{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.24037800687285224,
  "eval_steps": 500,
  "global_step": 2798,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000859106529209622,
      "grad_norm": 10.069700241088867,
      "learning_rate": 1.1061797752808989e-06,
      "loss": 2.3607,
      "step": 10
    },
    {
      "epoch": 0.001718213058419244,
      "grad_norm": 2.7327144145965576,
      "learning_rate": 2.2241573033707866e-06,
      "loss": 2.1048,
      "step": 20
    },
    {
      "epoch": 0.002577319587628866,
      "grad_norm": 3.3271842002868652,
      "learning_rate": 3.342134831460675e-06,
      "loss": 1.7854,
      "step": 30
    },
    {
      "epoch": 0.003436426116838488,
      "grad_norm": 1.4632568359375,
      "learning_rate": 4.4601123595505624e-06,
      "loss": 1.4144,
      "step": 40
    },
    {
      "epoch": 0.00429553264604811,
      "grad_norm": 0.96810382604599,
      "learning_rate": 5.5780898876404495e-06,
      "loss": 1.2037,
      "step": 50
    },
    {
      "epoch": 0.005154639175257732,
      "grad_norm": 0.7168840169906616,
      "learning_rate": 6.6960674157303374e-06,
      "loss": 1.0357,
      "step": 60
    },
    {
      "epoch": 0.006013745704467354,
      "grad_norm": 0.6445292830467224,
      "learning_rate": 7.814044943820226e-06,
      "loss": 0.9969,
      "step": 70
    },
    {
      "epoch": 0.006872852233676976,
      "grad_norm": 0.6907113194465637,
      "learning_rate": 8.932022471910112e-06,
      "loss": 1.0041,
      "step": 80
    },
    {
      "epoch": 0.007731958762886598,
      "grad_norm": 0.6093459725379944,
      "learning_rate": 1.005e-05,
      "loss": 0.9553,
      "step": 90
    },
    {
      "epoch": 0.00859106529209622,
      "grad_norm": 0.6630317568778992,
      "learning_rate": 1.1167977528089888e-05,
      "loss": 0.9573,
      "step": 100
    },
    {
      "epoch": 0.009450171821305841,
      "grad_norm": 0.6552422642707825,
      "learning_rate": 1.2285955056179776e-05,
      "loss": 0.9811,
      "step": 110
    },
    {
      "epoch": 0.010309278350515464,
      "grad_norm": 0.673576831817627,
      "learning_rate": 1.3403932584269664e-05,
      "loss": 0.9248,
      "step": 120
    },
    {
      "epoch": 0.011168384879725086,
      "grad_norm": 0.6397550106048584,
      "learning_rate": 1.4521910112359552e-05,
      "loss": 0.9155,
      "step": 130
    },
    {
      "epoch": 0.012027491408934709,
      "grad_norm": 0.6486415863037109,
      "learning_rate": 1.563988764044944e-05,
      "loss": 0.9121,
      "step": 140
    },
    {
      "epoch": 0.01288659793814433,
      "grad_norm": 0.5658463835716248,
      "learning_rate": 1.6757865168539328e-05,
      "loss": 0.9371,
      "step": 150
    },
    {
      "epoch": 0.013745704467353952,
      "grad_norm": 0.5926650762557983,
      "learning_rate": 1.7875842696629214e-05,
      "loss": 0.8875,
      "step": 160
    },
    {
      "epoch": 0.014604810996563574,
      "grad_norm": 0.576126217842102,
      "learning_rate": 1.89938202247191e-05,
      "loss": 0.9006,
      "step": 170
    },
    {
      "epoch": 0.015463917525773196,
      "grad_norm": 0.5573123097419739,
      "learning_rate": 2e-05,
      "loss": 0.9152,
      "step": 180
    },
    {
      "epoch": 0.01632302405498282,
      "grad_norm": 0.5773940086364746,
      "learning_rate": 2e-05,
      "loss": 0.8955,
      "step": 190
    },
    {
      "epoch": 0.01718213058419244,
      "grad_norm": 0.5635377764701843,
      "learning_rate": 2e-05,
      "loss": 0.8897,
      "step": 200
    },
    {
      "epoch": 0.01804123711340206,
      "grad_norm": 0.5612330436706543,
      "learning_rate": 2e-05,
      "loss": 0.8959,
      "step": 210
    },
    {
      "epoch": 0.018900343642611683,
      "grad_norm": 0.6228774785995483,
      "learning_rate": 2e-05,
      "loss": 0.8906,
      "step": 220
    },
    {
      "epoch": 0.019759450171821305,
      "grad_norm": 0.5534242391586304,
      "learning_rate": 2e-05,
      "loss": 0.8666,
      "step": 230
    },
    {
      "epoch": 0.020618556701030927,
      "grad_norm": 0.5617905855178833,
      "learning_rate": 2e-05,
      "loss": 0.8639,
      "step": 240
    },
    {
      "epoch": 0.02147766323024055,
      "grad_norm": 0.5597807765007019,
      "learning_rate": 2e-05,
