{
  "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": 0.6735236644744873,
      "learning_rate": 1.111111111111111e-05,
      "loss": 1.6565,
      "step": 1
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": 1.047855257987976,
      "learning_rate": 5.5555555555555545e-05,
      "loss": 1.602,
      "step": 5
    },
    {
      "epoch": 0.037037037037037035,
      "grad_norm": 0.8623495101928711,
      "learning_rate": 0.00011111111111111109,
      "loss": 1.5366,
      "step": 10
    },
    {
      "epoch": 0.05555555555555555,
      "grad_norm": 1.691426396369934,
      "learning_rate": 0.00016666666666666666,
      "loss": 1.3396,
      "step": 15
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.9092234969139099,
      "learning_rate": 0.00022222222222222218,
      "loss": 0.9343,
      "step": 20
    },
    {
      "epoch": 0.09259259259259259,
      "grad_norm": 0.4330471158027649,
      "learning_rate": 0.0002777777777777778,
      "loss": 0.8052,
      "step": 25
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 0.3238295912742615,
      "learning_rate": 0.0002998871928756345,
      "loss": 0.7332,
      "step": 30
    },
    {
      "epoch": 0.12962962962962962,
      "grad_norm": 0.29893988370895386,
      "learning_rate": 0.0002991984303609902,
      "loss": 0.6842,
      "step": 35
    },
    {
      "epoch": 0.14814814814814814,
      "grad_norm": 0.18665669858455658,
      "learning_rate": 0.0002978864495017194,
      "loss": 0.6534,
      "step": 40
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.16193003952503204,
      "learning_rate": 0.00029595673058697357,
      "loss": 0.6364,
      "step": 45
    },
    {
      "epoch": 0.18518518518518517,
      "grad_norm": 0.14426390826702118,
      "learning_rate": 0.0002934173342660819,
      "loss": 0.6201,
      "step": 50
    },
    {
      "epoch": 0.2037037037037037,
      "grad_norm": 0.1245051696896553,
      "learning_rate": 0.00029027886787832844,
      "loss": 0.6117,
      "step": 55
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.14398011565208435,
      "learning_rate": 0.000286554441144922,
      "loss": 0.6018,
      "step": 60
    },
    {
      "epoch": 0.24074074074074073,
      "grad_norm": 0.1676715612411499,
      "learning_rate": 0.0002822596114082412,
      "loss": 0.6073,
      "step": 65
    },
    {
      "epoch": 0.25925925925925924,
      "grad_norm": 0.1390787661075592,
      "learning_rate": 0.0002774123186470946,
      "loss": 0.594,
      "step": 70
    },
    {
      "epoch": 0.2777777777777778,
      "grad_norm": 0.13183851540088654,
      "learning_rate": 0.0002720328105394451,
      "loss": 0.589,
      "step": 75
    },
    {
      "epoch": 0.2962962962962963,
      "grad_norm": 0.14338625967502594,
      "learning_rate": 0.00026614355788561985,
      "loss": 0.5699,
      "step": 80
    },
    {
      "epoch": 0.3148148148148148,
      "grad_norm": 0.1453503519296646,
      "learning_rate": 0.00025976916074529183,
      "loss": 0.5717,
      "step": 85
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 0.13095735013484955,
      "learning_rate": 0.00025293624568031,
      "loss": 0.5729,
      "step": 90
    },
    {
      "epoch": 0.35185185185185186,
      "grad_norm": 0.16470138728618622,
      "learning_rate": 0.0002456733545326059,
      "loss": 0.5723,
      "step": 95
    },
    {
      "epoch": 0.37037037037037035,
      "grad_norm": 0.13821054995059967,
      "learning_rate": 0.00023801082520176267,
      "loss": 0.5583,
      "step": 100
    },
    {
      "epoch": 0.3888888888888889,
      "grad_norm": 0.16222749650478363,
      "learning_rate": 0.0002299806649202537,
      "loss": 0.5695,
      "step": 105
    },
    {
      "epoch": 0.4074074074074074,
      "grad_norm": 0.1531219631433487,
      "learning_rate": 0.00022161641655569234,
      "loss": 0.5538,
      "step": 110
    },
    {
      "epoch": 0.42592592592592593,
      "grad_norm": 0.15927164256572723,
      "learning_rate": 0.00021295301849856435,
      "loss": 0.5544,
      "step": 115
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.16342100501060486,
      "learning_rate": 0.00020402665872070654,
      "loss": 0.5492,
      "step": 120
    },
    {
      "epoch": 0.46296296296296297,
      "grad_norm": 0.15846914052963257,
      "learning_rate": 0.00019487462361414626,
      "loss": 0.552,
      "step": 125
    },
    {
      "epoch": 0.48148148148148145,
      "grad_norm": 0.14684665203094482,
      "learning_rate": 0.00018553514224171783,
      "loss": 0.5486,
      "step": 130
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.15133161842823029,
      "learning_rate": 0.00017604722665003956,
      "loss": 0.555,
      "step": 135
    },
    {
      "epoch": 0.5185185185185185,
      "grad_norm": 0.15221647918224335,
      "learning_rate": 0.00016645050891187974,
      "loss": 0.5451,
      "step": 140
