{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 51890,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05,
      "learning_rate": 4.95985096678872e-05,
      "loss": 8.2502,
      "step": 500
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.91970193357744e-05,
      "loss": 0.4362,
      "step": 1000
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.879552900366159e-05,
      "loss": 0.2711,
      "step": 1500
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.839403867154879e-05,
      "loss": 0.2293,
      "step": 2000
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.799254833943599e-05,
      "loss": 0.2035,
      "step": 2500
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.759105800732319e-05,
      "loss": 0.1796,
      "step": 3000
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.7189567675210385e-05,
      "loss": 0.1772,
      "step": 3500
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.678807734309758e-05,
      "loss": 0.1613,
      "step": 4000
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.6386587010984776e-05,
      "loss": 0.1587,
      "step": 4500
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.5985096678871974e-05,
      "loss": 0.1529,
      "step": 5000
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.558360634675917e-05,
      "loss": 0.1462,
      "step": 5500
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.518211601464637e-05,
      "loss": 0.1477,
      "step": 6000
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.478062568253357e-05,
      "loss": 0.1385,
      "step": 6500
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.437913535042076e-05,
      "loss": 0.137,
      "step": 7000
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.397764501830796e-05,
      "loss": 0.1299,
      "step": 7500
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.357615468619516e-05,
      "loss": 0.1336,
      "step": 8000
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.317466435408236e-05,
      "loss": 0.1288,
      "step": 8500
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.2773174021969556e-05,
      "loss": 0.1322,
      "step": 9000
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.237168368985675e-05,
      "loss": 0.1213,
      "step": 9500
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.1970193357743946e-05,
      "loss": 0.1286,
      "step": 10000
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.14025843143463135,
      "eval_runtime": 124.3791,
      "eval_samples_per_second": 89.798,
      "eval_steps_per_second": 11.232,
      "step": 10378
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.1568703025631145e-05,
      "loss": 0.1178,
      "step": 10500
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.116721269351834e-05,
      "loss": 0.1113,
      "step": 11000
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.076572236140554e-05,
      "loss": 0.1137,
      "step": 11500
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.0364232029292733e-05,
      "loss": 0.1077,
      "step": 12000
    },
    {
      "epoch": 1.2,
      "learning_rate": 3.996274169717993e-05,
      "loss": 0.1075,
      "step": 12500
    },
    {
      "epoch": 1.25,
      "learning_rate": 3.956125136506713e-05,
      "loss": 0.106,
      "step": 13000
    },
    {
      "epoch": 1.3,
      "learning_rate": 3.915976103295433e-05,
      "loss": 0.107,
      "step": 13500
    },
    {
      "epoch": 1.35,
      "learning_rate": 3.875827070084153e-05,
      "loss": 0.1057,
      "step": 14000
    },
    {
      "epoch": 1.4,
      "learning_rate": 3.8356780368728726e-05,
      "loss": 0.0984,
      "step": 14500
    },
    {
      "epoch": 1.45,
      "learning_rate": 3.795529003661592e-05,
      "loss": 0.1016,
      "step": 15000
    },
    {
      "epoch": 1.49,
      "learning_rate": 3.7553799704503117e-05,
      "loss": 0.1019,
      "step": 15500
    },
    {
      "epoch": 1.54,
      "learning_rate": 3.7152309372390315e-05,
      "loss": 0.1023,
      "step": 16000
    },
    {
      "epoch": 1.59,
      "learning_rate": 3.6750819040277514e-05,
      "loss": 0.1004,
      "step": 16500
    },
    {
      "epoch": 1.64,
      "learning_rate": 3.634932870816471e-05,
      "loss": 0.1008,
      "step": 17000
    },
    {
      "epoch": 1.69,
      "learning_rate": 3.5947838376051904e-05,
      "loss": 0.0962,
      "step": 17500
    },
    {
      "epoch": 1.73,
      "learning_rate": 3.55463480439391e-05,
      "loss": 0.1001,
      "step": 18000
    },
    {
      "epoch": 1.78,