      "loss": 0.8846,
      "step": 250
    },
    {
      "epoch": 0.022336769759450172,
      "grad_norm": 0.5115612149238586,
      "learning_rate": 2e-05,
      "loss": 0.8671,
      "step": 260
    },
    {
      "epoch": 0.023195876288659795,
      "grad_norm": 0.5317944288253784,
      "learning_rate": 2e-05,
      "loss": 0.8915,
      "step": 270
    },
    {
      "epoch": 0.024054982817869417,
      "grad_norm": 0.5044589638710022,
      "learning_rate": 2e-05,
      "loss": 0.8656,
      "step": 280
    },
    {
      "epoch": 0.02491408934707904,
      "grad_norm": 0.5581314563751221,
      "learning_rate": 2e-05,
      "loss": 0.8764,
      "step": 290
    },
    {
      "epoch": 0.02577319587628866,
      "grad_norm": 0.5628443956375122,
      "learning_rate": 2e-05,
      "loss": 0.8941,
      "step": 300
    },
    {
      "epoch": 0.02663230240549828,
      "grad_norm": 0.560197114944458,
      "learning_rate": 2e-05,
      "loss": 0.8491,
      "step": 310
    },
    {
      "epoch": 0.027491408934707903,
      "grad_norm": 0.524337649345398,
      "learning_rate": 2e-05,
      "loss": 0.8857,
      "step": 320
    },
    {
      "epoch": 0.028350515463917526,
      "grad_norm": 0.683029055595398,
      "learning_rate": 2e-05,
      "loss": 0.8597,
      "step": 330
    },
    {
      "epoch": 0.029209621993127148,
      "grad_norm": 0.5435221195220947,
      "learning_rate": 2e-05,
      "loss": 0.8483,
      "step": 340
    },
    {
      "epoch": 0.03006872852233677,
      "grad_norm": 0.5640478134155273,
      "learning_rate": 2e-05,
      "loss": 0.8865,
      "step": 350
    },
    {
      "epoch": 0.030927835051546393,
      "grad_norm": 0.4870714545249939,
      "learning_rate": 2e-05,
      "loss": 0.8616,
      "step": 360
    },
    {
      "epoch": 0.03178694158075601,
      "grad_norm": 0.4941020607948303,
      "learning_rate": 2e-05,
      "loss": 0.8745,
      "step": 370
    },
    {
      "epoch": 0.03264604810996564,
      "grad_norm": 0.4704708755016327,
      "learning_rate": 2e-05,
      "loss": 0.8337,
      "step": 380
    },
    {
      "epoch": 0.03350515463917526,
      "grad_norm": 0.5146850347518921,
      "learning_rate": 2e-05,
      "loss": 0.8392,
      "step": 390
    },
    {
      "epoch": 0.03436426116838488,
      "grad_norm": 0.5625430345535278,
      "learning_rate": 2e-05,
      "loss": 0.8679,
      "step": 400
    },
    {
      "epoch": 0.0352233676975945,
      "grad_norm": 0.5005638003349304,
      "learning_rate": 2e-05,
      "loss": 0.8686,
      "step": 410
    },
    {
      "epoch": 0.03608247422680412,
      "grad_norm": 0.5048443078994751,
      "learning_rate": 2e-05,
      "loss": 0.8587,
      "step": 420
    },
    {
      "epoch": 0.036941580756013746,
      "grad_norm": 0.5067149996757507,
      "learning_rate": 2e-05,
      "loss": 0.8821,
      "step": 430
    },
    {
      "epoch": 0.037800687285223365,
      "grad_norm": 0.5074286460876465,
      "learning_rate": 2e-05,
      "loss": 0.8589,
      "step": 440
    },
    {
      "epoch": 0.03865979381443299,
      "grad_norm": 0.4815230965614319,
      "learning_rate": 2e-05,
      "loss": 0.8735,
      "step": 450
    },
    {
      "epoch": 0.03951890034364261,
      "grad_norm": 0.4682285785675049,
      "learning_rate": 2e-05,
      "loss": 0.8988,
      "step": 460
    },
    {
      "epoch": 0.040378006872852236,
      "grad_norm": 0.4762243628501892,
      "learning_rate": 2e-05,
      "loss": 0.8572,
      "step": 470
    },
    {
      "epoch": 0.041237113402061855,
      "grad_norm": 0.48740312457084656,
      "learning_rate": 2e-05,
      "loss": 0.819,
      "step": 480
    },
    {
      "epoch": 0.04209621993127148,
      "grad_norm": 0.4676920473575592,
      "learning_rate": 2e-05,
      "loss": 0.8169,
      "step": 490
    },
    {
      "epoch": 0.0429553264604811,
      "grad_norm": 0.4818402826786041,
      "learning_rate": 2e-05,
      "loss": 0.8188,
      "step": 500
    },
    {
      "epoch": 0.04381443298969072,
      "grad_norm": 0.536251425743103,
      "learning_rate": 2e-05,
      "loss": 0.8857,
      "step": 510
    },
    {
      "epoch": 0.044673539518900345,
      "grad_norm": 0.46843159198760986,
      "learning_rate": 2e-05,
      "loss": 0.8162,
