{
  "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": 0.6748902201652527,
      "learning_rate": 1.111111111111111e-05,
      "loss": 1.6565,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 0.8883910775184631,
      "learning_rate": 5.5555555555555545e-05,
      "loss": 1.6019,
      "step": 5
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.9978822469711304,
      "learning_rate": 0.00011111111111111109,
      "loss": 1.5359,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.5893608331680298,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.3426,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.9495543241500854,
      "learning_rate": 0.00022222222222222218,
      "loss": 0.9366,
      "step": 20
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.4493098258972168,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.8074,
      "step": 25
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.3246346712112427,
      "learning_rate": 0.0002998871928756345,
      "loss": 0.7346,
      "step": 30
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.28874966502189636,
      "learning_rate": 0.0002991984303609902,
      "loss": 0.6855,
      "step": 35
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.19572241604328156,
      "learning_rate": 0.0002978864495017194,
      "loss": 0.6548,
      "step": 40
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.16895747184753418,
      "learning_rate": 0.00029595673058697357,
      "loss": 0.6371,
      "step": 45
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.16596512496471405,
      "learning_rate": 0.0002934173342660819,
      "loss": 0.6211,
      "step": 50
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.13342902064323425,
      "learning_rate": 0.00029027886787832844,
      "loss": 0.6124,
      "step": 55
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.1435386687517166,
      "learning_rate": 0.000286554441144922,
      "loss": 0.6021,
      "step": 60
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.1567266881465912,
      "learning_rate": 0.0002822596114082412,
      "loss": 0.6076,
      "step": 65
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.14005671441555023,
      "learning_rate": 0.0002774123186470946,
      "loss": 0.5941,
      "step": 70
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.13816745579242706,
      "learning_rate": 0.0002720328105394451,
      "loss": 0.5891,
      "step": 75
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.1502453237771988,
      "learning_rate": 0.00026614355788561985,
      "loss": 0.5701,
      "step": 80
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.14816893637180328,
      "learning_rate": 0.00025976916074529183,
      "loss": 0.5718,
      "step": 85
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.13009826838970184,
      "learning_rate": 0.00025293624568031,
      "loss": 0.5729,
      "step": 90
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.18656130135059357,
      "learning_rate": 0.0002456733545326059,
      "loss": 0.5724,
      "step": 95
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.14232292771339417,
      "learning_rate": 0.00023801082520176267,
      "loss": 0.5582,
      "step": 100
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.15933294594287872,
      "learning_rate": 0.0002299806649202537,
      "loss": 0.5697,
      "step": 105
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.15552918612957,
      "learning_rate": 0.00022161641655569234,
      "loss": 0.5544,
      "step": 110
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.16393014788627625,
      "learning_rate": 0.00021295301849856435,
      "loss": 0.5542,
      "step": 115
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.1773192435503006,
      "learning_rate": 0.00020402665872070654,
      "loss": 0.5491,
      "step": 120
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.16194891929626465,
      "learning_rate": 0.00019487462361414626,
      "loss": 0.5525,
      "step": 125
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.15379634499549866,
      "learning_rate": 0.00018553514224171783,
      "loss": 0.5489,
      "step": 130
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.170404314994812,
      "learning_rate": 0.00017604722665003956,
      "loss": 0.5549,
      "step": 135
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.15406401455402374,
      "learning_rate": 0.00016645050891187974,
      "loss": 0.5451,
      "step": 140
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.16518822312355042,
      "learning_rate": 0.00015678507557860595,
      "loss": 0.5436,
      "step": 145
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.15576022863388062,
      "learning_rate": 0.00014709130023422633,
      "loss": 0.5492,
      "step": 150
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.1619407832622528,
      "learning_rate": 0.00013740967485046393,
      "loss": 0.5525,
      "step": 155
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1685595065355301,
      "learning_rate": 0.0001277806406473127,
      "loss": 0.5385,
      "step": 160
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.16706547141075134,
      "learning_rate": 0.00011824441916558842,
      "loss": 0.5333,
      "step": 165
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.1658417284488678,
      "learning_rate": 0.00010884084425710479,
      "loss": 0.5383,
      "step": 170
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.16389456391334534,
      "learning_rate": 9.960919569426869e-05,
      "loss": 0.5353,
      "step": 175
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1591169834136963,
      "learning_rate": 9.058803509412646e-05,
      "loss": 0.5431,
      "step": 180
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.1656966358423233,
      "learning_rate": 8.18150448422249e-05,
      "loss": 0.5342,
      "step": 185
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.1611323356628418,
      "learning_rate": 7.332687068911903e-05,
      "loss": 0.5387,
      "step": 190
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.16765892505645752,
      "learning_rate": 6.515896867701923e-05,
      "loss": 0.5399,
      "step": 195
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.1689939796924591,
      "learning_rate": 5.734545703598145e-05,
      "loss": 0.5337,
      "step": 200
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.17689311504364014,
      "learning_rate": 4.991897366828704e-05,
      "loss": 0.539,
      "step": 205
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.16849064826965332,
      "learning_rate": 4.2910539816315164e-05,
      "loss": 0.5298,
      "step": 210
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.1593889743089676,
      "learning_rate": 3.6349430483382306e-05,
      "loss": 0.5287,
      "step": 215
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.1509651094675064,
      "learning_rate": 3.0263052148816046e-05,
      "loss": 0.5303,
      "step": 220
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.1566237062215805,
      "learning_rate": 2.4676828288059558e-05,
      "loss": 0.5365,
      "step": 225
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.15855161845684052,
      "learning_rate": 1.9614093176002828e-05,
      "loss": 0.5433,
      "step": 230
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.16000784933567047,
      "learning_rate": 1.5095994417136053e-05,
      "loss": 0.5336,
      "step": 235
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.15544116497039795,
      "learning_rate": 1.1141404609666449e-05,
      "loss": 0.5255,
      "step": 240
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.15555834770202637,
      "learning_rate": 7.766842512588529e-06,
      "loss": 0.5307,
      "step": 245
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.163555309176445,
      "learning_rate": 4.986404045000697e-06,
      "loss": 0.5301,
      "step": 250
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.16425177454948425,
      "learning_rate": 2.811703405892296e-06,
      "loss": 0.5268,
      "step": 255
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.15855489671230316,
      "learning_rate": 1.2518245603498345e-06,
      "loss": 0.5314,
      "step": 260
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.1560031622648239,
      "learning_rate": 3.1328329483019663e-07,
      "loss": 0.5381,
      "step": 265
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.16213464736938477,
      "learning_rate": 0.0,
      "loss": 0.5406,
      "step": 270
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2763605117797852,
      "eval_runtime": 1.1636,
      "eval_samples_per_second": 3.438,
      "eval_steps_per_second": 0.859,
      "step": 270
    },
    {
      "epoch": 1.0,
      "step": 270,
      "total_flos": 7.971483567941222e+17,
      "train_loss": 0.6257878903989439,
      "train_runtime": 2906.8071,
      "train_samples_per_second": 5.935,
      "train_steps_per_second": 0.093
    }
  ],
  "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": 7.971483567941222e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}