{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.249442213297635,
  "eval_steps": 70,
  "global_step": 350,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0178491744756805,
      "grad_norm": 1.8217403888702393,
      "learning_rate": 2.9761904761904763e-06,
      "loss": 2.7425,
      "step": 5
    },
    {
      "epoch": 0.035698348951361,
      "grad_norm": 2.104698419570923,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 2.861,
      "step": 10
    },
    {
      "epoch": 0.0535475234270415,
      "grad_norm": 2.7389333248138428,
      "learning_rate": 8.92857142857143e-06,
      "loss": 2.8281,
      "step": 15
    },
    {
      "epoch": 0.071396697902722,
      "grad_norm": 3.9298207759857178,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 3.1888,
      "step": 20
    },
    {
      "epoch": 0.0892458723784025,
      "grad_norm": 2.648014783859253,
      "learning_rate": 1.4880952380952381e-05,
      "loss": 2.6461,
      "step": 25
    },
    {
      "epoch": 0.107095046854083,
      "grad_norm": 1.587472915649414,
      "learning_rate": 1.785714285714286e-05,
      "loss": 2.3212,
      "step": 30
    },
    {
      "epoch": 0.1249442213297635,
      "grad_norm": 0.8390935063362122,
      "learning_rate": 2.0833333333333336e-05,
      "loss": 1.8036,
      "step": 35
    },
    {
      "epoch": 0.142793395805444,
      "grad_norm": 0.46670979261398315,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.5552,
      "step": 40
    },
    {
      "epoch": 0.1606425702811245,
      "grad_norm": 0.45171597599983215,
      "learning_rate": 2.6785714285714288e-05,
      "loss": 1.6626,
      "step": 45
    },
    {
      "epoch": 0.178491744756805,
      "grad_norm": 0.5605499744415283,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 1.4897,
      "step": 50
    },
    {
      "epoch": 0.1963409192324855,
      "grad_norm": 0.5553259253501892,
      "learning_rate": 3.273809523809524e-05,
      "loss": 1.5373,
      "step": 55
    },
    {
      "epoch": 0.214190093708166,
      "grad_norm": 0.6260251402854919,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.4779,
      "step": 60
    },
    {
      "epoch": 0.2320392681838465,
      "grad_norm": 0.6063796877861023,
      "learning_rate": 3.8690476190476195e-05,
      "loss": 1.483,
      "step": 65
    },
    {
      "epoch": 0.249888442659527,
      "grad_norm": 0.5549850463867188,
      "learning_rate": 4.166666666666667e-05,
      "loss": 1.5022,
      "step": 70
    },
    {
      "epoch": 0.249888442659527,
      "eval_loss": 1.451762318611145,
      "eval_runtime": 17.7549,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 70
    },
    {
      "epoch": 0.2677376171352075,
      "grad_norm": 0.482930988073349,
      "learning_rate": 4.464285714285715e-05,
      "loss": 1.4256,
      "step": 75
    },
    {
      "epoch": 0.285586791610888,
      "grad_norm": 0.4240593910217285,
      "learning_rate": 4.761904761904762e-05,
      "loss": 1.3655,
      "step": 80
    },
    {
      "epoch": 0.3034359660865685,
      "grad_norm": 0.4872314929962158,
      "learning_rate": 5.05952380952381e-05,
      "loss": 1.4478,
      "step": 85
    },
    {
      "epoch": 0.321285140562249,
      "grad_norm": 0.42132768034935,
      "learning_rate": 5.3571428571428575e-05,
      "loss": 1.3305,
      "step": 90
    },
    {
      "epoch": 0.3391343150379295,
      "grad_norm": 0.6932046413421631,
      "learning_rate": 5.6547619047619046e-05,
      "loss": 1.4279,
      "step": 95
    },
    {
      "epoch": 0.35698348951361,
      "grad_norm": 0.6714524626731873,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 1.4967,
      "step": 100
    },
    {
      "epoch": 0.3748326639892905,
      "grad_norm": 0.5682816505432129,
      "learning_rate": 6.25e-05,
      "loss": 1.4739,
      "step": 105
    },
    {
      "epoch": 0.392681838464971,
      "grad_norm": 0.7795937657356262,
      "learning_rate": 6.547619047619048e-05,
      "loss": 1.3751,
      "step": 110
    },
    {
      "epoch": 0.4105310129406515,
      "grad_norm": 0.8056842088699341,
      "learning_rate": 6.845238095238096e-05,
      "loss": 1.3699,
      "step": 115
    },
    {
      "epoch": 0.428380187416332,
      "grad_norm": 0.8373801112174988,
      "learning_rate": 7.142857142857143e-05,
      "loss": 1.4696,
      "step": 120
    },
    {
      "epoch": 0.4462293618920125,
      "grad_norm": 1.0051416158676147,
