{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.99968,
  "eval_steps": 500,
  "global_step": 781,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0128,
      "grad_norm": 3.1302534958568193,
      "learning_rate": 1.2738853503184715e-06,
      "loss": 0.6569,
      "step": 10
    },
    {
      "epoch": 0.0256,
      "grad_norm": 3.1468711921047627,
      "learning_rate": 2.547770700636943e-06,
      "loss": 0.5179,
      "step": 20
    },
    {
      "epoch": 0.0384,
      "grad_norm": 0.5540977306160393,
      "learning_rate": 3.821656050955415e-06,
      "loss": 0.2369,
      "step": 30
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.5002871919834374,
      "learning_rate": 5.095541401273886e-06,
      "loss": 0.1819,
      "step": 40
    },
    {
      "epoch": 0.064,
      "grad_norm": 0.7150745925714665,
      "learning_rate": 6.369426751592357e-06,
      "loss": 0.1759,
      "step": 50
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.7619036468756623,
      "learning_rate": 7.64331210191083e-06,
      "loss": 0.16,
      "step": 60
    },
    {
      "epoch": 0.0896,
      "grad_norm": 0.44198933481881236,
      "learning_rate": 8.9171974522293e-06,
      "loss": 0.1608,
      "step": 70
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.37478693328542767,
      "learning_rate": 1.0191082802547772e-05,
      "loss": 0.1617,
      "step": 80
    },
    {
      "epoch": 0.1152,
      "grad_norm": 0.3696718954770576,
      "learning_rate": 1.1464968152866242e-05,
      "loss": 0.1596,
      "step": 90
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.5203159641478062,
      "learning_rate": 1.2738853503184714e-05,
      "loss": 0.1602,
      "step": 100
    },
    {
      "epoch": 0.1408,
      "grad_norm": 0.37773491168605033,
      "learning_rate": 1.4012738853503186e-05,
      "loss": 0.1485,
      "step": 110
    },
    {
      "epoch": 0.1536,
      "grad_norm": 0.24203685828143712,
      "learning_rate": 1.528662420382166e-05,
      "loss": 0.1555,
      "step": 120
    },
    {
      "epoch": 0.1664,
      "grad_norm": 0.3898599912917371,
      "learning_rate": 1.6560509554140128e-05,
      "loss": 0.1571,
      "step": 130
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.22025246679268023,
      "learning_rate": 1.78343949044586e-05,
      "loss": 0.1559,
      "step": 140
    },
    {
      "epoch": 0.192,
      "grad_norm": 0.5943517884905586,
      "learning_rate": 1.910828025477707e-05,
      "loss": 0.1578,
      "step": 150
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.4363975905376457,
      "learning_rate": 1.999977501271127e-05,
      "loss": 0.1468,
      "step": 160
    },
    {
      "epoch": 0.2176,
      "grad_norm": 0.4874326999671375,
      "learning_rate": 1.9995775520317924e-05,
      "loss": 0.1519,
      "step": 170
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.32242234734849035,
      "learning_rate": 1.998677861199748e-05,
      "loss": 0.1537,
      "step": 180
    },
    {
      "epoch": 0.2432,
      "grad_norm": 0.338978065876802,
      "learning_rate": 1.9972788785779404e-05,
      "loss": 0.1535,
      "step": 190
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.5405845227789843,
      "learning_rate": 1.9953813035916444e-05,
      "loss": 0.1552,
      "step": 200
    },
    {
      "epoch": 0.2688,
      "grad_norm": 0.3187325098825458,
      "learning_rate": 1.9929860849387815e-05,
      "loss": 0.1441,
      "step": 210
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.181656187619335,
      "learning_rate": 1.9900944201156164e-05,
      "loss": 0.1489,
      "step": 220
    },
    {
      "epoch": 0.2944,
      "grad_norm": 0.26409308919505864,
      "learning_rate": 1.986707754818064e-05,
      "loss": 0.1509,
      "step": 230
    },
    {
      "epoch": 0.3072,
      "grad_norm": 0.23639855452929004,
      "learning_rate": 1.982827782218912e-05,
      "loss": 0.1525,
      "step": 240
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.42132507371171557,
      "learning_rate": 1.9784564421213122e-05,
      "loss": 0.1513,
      "step": 250
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.30911958261458256,
      "learning_rate": 1.9735959199889723e-05,
      "loss": 0.1415,
      "step": 260
    },
