{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0653893938403191,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000653893938403191,
      "grad_norm": 8.0,
      "learning_rate": 1e-05,
      "loss": 10.9235,
      "step": 5
    },
    {
      "epoch": 0.001307787876806382,
      "grad_norm": 7.3125,
      "learning_rate": 2e-05,
      "loss": 10.8446,
      "step": 10
    },
    {
      "epoch": 0.001961681815209573,
      "grad_norm": 5.1875,
      "learning_rate": 3e-05,
      "loss": 10.6184,
      "step": 15
    },
    {
      "epoch": 0.002615575753612764,
      "grad_norm": 3.453125,
      "learning_rate": 4e-05,
      "loss": 10.4354,
      "step": 20
    },
    {
      "epoch": 0.003269469692015955,
      "grad_norm": 3.359375,
      "learning_rate": 5e-05,
      "loss": 10.2832,
      "step": 25
    },
    {
      "epoch": 0.003923363630419146,
      "grad_norm": 2.90625,
      "learning_rate": 6e-05,
      "loss": 10.1894,
      "step": 30
    },
    {
      "epoch": 0.004577257568822337,
      "grad_norm": 2.984375,
      "learning_rate": 7.000000000000001e-05,
      "loss": 10.0521,
      "step": 35
    },
    {
      "epoch": 0.005231151507225528,
      "grad_norm": 2.5625,
      "learning_rate": 8e-05,
      "loss": 9.9261,
      "step": 40
    },
    {
      "epoch": 0.005885045445628719,
      "grad_norm": 2.59375,
      "learning_rate": 8.999999999999999e-05,
      "loss": 9.7805,
      "step": 45
    },
    {
      "epoch": 0.00653893938403191,
      "grad_norm": 2.515625,
      "learning_rate": 0.0001,
      "loss": 9.5316,
      "step": 50
    },
    {
      "epoch": 0.007192833322435101,
      "grad_norm": 2.109375,
      "learning_rate": 0.00011,
      "loss": 9.3912,
      "step": 55
    },
    {
      "epoch": 0.007846727260838291,
      "grad_norm": 2.015625,
      "learning_rate": 0.00012,
      "loss": 9.2058,
      "step": 60
    },
    {
      "epoch": 0.008500621199241483,
      "grad_norm": 1.828125,
      "learning_rate": 0.00013000000000000002,
      "loss": 9.0564,
      "step": 65
    },
    {
      "epoch": 0.009154515137644674,
      "grad_norm": 1.703125,
      "learning_rate": 0.00014000000000000001,
      "loss": 8.8344,
      "step": 70
    },
    {
      "epoch": 0.009808409076047865,
      "grad_norm": 1.375,
      "learning_rate": 0.00015,
      "loss": 8.6926,
      "step": 75
    },
    {
      "epoch": 0.010462303014451056,
      "grad_norm": 1.3125,
      "learning_rate": 0.00016,
      "loss": 8.5817,
      "step": 80
    },
    {
      "epoch": 0.011116196952854247,
      "grad_norm": 1.171875,
      "learning_rate": 0.00017,
      "loss": 8.4945,
      "step": 85
    },
    {
      "epoch": 0.011770090891257438,
      "grad_norm": 1.0859375,
      "learning_rate": 0.00017999999999999998,
      "loss": 8.4975,
      "step": 90
    },
    {
      "epoch": 0.01242398482966063,
      "grad_norm": 1.2734375,
      "learning_rate": 0.00019,
      "loss": 8.4394,
      "step": 95
    },
    {
      "epoch": 0.01307787876806382,
      "grad_norm": 1.359375,
      "learning_rate": 0.0002,
      "loss": 8.4332,
      "step": 100
    },
    {
      "epoch": 0.013731772706467011,
      "grad_norm": 1.9375,
      "learning_rate": 0.00021,
      "loss": 8.4649,
      "step": 105
    },
    {
      "epoch": 0.014385666644870202,
      "grad_norm": 1.34375,
      "learning_rate": 0.00022,
      "loss": 8.408,
      "step": 110
    },
    {
      "epoch": 0.015039560583273394,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00023,
      "loss": 8.3359,
      "step": 115
    },
    {
      "epoch": 0.015693454521676583,
      "grad_norm": 1.3671875,
      "learning_rate": 0.00024,
      "loss": 8.3483,
      "step": 120
    },
    {
      "epoch": 0.016347348460079774,
      "grad_norm": 1.484375,
      "learning_rate": 0.00025,
      "loss": 8.3056,