      "learning_rate": 7.440476190476191e-05,
      "loss": 1.4059,
      "step": 125
    },
    {
      "epoch": 0.464078536367693,
      "grad_norm": 0.5304180383682251,
      "learning_rate": 7.738095238095239e-05,
      "loss": 1.3072,
      "step": 130
    },
    {
      "epoch": 0.4819277108433735,
      "grad_norm": 0.8797634243965149,
      "learning_rate": 8.035714285714287e-05,
      "loss": 1.4132,
      "step": 135
    },
    {
      "epoch": 0.499776885319054,
      "grad_norm": 0.9049625396728516,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.4121,
      "step": 140
    },
    {
      "epoch": 0.499776885319054,
      "eval_loss": 1.3727394342422485,
      "eval_runtime": 17.745,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 140
    },
    {
      "epoch": 0.5176260597947345,
      "grad_norm": 0.6793915033340454,
      "learning_rate": 8.630952380952382e-05,
      "loss": 1.3109,
      "step": 145
    },
    {
      "epoch": 0.535475234270415,
      "grad_norm": 0.7171015739440918,
      "learning_rate": 8.92857142857143e-05,
      "loss": 1.3781,
      "step": 150
    },
    {
      "epoch": 0.5533244087460955,
      "grad_norm": 0.6738716959953308,
      "learning_rate": 9.226190476190478e-05,
      "loss": 1.3564,
      "step": 155
    },
    {
      "epoch": 0.571173583221776,
      "grad_norm": 0.699975311756134,
      "learning_rate": 9.523809523809524e-05,
      "loss": 1.2387,
      "step": 160
    },
    {
      "epoch": 0.5890227576974565,
      "grad_norm": 0.7659904956817627,
      "learning_rate": 9.821428571428572e-05,
      "loss": 1.3042,
      "step": 165
    },
    {
      "epoch": 0.606871932173137,
      "grad_norm": 0.9782125353813171,
      "learning_rate": 9.999956828659095e-05,
      "loss": 1.3709,
      "step": 170
    },
    {
      "epoch": 0.6247211066488175,
      "grad_norm": 1.0532957315444946,
      "learning_rate": 9.999471159635539e-05,
      "loss": 1.3844,
      "step": 175
    },
    {
      "epoch": 0.642570281124498,
      "grad_norm": 0.7373877167701721,
      "learning_rate": 9.998445910004082e-05,
      "loss": 1.2852,
      "step": 180
    },
    {
      "epoch": 0.6604194556001785,
      "grad_norm": 1.0207768678665161,
      "learning_rate": 9.996881190417393e-05,
      "loss": 1.4652,
      "step": 185
    },
    {
      "epoch": 0.678268630075859,
      "grad_norm": 0.7943917512893677,
      "learning_rate": 9.994777169751806e-05,
      "loss": 1.3743,
      "step": 190
    },
    {
      "epoch": 0.6961178045515395,
      "grad_norm": 0.7461659908294678,
      "learning_rate": 9.992134075089084e-05,
      "loss": 1.2423,
      "step": 195
    },
    {
      "epoch": 0.71396697902722,
      "grad_norm": 0.9689913988113403,
      "learning_rate": 9.988952191691925e-05,
      "loss": 1.3113,
      "step": 200
    },
    {
      "epoch": 0.7318161535029005,
      "grad_norm": 0.766276478767395,
      "learning_rate": 9.985231862973168e-05,
      "loss": 1.3524,
      "step": 205
    },
    {
      "epoch": 0.749665327978581,
      "grad_norm": 0.6728419661521912,
      "learning_rate": 9.980973490458728e-05,
      "loss": 1.4038,
      "step": 210
    },
    {
      "epoch": 0.749665327978581,
      "eval_loss": 1.3051044940948486,
      "eval_runtime": 17.7559,
      "eval_samples_per_second": 2.591,
      "eval_steps_per_second": 2.591,
      "step": 210
    },
    {
      "epoch": 0.7675145024542614,
      "grad_norm": 1.0456575155258179,
      "learning_rate": 9.976177533744261e-05,
      "loss": 1.3626,
      "step": 215
    },
    {
      "epoch": 0.785363676929942,
      "grad_norm": 0.9017456769943237,
      "learning_rate": 9.97084451044556e-05,
      "loss": 1.3232,
      "step": 220
    },
    {
      "epoch": 0.8032128514056225,
      "grad_norm": 0.9113703966140747,
      "learning_rate": 9.964974996142698e-05,
      "loss": 1.2826,
      "step": 225
    },
    {
      "epoch": 0.821062025881303,
      "grad_norm": 0.7177279591560364,
      "learning_rate": 9.958569624317893e-05,
      "loss": 1.2794,
      "step": 230
    },
    {
      "epoch": 0.8389112003569835,
      "grad_norm": 0.9058728814125061,
      "learning_rate": 9.951629086287151e-05,
      "loss": 1.3853,
      "step": 235
    },
    {
      "epoch": 0.856760374832664,
      "grad_norm": 0.6813459992408752,
      "learning_rate": 9.944154131125642e-05,
      "loss": 1.3533,
      "step": 240