    {
      "epoch": 0.3456,
      "grad_norm": 0.286475064941514,
      "learning_rate": 1.968248645853526e-05,
      "loss": 0.1483,
      "step": 270
    },
    {
      "epoch": 0.3584,
      "grad_norm": 0.3223686350575121,
      "learning_rate": 1.9624172930996322e-05,
      "loss": 0.1496,
      "step": 280
    },
    {
      "epoch": 0.3712,
      "grad_norm": 0.33039144824318656,
      "learning_rate": 1.956104777128409e-05,
      "loss": 0.1496,
      "step": 290
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.3268436732392019,
      "learning_rate": 1.9493142538998713e-05,
      "loss": 0.1524,
      "step": 300
    },
    {
      "epoch": 0.3968,
      "grad_norm": 0.3768976535567336,
      "learning_rate": 1.9420491183550983e-05,
      "loss": 0.1397,
      "step": 310
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.344679435905093,
      "learning_rate": 1.934313002718924e-05,
      "loss": 0.1459,
      "step": 320
    },
    {
      "epoch": 0.4224,
      "grad_norm": 0.1867877479920934,
      "learning_rate": 1.9261097746839974e-05,
      "loss": 0.149,
      "step": 330
    },
    {
      "epoch": 0.4352,
      "grad_norm": 0.22826415693304572,
      "learning_rate": 1.9174435354771167e-05,
      "loss": 0.1515,
      "step": 340
    },
    {
      "epoch": 0.448,
      "grad_norm": 0.2574654153325295,
      "learning_rate": 1.9083186178088103e-05,
      "loss": 0.1501,
      "step": 350
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.23070296857068737,
      "learning_rate": 1.898739583707187e-05,
      "loss": 0.1383,
      "step": 360
    },
    {
      "epoch": 0.4736,
      "grad_norm": 0.21129982050815863,
      "learning_rate": 1.8887112222371363e-05,
      "loss": 0.1437,
      "step": 370
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.17026221614799503,
      "learning_rate": 1.8782385471060217e-05,
      "loss": 0.1495,
      "step": 380
    },
    {
      "epoch": 0.4992,
      "grad_norm": 0.2103435712105906,
      "learning_rate": 1.8673267941570646e-05,
      "loss": 0.1495,
      "step": 390
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.2949165035198057,
      "learning_rate": 1.8559814187516692e-05,
      "loss": 0.1482,
      "step": 400
    },
    {
      "epoch": 0.5248,
      "grad_norm": 0.2727792628609804,
      "learning_rate": 1.844208093042e-05,
      "loss": 0.1385,
      "step": 410
    },
    {
      "epoch": 0.5376,
      "grad_norm": 0.19011236871362203,
      "learning_rate": 1.8320127031351723e-05,
      "loss": 0.1447,
      "step": 420
    },
    {
      "epoch": 0.5504,
      "grad_norm": 0.20224724252134554,
      "learning_rate": 1.8194013461504774e-05,
      "loss": 0.1457,
      "step": 430
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.21758912206027958,
      "learning_rate": 1.806380327171111e-05,
      "loss": 0.146,
      "step": 440
    },
    {
      "epoch": 0.576,
      "grad_norm": 0.394244725563091,
      "learning_rate": 1.792956156091928e-05,
      "loss": 0.1473,
      "step": 450
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.3292629665585757,
      "learning_rate": 1.7791355443648045e-05,
      "loss": 0.1378,
      "step": 460
    },
    {
      "epoch": 0.6016,
      "grad_norm": 0.19521004688992183,
      "learning_rate": 1.7649254016432247e-05,
      "loss": 0.1456,
      "step": 470
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.2316602793370239,
      "learning_rate": 1.750332832327786e-05,
      "loss": 0.1451,
      "step": 480
    },
    {
      "epoch": 0.6272,
      "grad_norm": 0.17573541945620594,
      "learning_rate": 1.735365132014329e-05,
      "loss": 0.1486,
      "step": 490
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.3527896812147239,
      "learning_rate": 1.7200297838464864e-05,
      "loss": 0.1488,
      "step": 500
    },
    {
      "epoch": 0.6528,
      "grad_norm": 0.21609855998849087,
      "learning_rate": 1.7043344547744637e-05,
      "loss": 0.138,
      "step": 510
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.20743287144243716,
      "learning_rate": 1.6882869917219265e-05,
      "loss": 0.1432,
      "step": 520
    },
    {
      "epoch": 0.6784,
      "grad_norm": 0.14306391155148201,
      "learning_rate": 1.6718954176629088e-05,