    },
    {
      "epoch": 0.5370370370370371,
      "grad_norm": 0.1682116985321045,
      "learning_rate": 0.00015678507557860595,
      "loss": 0.5435,
      "step": 145
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 0.15022225677967072,
      "learning_rate": 0.00014709130023422633,
      "loss": 0.5494,
      "step": 150
    },
    {
      "epoch": 0.5740740740740741,
      "grad_norm": 0.16548554599285126,
      "learning_rate": 0.00013740967485046393,
      "loss": 0.5528,
      "step": 155
    },
    {
      "epoch": 0.5925925925925926,
      "grad_norm": 0.16638116538524628,
      "learning_rate": 0.0001277806406473127,
      "loss": 0.5383,
      "step": 160
    },
    {
      "epoch": 0.6111111111111112,
      "grad_norm": 0.16238638758659363,
      "learning_rate": 0.00011824441916558842,
      "loss": 0.534,
      "step": 165
    },
    {
      "epoch": 0.6296296296296297,
      "grad_norm": 0.16411995887756348,
      "learning_rate": 0.00010884084425710479,
      "loss": 0.5385,
      "step": 170
    },
    {
      "epoch": 0.6481481481481481,
      "grad_norm": 0.16393356025218964,
      "learning_rate": 9.960919569426869e-05,
      "loss": 0.5353,
      "step": 175
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.1613512635231018,
      "learning_rate": 9.058803509412646e-05,
      "loss": 0.5434,
      "step": 180
    },
    {
      "epoch": 0.6851851851851852,
      "grad_norm": 0.1644994616508484,
      "learning_rate": 8.18150448422249e-05,
      "loss": 0.5345,
      "step": 185
    },
    {
      "epoch": 0.7037037037037037,
      "grad_norm": 0.15923035144805908,
      "learning_rate": 7.332687068911903e-05,
      "loss": 0.5385,
      "step": 190
    },
    {
      "epoch": 0.7222222222222222,
      "grad_norm": 0.16599948704242706,
      "learning_rate": 6.515896867701923e-05,
      "loss": 0.54,
      "step": 195
    },
    {
      "epoch": 0.7407407407407407,
      "grad_norm": 0.16556750237941742,
      "learning_rate": 5.734545703598145e-05,
      "loss": 0.5339,
      "step": 200
    },
    {
      "epoch": 0.7592592592592593,
      "grad_norm": 0.17149387300014496,
      "learning_rate": 4.991897366828704e-05,
      "loss": 0.5386,
      "step": 205
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 0.16719135642051697,
      "learning_rate": 4.2910539816315164e-05,
      "loss": 0.53,
      "step": 210
    },
    {
      "epoch": 0.7962962962962963,
      "grad_norm": 0.15575380623340607,
      "learning_rate": 3.6349430483382306e-05,
      "loss": 0.5288,
      "step": 215
    },
    {
      "epoch": 0.8148148148148148,
      "grad_norm": 0.15009023249149323,
      "learning_rate": 3.0263052148816046e-05,
      "loss": 0.5302,
      "step": 220
    },
    {
      "epoch": 0.8333333333333334,
      "grad_norm": 0.15368495881557465,
      "learning_rate": 2.4676828288059558e-05,
      "loss": 0.5369,
      "step": 225
    },
    {
      "epoch": 0.8518518518518519,
      "grad_norm": 0.1581869274377823,
      "learning_rate": 1.9614093176002828e-05,
      "loss": 0.5435,
      "step": 230
    },
    {
      "epoch": 0.8703703703703703,
      "grad_norm": 0.16010069847106934,
      "learning_rate": 1.5095994417136053e-05,
      "loss": 0.5342,
      "step": 235
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.15556618571281433,
      "learning_rate": 1.1141404609666449e-05,
      "loss": 0.5253,
      "step": 240
    },
    {
      "epoch": 0.9074074074074074,
      "grad_norm": 0.15522176027297974,
      "learning_rate": 7.766842512588529e-06,
      "loss": 0.531,
      "step": 245
    },
    {
      "epoch": 0.9259259259259259,
      "grad_norm": 0.16106705367565155,
      "learning_rate": 4.986404045000697e-06,
      "loss": 0.5304,
      "step": 250
    },
    {
      "epoch": 0.9444444444444444,
      "grad_norm": 0.1596304476261139,
      "learning_rate": 2.811703405892296e-06,
      "loss": 0.5268,
      "step": 255
    },
    {
      "epoch": 0.9629629629629629,
      "grad_norm": 0.15755844116210938,
      "learning_rate": 1.2518245603498345e-06,
      "loss": 0.5315,
      "step": 260
    },
    {
      "epoch": 0.9814814814814815,
      "grad_norm": 0.20954440534114838,
      "learning_rate": 3.1328329483019663e-07,
      "loss": 0.5378,
      "step": 265
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.16012723743915558,
      "learning_rate": 0.0,
      "loss": 0.5403,
      "step": 270
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.2819597721099854,
      "eval_runtime": 1.1563,
      "eval_samples_per_second": 3.459,
      "eval_steps_per_second": 0.865,
      "step": 270
    },
    {
      "epoch": 1.0,
      "step": 270,
      "total_flos": 7.971483567941222e+17,
      "train_loss": 0.6255532653243453,
      "train_runtime": 2916.7528,
      "train_samples_per_second": 5.915,
      "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
}