "loss": 0.2208,
      "step": 520
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.873763400485387e-06,
      "loss": 0.1483,
      "step": 530
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.868978284081688e-06,
      "loss": 0.1322,
      "step": 540
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.864105493595962e-06,
      "loss": 0.1227,
      "step": 550
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.859145126812497e-06,
      "loss": 0.1371,
      "step": 560
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.854097283273012e-06,
      "loss": 0.1909,
      "step": 570
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.848962064274655e-06,
      "loss": 0.0993,
      "step": 580
    },
    {
      "epoch": 0.08,
      "learning_rate": 8.843739572867977e-06,
      "loss": 0.1053,
      "step": 590
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.838429913854859e-06,
      "loss": 0.1401,
      "step": 600
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.83303319378641e-06,
      "loss": 0.09,
      "step": 610
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.827549520960827e-06,
      "loss": 0.1667,
      "step": 620
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.821979005421223e-06,
      "loss": 0.1069,
      "step": 630
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.816321758953426e-06,
      "loss": 0.1659,
      "step": 640
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.810577895083726e-06,
      "loss": 0.1309,
      "step": 650
    },
    {
      "epoch": 0.09,
      "learning_rate": 8.804747529076592e-06,
      "loss": 0.16,
      "step": 660
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.79883077793238e-06,
      "loss": 0.1041,
      "step": 670
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.792827760384965e-06,
      "loss": 0.1344,
      "step": 680
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.786738596899362e-06,
      "loss": 0.0922,
      "step": 690
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.780563409669322e-06,
      "loss": 0.0813,
      "step": 700
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.774302322614858e-06,
      "loss": 0.1795,
      "step": 710
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.767955461379783e-06,
      "loss": 0.1409,
      "step": 720
    },
    {
      "epoch": 0.1,
      "learning_rate": 8.761522953329163e-06,
      "loss": 0.1362,
      "step": 730
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.75500492754678e-06,
      "loss": 0.1227,
      "step": 740
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.74840151483254e-06,
      "loss": 0.0643,
      "step": 750
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.741712847699832e-06,
      "loss": 0.1895,
      "step": 760
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.734939060372892e-06,
      "loss": 0.0959,
      "step": 770
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.72808028878409e-06,
      "loss": 0.1089,
      "step": 780
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.721136670571216e-06,
      "loss": 0.0959,
      "step": 790
    },
    {
      "epoch": 0.11,
      "learning_rate": 8.714108345074704e-06,
      "loss": 0.1264,
      "step": 800
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.706995453334855e-06,
      "loss": 0.1078,
      "step": 810
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.699798138088988e-06,
      "loss": 0.1278,
      "step": 820
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.692516543768581e-06,
      "loss": 0.1337,
      "step": 830
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.685150816496384e-06,
      "loss": 0.0815,
      "step": 840
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.677701104083467e-06,
      "loss": 0.1033,
      "step": 850
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.670167556026274e-06,
      "loss": 0.1412,
      "step": 860
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.662550323503606e-06,
      "loss": 0.197,
      "step": 870
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.654849559373595e-06,
      "loss": 0.1118,
      "step": 880
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.647065418170644e-06,
      "loss": 0.1132,
      "step": 890
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.639198056102309e-06,
      "loss": 0.0928,
      "step": 900
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.631247631046176e-06,
      "loss": 0.0723,
      "step": 910
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.623214302546691e-06,
      "loss": 0.126,
      "step": 920
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.615098231811958e-06,
      "loss": 0.1363,
      "step": 930
    },
    {
      "epoch": 0.13,
      "learning_rate": 8.606899581710505e-06,
      "loss": 0.1243,
      "step": 940
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.598618516768005e-06,
      "loss": 0.0382,
      "step": 950
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.590255203163995e-06,
      "loss": 0.1295,
      "step": 960
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.581809808728524e-06,
      "loss": 0.1145,
      "step": 970
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.573282502938791e-06,
      "loss": 0.0915,
      "step": 980
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.564673456915746e-06,
      "loss": 0.1918,
      "step": 990
    },
    {
      "epoch": 0.14,
      "learning_rate": 8.55598284342065e-06,
      "loss": 0.1732,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "eval_accuracy": 0.0,
      "eval_loss": 0.12965914607048035,
      "eval_runtime": 448.5256,
      "eval_samples_per_second": 52.124,
      "eval_steps_per_second": 8.688,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 7013,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 0.0,
  "trial_name": null,
  "trial_params": null
}