{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 270,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003703703703703704,
      "grad_norm": 0.6600888967514038,
      "learning_rate": 1.111111111111111e-05,
      "loss": 1.6547,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.0668487548828125,
      "learning_rate": 5.5555555555555545e-05,
      "loss": 1.6004,
      "step": 5
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.8215888142585754,
      "learning_rate": 0.00011111111111111109,
      "loss": 1.5361,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.627755045890808,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.3368,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 1.0417497158050537,
      "learning_rate": 0.00022222222222222218,
      "loss": 0.9318,
      "step": 20
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.45057186484336853,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.7995,
      "step": 25
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.3393832743167877,
      "learning_rate": 0.0002998871928756345,
      "loss": 0.7298,
      "step": 30
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.2655043601989746,
      "learning_rate": 0.0002991984303609902,
      "loss": 0.6803,
      "step": 35
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.1693999469280243,
      "learning_rate": 0.0002978864495017194,
      "loss": 0.65,
      "step": 40
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.1550581008195877,
      "learning_rate": 0.00029595673058697357,
      "loss": 0.6344,
      "step": 45
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.13547781109809875,
      "learning_rate": 0.0002934173342660819,
      "loss": 0.6189,
      "step": 50
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.12479308992624283,
      "learning_rate": 0.00029027886787832844,
      "loss": 0.6105,
      "step": 55
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.14283517003059387,
      "learning_rate": 0.000286554441144922,
      "loss": 0.6005,
      "step": 60
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.15204459428787231,
      "learning_rate": 0.0002822596114082412,
      "loss": 0.6063,
      "step": 65
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.1366046667098999,
      "learning_rate": 0.0002774123186470946,
      "loss": 0.5926,
      "step": 70
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.13155071437358856,
      "learning_rate": 0.0002720328105394451,
      "loss": 0.5877,
      "step": 75
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.14542943239212036,
      "learning_rate": 0.00026614355788561985,
      "loss": 0.5688,
      "step": 80
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.14441293478012085,
      "learning_rate": 0.00025976916074529183,
      "loss": 0.5706,
      "step": 85
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.13577958941459656,
      "learning_rate": 0.00025293624568031,
      "loss": 0.5717,
      "step": 90
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.16319440305233002,
      "learning_rate": 0.0002456733545326059,
      "loss": 0.5709,
      "step": 95
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.13978739082813263,
      "learning_rate": 0.00023801082520176267,
      "loss": 0.5565,
      "step": 100
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.16405534744262695,
      "learning_rate": 0.0002299806649202537,
      "loss": 0.5682,
      "step": 105
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.14882802963256836,
      "learning_rate": 0.00022161641655569234,
      "loss": 0.5525,
      "step": 110
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.15766838192939758,
      "learning_rate": 0.00021295301849856435,
      "loss": 0.5525,
      "step": 115
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.16089104115962982,
      "learning_rate": 0.00020402665872070654,
      "loss": 0.5477,
      "step": 120
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.1631491482257843,
      "learning_rate": 0.00019487462361414626,
      "loss": 0.5503,
      "step": 125
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.15596701204776764,
      "learning_rate": 0.00018553514224171783,
      "loss": 0.5469,
      "step": 130
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.1614404171705246,
      "learning_rate": 0.00017604722665003956,
      "loss": 0.5532,
      "step": 135
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.15226240456104279,
      "learning_rate": 0.00016645050891187974,
      "loss": 0.5432,
      "step": 140
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.16388216614723206,
      "learning_rate": 0.00015678507557860595,
      "loss": 0.542,
      "step": 145
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.15366673469543457,
      "learning_rate": 0.00014709130023422633,
      "loss": 0.5475,
      "step": 150
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.16850697994232178,
      "learning_rate": 0.00013740967485046393,
      "loss": 0.5516,
      "step": 155
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.16164420545101166,
      "learning_rate": 0.0001277806406473127,
      "loss": 0.5372,
      "step": 160
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.16969184577465057,
      "learning_rate": 0.00011824441916558842,
      "loss": 0.5324,
      "step": 165
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.17503169178962708,
      "learning_rate": 0.00010884084425710479,
      "loss": 0.5372,
      "step": 170
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.17154920101165771,
      "learning_rate": 9.960919569426869e-05,
      "loss": 0.5339,
      "step": 175
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.16324155032634735,
      "learning_rate": 9.058803509412646e-05,
      "loss": 0.5415,
      "step": 180
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.1716451346874237,
      "learning_rate": 8.18150448422249e-05,
      "loss": 0.5329,
      "step": 185
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.15859860181808472,
      "learning_rate": 7.332687068911903e-05,
      "loss": 0.5368,
      "step": 190
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.16680656373500824,
      "learning_rate": 6.515896867701923e-05,
      "loss": 0.538,
      "step": 195
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.1692035049200058,
      "learning_rate": 5.734545703598145e-05,
      "loss": 0.5323,
      "step": 200
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.1742638200521469,
      "learning_rate": 4.991897366828704e-05,
      "loss": 0.5375,
      "step": 205
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.1706262081861496,
      "learning_rate": 4.2910539816315164e-05,
      "loss": 0.5286,
      "step": 210
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.15826331079006195,
      "learning_rate": 3.6349430483382306e-05,
      "loss": 0.5273,
      "step": 215
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.15241724252700806,
      "learning_rate": 3.0263052148816046e-05,
      "loss": 0.5285,
      "step": 220
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.1507098227739334,
      "learning_rate": 2.4676828288059558e-05,
      "loss": 0.5356,
      "step": 225
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.15940095484256744,
      "learning_rate": 1.9614093176002828e-05,
      "loss": 0.5417,
      "step": 230
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.16012977063655853,
      "learning_rate": 1.5095994417136053e-05,
      "loss": 0.5323,
      "step": 235
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.1607007086277008,
      "learning_rate": 1.1141404609666449e-05,
      "loss": 0.5234,
      "step": 240
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.15569806098937988,
      "learning_rate": 7.766842512588529e-06,
      "loss": 0.5293,
      "step": 245
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.15847626328468323,
      "learning_rate": 4.986404045000697e-06,
      "loss": 0.5286,
      "step": 250
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.16243720054626465,
      "learning_rate": 2.811703405892296e-06,
      "loss": 0.525,
      "step": 255
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.1597120612859726,
      "learning_rate": 1.2518245603498345e-06,
      "loss": 0.5295,
      "step": 260
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.15212252736091614,
      "learning_rate": 3.1328329483019663e-07,
      "loss": 0.5356,
      "step": 265
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.15848107635974884,
      "learning_rate": 0.0,
      "loss": 0.5385,
      "step": 270
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2769262790679932,
      "eval_runtime": 1.0983,
      "eval_samples_per_second": 3.642,
      "eval_steps_per_second": 0.911,
      "step": 270
    },
    {
      "epoch": 1.0,
      "step": 270,
      "total_flos": 7.971478934745252e+17,
      "train_loss": 0.6237873245168615,
      "train_runtime": 2852.5229,
      "train_samples_per_second": 6.048,
      "train_steps_per_second": 0.095
    }
  ],
  "logging_steps": 5,
  "max_steps": 270,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.971478934745252e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}