      "step": 125
    },
    {
      "epoch": 0.017001242398482965,
      "grad_norm": 1.390625,
      "learning_rate": 0.00026000000000000003,
      "loss": 8.3724,
      "step": 130
    },
    {
      "epoch": 0.017655136336886156,
      "grad_norm": 2.171875,
      "learning_rate": 0.00027,
      "loss": 8.3476,
      "step": 135
    },
    {
      "epoch": 0.018309030275289347,
      "grad_norm": 1.421875,
      "learning_rate": 0.00028000000000000003,
      "loss": 8.2929,
      "step": 140
    },
    {
      "epoch": 0.01896292421369254,
      "grad_norm": 1.6875,
      "learning_rate": 0.00029,
      "loss": 8.2493,
      "step": 145
    },
    {
      "epoch": 0.01961681815209573,
      "grad_norm": 1.3125,
      "learning_rate": 0.0003,
      "loss": 8.291,
      "step": 150
    },
    {
      "epoch": 0.02027071209049892,
      "grad_norm": 1.3046875,
      "learning_rate": 0.00031,
      "loss": 8.1787,
      "step": 155
    },
    {
      "epoch": 0.02092460602890211,
      "grad_norm": 1.4375,
      "learning_rate": 0.00032,
      "loss": 8.2745,
      "step": 160
    },
    {
      "epoch": 0.021578499967305303,
      "grad_norm": 1.484375,
      "learning_rate": 0.00033,
      "loss": 8.1676,
      "step": 165
    },
    {
      "epoch": 0.022232393905708494,
      "grad_norm": 1.453125,
      "learning_rate": 0.00034,
      "loss": 8.1576,
      "step": 170
    },
    {
      "epoch": 0.022886287844111685,
      "grad_norm": 1.515625,
      "learning_rate": 0.00035,
      "loss": 8.1338,
      "step": 175
    },
    {
      "epoch": 0.023540181782514876,
      "grad_norm": 1.34375,
      "learning_rate": 0.00035999999999999997,
      "loss": 8.0981,
      "step": 180
    },
    {
      "epoch": 0.024194075720918067,
      "grad_norm": 1.8515625,
      "learning_rate": 0.00037,
      "loss": 8.1553,
      "step": 185
    },
    {
      "epoch": 0.02484796965932126,
      "grad_norm": 2.0625,
      "learning_rate": 0.00038,
      "loss": 8.0505,
      "step": 190
    },
    {
      "epoch": 0.02550186359772445,
      "grad_norm": 1.4140625,
      "learning_rate": 0.00039000000000000005,
      "loss": 8.0276,
      "step": 195
    },
    {
      "epoch": 0.02615575753612764,
      "grad_norm": 1.46875,
      "learning_rate": 0.0004,
      "loss": 8.026,
      "step": 200
    },
    {
      "epoch": 0.02680965147453083,
      "grad_norm": 1.453125,
      "learning_rate": 0.00041,
      "loss": 8.0615,
      "step": 205
    },
    {
      "epoch": 0.027463545412934023,
      "grad_norm": 1.6171875,
      "learning_rate": 0.00042,
      "loss": 8.0192,
      "step": 210
    },
    {
      "epoch": 0.028117439351337214,
      "grad_norm": 1.5390625,
      "learning_rate": 0.00043,
      "loss": 7.9596,
      "step": 215
    },
    {
      "epoch": 0.028771333289740405,
      "grad_norm": 1.484375,
      "learning_rate": 0.00044,
      "loss": 7.9729,
      "step": 220
    },
    {
      "epoch": 0.029425227228143596,
      "grad_norm": 1.5078125,
      "learning_rate": 0.00045000000000000004,
      "loss": 7.9676,
      "step": 225
    },
    {
      "epoch": 0.030079121166546787,
      "grad_norm": 1.703125,
      "learning_rate": 0.00046,
      "loss": 7.9347,
      "step": 230
    },
    {
      "epoch": 0.030733015104949978,
      "grad_norm": 1.875,
      "learning_rate": 0.00047,
      "loss": 7.9303,
      "step": 235
    },
    {
      "epoch": 0.031386909043353166,
      "grad_norm": 1.671875,
      "learning_rate": 0.00048,
      "loss": 7.9393,
      "step": 240
    },
    {
      "epoch": 0.03204080298175636,
      "grad_norm": 1.59375,
      "learning_rate": 0.00049,
      "loss": 7.8751,
      "step": 245
    },
    {
      "epoch": 0.03269469692015955,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0005,
      "loss": 7.9601,
      "step": 250
    },
    {
      "epoch": 0.03334859085856274,