      "learning_rate": 3.51448577118263e-05,
      "loss": 0.0942,
      "step": 18500
    },
    {
      "epoch": 1.83,
      "learning_rate": 3.47433673797135e-05,
      "loss": 0.0975,
      "step": 19000
    },
    {
      "epoch": 1.88,
      "learning_rate": 3.43418770476007e-05,
      "loss": 0.1006,
      "step": 19500
    },
    {
      "epoch": 1.93,
      "learning_rate": 3.394038671548789e-05,
      "loss": 0.0932,
      "step": 20000
    },
    {
      "epoch": 1.98,
      "learning_rate": 3.353889638337509e-05,
      "loss": 0.0937,
      "step": 20500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.12487868219614029,
      "eval_runtime": 124.206,
      "eval_samples_per_second": 89.923,
      "eval_steps_per_second": 11.247,
      "step": 20756
    },
    {
      "epoch": 2.02,
      "learning_rate": 3.313740605126229e-05,
      "loss": 0.0927,
      "step": 21000
    },
    {
      "epoch": 2.07,
      "learning_rate": 3.2735915719149485e-05,
      "loss": 0.0833,
      "step": 21500
    },
    {
      "epoch": 2.12,
      "learning_rate": 3.2334425387036684e-05,
      "loss": 0.0838,
      "step": 22000
    },
    {
      "epoch": 2.17,
      "learning_rate": 3.193293505492388e-05,
      "loss": 0.0833,
      "step": 22500
    },
    {
      "epoch": 2.22,
      "learning_rate": 3.1531444722811074e-05,
      "loss": 0.0807,
      "step": 23000
    },
    {
      "epoch": 2.26,
      "learning_rate": 3.112995439069827e-05,
      "loss": 0.0802,
      "step": 23500
    },
    {
      "epoch": 2.31,
      "learning_rate": 3.072846405858547e-05,
      "loss": 0.0818,
      "step": 24000
    },
    {
      "epoch": 2.36,
      "learning_rate": 3.032697372647267e-05,
      "loss": 0.0834,
      "step": 24500
    },
    {
      "epoch": 2.41,
      "learning_rate": 2.9925483394359865e-05,
      "loss": 0.0815,
      "step": 25000
    },
    {
      "epoch": 2.46,
      "learning_rate": 2.9523993062247064e-05,
      "loss": 0.0831,
      "step": 25500
    },
    {
      "epoch": 2.51,
      "learning_rate": 2.912250273013426e-05,
      "loss": 0.0835,
      "step": 26000
    },
    {
      "epoch": 2.55,
      "learning_rate": 2.8721012398021457e-05,
      "loss": 0.0812,
      "step": 26500
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.8319522065908656e-05,
      "loss": 0.0782,
      "step": 27000
    },
    {
      "epoch": 2.65,
      "learning_rate": 2.791803173379585e-05,
      "loss": 0.084,
      "step": 27500
    },
    {
      "epoch": 2.7,
      "learning_rate": 2.751654140168305e-05,
      "loss": 0.0821,
      "step": 28000
    },
    {
      "epoch": 2.75,
      "learning_rate": 2.7115051069570248e-05,
      "loss": 0.0788,
      "step": 28500
    },
    {
      "epoch": 2.79,
      "learning_rate": 2.6713560737457443e-05,
      "loss": 0.0838,
      "step": 29000
    },
    {
      "epoch": 2.84,
      "learning_rate": 2.6312070405344642e-05,
      "loss": 0.0822,
      "step": 29500
    },
    {
      "epoch": 2.89,
      "learning_rate": 2.5910580073231837e-05,
      "loss": 0.0801,
      "step": 30000
    },
    {
      "epoch": 2.94,
      "learning_rate": 2.5509089741119035e-05,
      "loss": 0.0799,
      "step": 30500
    },
    {
      "epoch": 2.99,
      "learning_rate": 2.5107599409006234e-05,
      "loss": 0.0809,
      "step": 31000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.11599379032850266,
      "eval_runtime": 124.1737,
      "eval_samples_per_second": 89.947,
      "eval_steps_per_second": 11.25,
      "step": 31134
    },
    {
      "epoch": 3.04,
      "learning_rate": 2.470610907689343e-05,
      "loss": 0.0754,
      "step": 31500
    },
    {
      "epoch": 3.08,
      "learning_rate": 2.4304618744780628e-05,
      "loss": 0.0693,
      "step": 32000
    },
    {
      "epoch": 3.13,
      "learning_rate": 2.3903128412667826e-05,
      "loss": 0.0726,
      "step": 32500
    },
    {
      "epoch": 3.18,
      "learning_rate": 2.350163808055502e-05,
      "loss": 0.0689,
      "step": 33000
    },
    {
      "epoch": 3.23,
      "learning_rate": 2.310014774844222e-05,
      "loss": 0.0718,
      "step": 33500
    },
    {
      "epoch": 3.28,
      "learning_rate": 2.2698657416329415e-05,
      "loss": 0.07,
      "step": 34000
    },
    {
      "epoch": 3.32,
      "learning_rate": 2.2297167084216614e-05,
      "loss": 0.0753,
      "step": 34500
    },
    {
      "epoch": 3.37,
      "learning_rate": 2.1895676752103812e-05,
      "loss": 0.071,
      "step": 35000
    },
    {
      "epoch": 3.42,