    },
    {
      "epoch": 0.8746095493083444,
      "grad_norm": 0.7113555073738098,
      "learning_rate": 9.936145565586871e-05,
      "loss": 1.3395,
      "step": 245
    },
    {
      "epoch": 0.892458723784025,
      "grad_norm": 1.243597149848938,
      "learning_rate": 9.927604254015585e-05,
      "loss": 1.443,
      "step": 250
    },
    {
      "epoch": 0.9103078982597055,
      "grad_norm": 0.8651953339576721,
      "learning_rate": 9.918531118254507e-05,
      "loss": 1.398,
      "step": 255
    },
    {
      "epoch": 0.928157072735386,
      "grad_norm": 0.8877395987510681,
      "learning_rate": 9.90892713754483e-05,
      "loss": 1.346,
      "step": 260
    },
    {
      "epoch": 0.9460062472110665,
      "grad_norm": 0.8857008814811707,
      "learning_rate": 9.898793348420536e-05,
      "loss": 1.3921,
      "step": 265
    },
    {
      "epoch": 0.963855421686747,
      "grad_norm": 0.8319969177246094,
      "learning_rate": 9.888130844596524e-05,
      "loss": 1.3838,
      "step": 270
    },
    {
      "epoch": 0.9817045961624274,
      "grad_norm": 0.7452044486999512,
      "learning_rate": 9.876940776850569e-05,
      "loss": 1.3529,
      "step": 275
    },
    {
      "epoch": 0.999553770638108,
      "grad_norm": 0.7535015940666199,
      "learning_rate": 9.865224352899119e-05,
      "loss": 1.2739,
      "step": 280
    },
    {
      "epoch": 0.999553770638108,
      "eval_loss": 1.289029836654663,
      "eval_runtime": 17.7491,
      "eval_samples_per_second": 2.592,
      "eval_steps_per_second": 2.592,
      "step": 280
    },
    {
      "epoch": 1.0174029451137885,
      "grad_norm": 0.7779117226600647,
      "learning_rate": 9.852982837266955e-05,
      "loss": 1.2339,
      "step": 285
    },
    {
      "epoch": 1.035252119589469,
      "grad_norm": 0.8113610744476318,
      "learning_rate": 9.840217551150706e-05,
      "loss": 1.0982,
      "step": 290
    },
    {
      "epoch": 1.0531012940651494,
      "grad_norm": 1.004701852798462,
      "learning_rate": 9.826929872276255e-05,
      "loss": 1.2537,
      "step": 295
    },
    {
      "epoch": 1.07095046854083,
      "grad_norm": 1.524734616279602,
      "learning_rate": 9.81312123475006e-05,
      "loss": 1.1664,
      "step": 300
    },
    {
      "epoch": 1.0887996430165106,
      "grad_norm": 1.5680856704711914,
      "learning_rate": 9.798793128904356e-05,
      "loss": 1.08,
      "step": 305
    },
    {
      "epoch": 1.106648817492191,
      "grad_norm": 1.4838035106658936,
      "learning_rate": 9.78394710113631e-05,
      "loss": 1.1029,
      "step": 310
    },
    {
      "epoch": 1.1244979919678715,
      "grad_norm": 1.522316575050354,
      "learning_rate": 9.768584753741134e-05,
      "loss": 1.1524,
      "step": 315
    },
    {
      "epoch": 1.142347166443552,
      "grad_norm": 1.3976528644561768,
      "learning_rate": 9.752707744739145e-05,
      "loss": 1.1328,
      "step": 320
    },
    {
      "epoch": 1.1601963409192324,
      "grad_norm": 1.4764764308929443,
      "learning_rate": 9.736317787696816e-05,
      "loss": 1.1174,
      "step": 325
    },
    {
      "epoch": 1.178045515394913,
      "grad_norm": 1.3623173236846924,
      "learning_rate": 9.719416651541839e-05,
      "loss": 1.0493,
      "step": 330
    },
    {
      "epoch": 1.1958946898705936,
      "grad_norm": 1.3625001907348633,
      "learning_rate": 9.702006160372209e-05,
      "loss": 1.0479,
      "step": 335
    },
    {
      "epoch": 1.213743864346274,
      "grad_norm": 1.7509726285934448,
      "learning_rate": 9.684088193259355e-05,
      "loss": 1.1043,
      "step": 340
    },
    {
      "epoch": 1.2315930388219545,
      "grad_norm": 1.5920188426971436,
      "learning_rate": 9.665664684045333e-05,
      "loss": 1.1096,
      "step": 345
    },
    {
      "epoch": 1.249442213297635,
      "grad_norm": 1.6554943323135376,
      "learning_rate": 9.646737621134112e-05,
      "loss": 1.1436,
      "step": 350
    },
    {
      "epoch": 1.249442213297635,
      "eval_loss": 1.3194608688354492,
      "eval_runtime": 17.7382,
      "eval_samples_per_second": 2.593,
      "eval_steps_per_second": 2.593,
      "step": 350
    }
  ],
  "logging_steps": 5,
  "max_steps": 1680,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 70,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.6873658006634496e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}