      "grad_norm": 1.4765625,
      "learning_rate": 0.00051,
      "loss": 7.8759,
      "step": 255
    },
    {
      "epoch": 0.03400248479696593,
      "grad_norm": 1.6796875,
      "learning_rate": 0.0005200000000000001,
      "loss": 7.8174,
      "step": 260
    },
    {
      "epoch": 0.03465637873536912,
      "grad_norm": 1.4609375,
      "learning_rate": 0.0005300000000000001,
      "loss": 7.8309,
      "step": 265
    },
    {
      "epoch": 0.03531027267377231,
      "grad_norm": 1.90625,
      "learning_rate": 0.00054,
      "loss": 7.8638,
      "step": 270
    },
    {
      "epoch": 0.035964166612175504,
      "grad_norm": 1.6875,
      "learning_rate": 0.00055,
      "loss": 7.8285,
      "step": 275
    },
    {
      "epoch": 0.036618060550578695,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0005600000000000001,
      "loss": 7.8669,
      "step": 280
    },
    {
      "epoch": 0.037271954488981886,
      "grad_norm": 1.5,
      "learning_rate": 0.00057,
      "loss": 7.8088,
      "step": 285
    },
    {
      "epoch": 0.03792584842738508,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00058,
      "loss": 7.7459,
      "step": 290
    },
    {
      "epoch": 0.03857974236578827,
      "grad_norm": 1.6015625,
      "learning_rate": 0.00059,
      "loss": 7.7809,
      "step": 295
    },
    {
      "epoch": 0.03923363630419146,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0006,
      "loss": 7.7242,
      "step": 300
    },
    {
      "epoch": 0.03988753024259465,
      "grad_norm": 1.5625,
      "learning_rate": 0.00061,
      "loss": 7.7242,
      "step": 305
    },
    {
      "epoch": 0.04054142418099784,
      "grad_norm": 1.625,
      "learning_rate": 0.00062,
      "loss": 7.7411,
      "step": 310
    },
    {
      "epoch": 0.04119531811940103,
      "grad_norm": 1.4921875,
      "learning_rate": 0.00063,
      "loss": 7.6911,
      "step": 315
    },
    {
      "epoch": 0.04184921205780422,
      "grad_norm": 1.4296875,
      "learning_rate": 0.00064,
      "loss": 7.6351,
      "step": 320
    },
    {
      "epoch": 0.042503105996207415,
      "grad_norm": 1.5078125,
      "learning_rate": 0.0006500000000000001,
      "loss": 7.6582,
      "step": 325
    },
    {
      "epoch": 0.043156999934610606,
      "grad_norm": 1.6640625,
      "learning_rate": 0.00066,
      "loss": 7.6329,
      "step": 330
    },
    {
      "epoch": 0.0438108938730138,
      "grad_norm": 1.6875,
      "learning_rate": 0.00067,
      "loss": 7.6285,
      "step": 335
    },
    {
      "epoch": 0.04446478781141699,
      "grad_norm": 1.5,
      "learning_rate": 0.00068,
      "loss": 7.6687,
      "step": 340
    },
    {
      "epoch": 0.04511868174982018,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00069,
      "loss": 7.6195,
      "step": 345
    },
    {
      "epoch": 0.04577257568822337,
      "grad_norm": 1.5390625,
      "learning_rate": 0.0007,
      "loss": 7.5768,
      "step": 350
    },
    {
      "epoch": 0.04642646962662656,
      "grad_norm": 1.9609375,
      "learning_rate": 0.00071,
      "loss": 7.6513,
      "step": 355
    },
    {
      "epoch": 0.04708036356502975,
      "grad_norm": 1.6953125,
      "learning_rate": 0.0007199999999999999,
      "loss": 7.587,
      "step": 360
    },
    {
      "epoch": 0.04773425750343294,
      "grad_norm": 1.9765625,
      "learning_rate": 0.00073,
      "loss": 7.5975,
      "step": 365
    },
    {
      "epoch": 0.048388151441836134,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00074,
      "loss": 7.565,
      "step": 370
    },
    {
      "epoch": 0.049042045380239326,
      "grad_norm": 1.515625,
      "learning_rate": 0.00075,
      "loss": 7.5604,
      "step": 375
    },
    {
      "epoch": 0.04969593931864252,
      "grad_norm": 1.515625,
      "learning_rate": 0.00076,