      "learning_rate": 2.1494186419991007e-05,
      "loss": 0.0688,
      "step": 35500
    },
    {
      "epoch": 3.47,
      "learning_rate": 2.1092696087878206e-05,
      "loss": 0.0692,
      "step": 36000
    },
    {
      "epoch": 3.52,
      "learning_rate": 2.06912057557654e-05,
      "loss": 0.0696,
      "step": 36500
    },
    {
      "epoch": 3.57,
      "learning_rate": 2.02897154236526e-05,
      "loss": 0.0714,
      "step": 37000
    },
    {
      "epoch": 3.61,
      "learning_rate": 1.9888225091539798e-05,
      "loss": 0.0682,
      "step": 37500
    },
    {
      "epoch": 3.66,
      "learning_rate": 1.9486734759426993e-05,
      "loss": 0.0675,
      "step": 38000
    },
    {
      "epoch": 3.71,
      "learning_rate": 1.9085244427314192e-05,
      "loss": 0.0689,
      "step": 38500
    },
    {
      "epoch": 3.76,
      "learning_rate": 1.868375409520139e-05,
      "loss": 0.0727,
      "step": 39000
    },
    {
      "epoch": 3.81,
      "learning_rate": 1.8282263763088585e-05,
      "loss": 0.0688,
      "step": 39500
    },
    {
      "epoch": 3.85,
      "learning_rate": 1.7880773430975784e-05,
      "loss": 0.0677,
      "step": 40000
    },
    {
      "epoch": 3.9,
      "learning_rate": 1.747928309886298e-05,
      "loss": 0.0664,
      "step": 40500
    },
    {
      "epoch": 3.95,
      "learning_rate": 1.7077792766750178e-05,
      "loss": 0.0677,
      "step": 41000
    },
    {
      "epoch": 4.0,
      "learning_rate": 1.6676302434637376e-05,
      "loss": 0.0712,
      "step": 41500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.11910858005285263,
      "eval_runtime": 124.1925,
      "eval_samples_per_second": 89.933,
      "eval_steps_per_second": 11.249,
      "step": 41512
    },
    {
      "epoch": 4.05,
      "learning_rate": 1.627481210252457e-05,
      "loss": 0.064,
      "step": 42000
    },
    {
      "epoch": 4.1,
      "learning_rate": 1.587332177041177e-05,
      "loss": 0.0642,
      "step": 42500
    },
    {
      "epoch": 4.14,
      "learning_rate": 1.547183143829897e-05,
      "loss": 0.0603,
      "step": 43000
    },
    {
      "epoch": 4.19,
      "learning_rate": 1.5070341106186164e-05,
      "loss": 0.059,
      "step": 43500
    },
    {
      "epoch": 4.24,
      "learning_rate": 1.4668850774073362e-05,
      "loss": 0.0636,
      "step": 44000
    },
    {
      "epoch": 4.29,
      "learning_rate": 1.4267360441960559e-05,
      "loss": 0.0582,
      "step": 44500
    },
    {
      "epoch": 4.34,
      "learning_rate": 1.3865870109847756e-05,
      "loss": 0.0648,
      "step": 45000
    },
    {
      "epoch": 4.38,
      "learning_rate": 1.3464379777734953e-05,
      "loss": 0.0586,
      "step": 45500
    },
    {
      "epoch": 4.43,
      "learning_rate": 1.3062889445622151e-05,
      "loss": 0.0612,
      "step": 46000
    },
    {
      "epoch": 4.48,
      "learning_rate": 1.2661399113509348e-05,
      "loss": 0.0601,
      "step": 46500
    },
    {
      "epoch": 4.53,
      "learning_rate": 1.2259908781396545e-05,
      "loss": 0.0618,
      "step": 47000
    },
    {
      "epoch": 4.58,
      "learning_rate": 1.1858418449283742e-05,
      "loss": 0.0612,
      "step": 47500
    },
    {
      "epoch": 4.63,
      "learning_rate": 1.145692811717094e-05,
      "loss": 0.0598,
      "step": 48000
    },
    {
      "epoch": 4.67,
      "learning_rate": 1.1055437785058137e-05,
      "loss": 0.0609,
      "step": 48500
    },
    {
      "epoch": 4.72,
      "learning_rate": 1.0653947452945334e-05,
      "loss": 0.0639,
      "step": 49000
    },
    {
      "epoch": 4.77,
      "learning_rate": 1.0252457120832531e-05,
      "loss": 0.0639,
      "step": 49500
    },
    {
      "epoch": 4.82,
      "learning_rate": 9.85096678871973e-06,
      "loss": 0.064,
      "step": 50000
    },
    {
      "epoch": 4.87,
      "learning_rate": 9.449476456606926e-06,
      "loss": 0.0614,
      "step": 50500
    },
    {
      "epoch": 4.91,
      "learning_rate": 9.047986124494123e-06,
      "loss": 0.0618,
      "step": 51000
    },
    {
      "epoch": 4.96,
      "learning_rate": 8.64649579238132e-06,
      "loss": 0.0624,
      "step": 51500
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.1161259263753891,
      "eval_runtime": 124.2379,
      "eval_samples_per_second": 89.9,
      "eval_steps_per_second": 11.245,
      "step": 51890
    }
  ],
  "logging_steps": 500,
  "max_steps": 62268,
  "num_train_epochs": 6,
  "save_steps": 500,
  "total_flos": 4.977120588123341e+17,
  "trial_name": null,
  "trial_params": null
}