      "loss": 0.1458,
      "step": 530
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.13082293792565916,
      "learning_rate": 1.6551679276107047e-05,
      "loss": 0.1468,
      "step": 540
    },
    {
      "epoch": 0.704,
      "grad_norm": 0.36161924084937497,
      "learning_rate": 1.638112884520748e-05,
      "loss": 0.1469,
      "step": 550
    },
    {
      "epoch": 0.7168,
      "grad_norm": 0.28617618689753893,
      "learning_rate": 1.620738815109531e-05,
      "loss": 0.1371,
      "step": 560
    },
    {
      "epoch": 0.7296,
      "grad_norm": 0.13750653322717393,
      "learning_rate": 1.6030544055916462e-05,
      "loss": 0.1423,
      "step": 570
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.15234113342700173,
      "learning_rate": 1.5850684973370913e-05,
      "loss": 0.1473,
      "step": 580
    },
    {
      "epoch": 0.7552,
      "grad_norm": 0.1674605203651358,
      "learning_rate": 1.5667900824510005e-05,
      "loss": 0.1465,
      "step": 590
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.30120726166690853,
      "learning_rate": 1.5482282992780155e-05,
      "loss": 0.1459,
      "step": 600
    },
    {
      "epoch": 0.7808,
      "grad_norm": 0.2556669288569797,
      "learning_rate": 1.5293924278335475e-05,
      "loss": 0.1372,
      "step": 610
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.19878411049962907,
      "learning_rate": 1.5102918851642035e-05,
      "loss": 0.1416,
      "step": 620
    },
    {
      "epoch": 0.8064,
      "grad_norm": 0.14869095864210355,
      "learning_rate": 1.4909362206397114e-05,
      "loss": 0.1435,
      "step": 630
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.21996626003622385,
      "learning_rate": 1.4713351111786824e-05,
      "loss": 0.1462,
      "step": 640
    },
    {
      "epoch": 0.832,
      "grad_norm": 0.29224476727899246,
      "learning_rate": 1.4514983564106117e-05,
      "loss": 0.1449,
      "step": 650
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.2688310061351837,
      "learning_rate": 1.431435873776524e-05,
      "loss": 0.1374,
      "step": 660
    },
    {
      "epoch": 0.8576,
      "grad_norm": 0.20038216433613684,
      "learning_rate": 1.4111576935707214e-05,
      "loss": 0.1426,
      "step": 670
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.13687808263034185,
      "learning_rate": 1.3906739539261115e-05,
      "loss": 0.1457,
      "step": 680
    },
    {
      "epoch": 0.8832,
      "grad_norm": 0.19032971439937477,
      "learning_rate": 1.3699948957456176e-05,
      "loss": 0.1455,
      "step": 690
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.3208508208806956,
      "learning_rate": 1.3491308575822111e-05,
      "loss": 0.1435,
      "step": 700
    },
    {
      "epoch": 0.9088,
      "grad_norm": 0.19524278584922394,
      "learning_rate": 1.3280922704701231e-05,
      "loss": 0.1365,
      "step": 710
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.17798035245935892,
      "learning_rate": 1.3068896527098205e-05,
      "loss": 0.1433,
      "step": 720
    },
    {
      "epoch": 0.9344,
      "grad_norm": 0.17884600087369845,
      "learning_rate": 1.2855336046093513e-05,
      "loss": 0.1447,
      "step": 730
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.14100954677816485,
      "learning_rate": 1.2640348031846897e-05,
      "loss": 0.1447,
      "step": 740
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.33304512484187876,
      "learning_rate": 1.2424039968217361e-05,
      "loss": 0.145,
      "step": 750
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.2096407271139896,
      "learning_rate": 1.220651999902627e-05,
      "loss": 0.1355,
      "step": 760
    },
    {
      "epoch": 0.9856,
      "grad_norm": 0.18948626555533854,
      "learning_rate": 1.1987896873990572e-05,
      "loss": 0.1422,
      "step": 770
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.25576476392968256,
      "learning_rate": 1.176827989435307e-05,
      "loss": 0.1473,
      "step": 780
    }
  ],
  "logging_steps": 10,
  "max_steps": 1562,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 781,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 267046948257792.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}