      "loss": 7.5916,
      "step": 380
    },
    {
      "epoch": 0.05034983325704571,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0007700000000000001,
      "loss": 7.5601,
      "step": 385
    },
    {
      "epoch": 0.0510037271954489,
      "grad_norm": 1.5546875,
      "learning_rate": 0.0007800000000000001,
      "loss": 7.5528,
      "step": 390
    },
    {
      "epoch": 0.05165762113385209,
      "grad_norm": 1.7109375,
      "learning_rate": 0.00079,
      "loss": 7.5534,
      "step": 395
    },
    {
      "epoch": 0.05231151507225528,
      "grad_norm": 1.4765625,
      "learning_rate": 0.0008,
      "loss": 7.5243,
      "step": 400
    },
    {
      "epoch": 0.05296540901065847,
      "grad_norm": 1.5703125,
      "learning_rate": 0.0008100000000000001,
      "loss": 7.5231,
      "step": 405
    },
    {
      "epoch": 0.05361930294906166,
      "grad_norm": 1.46875,
      "learning_rate": 0.00082,
      "loss": 7.5174,
      "step": 410
    },
    {
      "epoch": 0.054273196887464854,
      "grad_norm": 1.46875,
      "learning_rate": 0.00083,
      "loss": 7.4922,
      "step": 415
    },
    {
      "epoch": 0.054927090825868045,
      "grad_norm": 1.6484375,
      "learning_rate": 0.00084,
      "loss": 7.3765,
      "step": 420
    },
    {
      "epoch": 0.055580984764271237,
      "grad_norm": 1.609375,
      "learning_rate": 0.00085,
      "loss": 7.4035,
      "step": 425
    },
    {
      "epoch": 0.05623487870267443,
      "grad_norm": 1.53125,
      "learning_rate": 0.00086,
      "loss": 7.4614,
      "step": 430
    },
    {
      "epoch": 0.05688877264107762,
      "grad_norm": 1.53125,
      "learning_rate": 0.00087,
      "loss": 7.4449,
      "step": 435
    },
    {
      "epoch": 0.05754266657948081,
      "grad_norm": 1.5859375,
      "learning_rate": 0.00088,
      "loss": 7.5239,
      "step": 440
    },
    {
      "epoch": 0.058196560517884,
      "grad_norm": 1.5,
      "learning_rate": 0.0008900000000000001,
      "loss": 7.3661,
      "step": 445
    },
    {
      "epoch": 0.05885045445628719,
      "grad_norm": 1.53125,
      "learning_rate": 0.0009000000000000001,
      "loss": 7.3652,
      "step": 450
    },
    {
      "epoch": 0.05950434839469038,
      "grad_norm": 1.296875,
      "learning_rate": 0.00091,
      "loss": 7.4256,
      "step": 455
    },
    {
      "epoch": 0.060158242333093574,
      "grad_norm": 1.5546875,
      "learning_rate": 0.00092,
      "loss": 7.4048,
      "step": 460
    },
    {
      "epoch": 0.060812136271496765,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00093,
      "loss": 7.4004,
      "step": 465
    },
    {
      "epoch": 0.061466030209899956,
      "grad_norm": 1.390625,
      "learning_rate": 0.00094,
      "loss": 7.3547,
      "step": 470
    },
    {
      "epoch": 0.06211992414830315,
      "grad_norm": 1.5234375,
      "learning_rate": 0.00095,
      "loss": 7.4078,
      "step": 475
    },
    {
      "epoch": 0.06277381808670633,
      "grad_norm": 1.46875,
      "learning_rate": 0.00096,
      "loss": 7.3878,
      "step": 480
    },
    {
      "epoch": 0.06342771202510952,
      "grad_norm": 1.453125,
      "learning_rate": 0.0009699999999999999,
      "loss": 7.3434,
      "step": 485
    },
    {
      "epoch": 0.06408160596351271,
      "grad_norm": 1.625,
      "learning_rate": 0.00098,
      "loss": 7.3696,
      "step": 490
    },
    {
      "epoch": 0.0647354999019159,
      "grad_norm": 1.4453125,
      "learning_rate": 0.00099,
      "loss": 7.3436,
      "step": 495
    },
    {
      "epoch": 0.0653893938403191,
      "grad_norm": 1.4921875,
      "learning_rate": 0.001,
      "loss": 7.2601,
      "step": 500
    }
  ],
  "logging_steps": 5,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 670418530467840.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}