      "step": 520
    },
    {
      "epoch": 0.04553264604810996,
      "grad_norm": 0.47590792179107666,
      "learning_rate": 2e-05,
      "loss": 0.8749,
      "step": 530
    },
    {
      "epoch": 0.04639175257731959,
      "grad_norm": 0.48866006731987,
      "learning_rate": 2e-05,
      "loss": 0.8761,
      "step": 540
    },
    {
      "epoch": 0.04725085910652921,
      "grad_norm": 0.529727041721344,
      "learning_rate": 2e-05,
      "loss": 0.8591,
      "step": 550
    },
    {
      "epoch": 0.048109965635738834,
      "grad_norm": 0.46046891808509827,
      "learning_rate": 2e-05,
      "loss": 0.84,
      "step": 560
    },
    {
      "epoch": 0.04896907216494845,
      "grad_norm": 0.503052830696106,
      "learning_rate": 2e-05,
      "loss": 0.841,
      "step": 570
    },
    {
      "epoch": 0.04982817869415808,
      "grad_norm": 0.47345227003097534,
      "learning_rate": 2e-05,
      "loss": 0.8206,
      "step": 580
    },
    {
      "epoch": 0.0506872852233677,
      "grad_norm": 0.4749337136745453,
      "learning_rate": 2e-05,
      "loss": 0.8191,
      "step": 590
    },
    {
      "epoch": 0.05154639175257732,
      "grad_norm": 0.45893123745918274,
      "learning_rate": 2e-05,
      "loss": 0.8512,
      "step": 600
    },
    {
      "epoch": 0.05240549828178694,
      "grad_norm": 0.4918938875198364,
      "learning_rate": 2e-05,
      "loss": 0.8324,
      "step": 610
    },
    {
      "epoch": 0.05326460481099656,
      "grad_norm": 0.5130265951156616,
      "learning_rate": 2e-05,
      "loss": 0.8261,
      "step": 620
    },
    {
      "epoch": 0.05412371134020619,
      "grad_norm": 0.48524969816207886,
      "learning_rate": 2e-05,
      "loss": 0.8402,
      "step": 630
    },
    {
      "epoch": 0.054982817869415807,
      "grad_norm": 0.4443276822566986,
      "learning_rate": 2e-05,
      "loss": 0.778,
      "step": 640
    },
    {
      "epoch": 0.05584192439862543,
      "grad_norm": 0.48050761222839355,
      "learning_rate": 2e-05,
      "loss": 0.8328,
      "step": 650
    },
    {
      "epoch": 0.05670103092783505,
      "grad_norm": 0.468749463558197,
      "learning_rate": 2e-05,
      "loss": 0.8126,
      "step": 660
    },
    {
      "epoch": 0.05756013745704467,
      "grad_norm": 0.47499385476112366,
      "learning_rate": 2e-05,
      "loss": 0.8567,
      "step": 670
    },
    {
      "epoch": 0.058419243986254296,
      "grad_norm": 0.47868019342422485,
      "learning_rate": 2e-05,
      "loss": 0.8247,
      "step": 680
    },
    {
      "epoch": 0.059278350515463915,
      "grad_norm": 0.4504624009132385,
      "learning_rate": 2e-05,
      "loss": 0.8265,
      "step": 690
    },
    {
      "epoch": 0.06013745704467354,
      "grad_norm": 0.481806218624115,
      "learning_rate": 2e-05,
      "loss": 0.8208,
      "step": 700
    },
    {
      "epoch": 0.06099656357388316,
      "grad_norm": 2.282531261444092,
      "learning_rate": 2e-05,
      "loss": 0.8281,
      "step": 710
    },
    {
      "epoch": 0.061855670103092786,
      "grad_norm": 0.48688116669654846,
      "learning_rate": 2e-05,
      "loss": 0.8329,
      "step": 720
    },
    {
      "epoch": 0.0627147766323024,
      "grad_norm": 0.5048409104347229,
      "learning_rate": 2e-05,
      "loss": 0.8492,
      "step": 730
    },
    {
      "epoch": 0.06357388316151202,
      "grad_norm": 0.493664413690567,
      "learning_rate": 2e-05,
      "loss": 0.8449,
      "step": 740
    },
    {
      "epoch": 0.06443298969072164,
      "grad_norm": 0.4665951728820801,
      "learning_rate": 2e-05,
      "loss": 0.8156,
      "step": 750
    },
    {
      "epoch": 0.06529209621993128,
      "grad_norm": 0.4632743000984192,
      "learning_rate": 2e-05,
      "loss": 0.8592,
      "step": 760
    },
    {
      "epoch": 0.0661512027491409,
      "grad_norm": 0.5417582392692566,
      "learning_rate": 2e-05,
      "loss": 0.8185,
      "step": 770
    },
    {
      "epoch": 0.06701030927835051,
      "grad_norm": 0.5666975378990173,
      "learning_rate": 2e-05,
      "loss": 0.8282,
      "step": 780
    },
    {
      "epoch": 0.06786941580756013,
      "grad_norm": 0.4715534746646881,
      "learning_rate": 2e-05,
      "loss": 0.8251,
      "step": 790
    },
    {
      "epoch": 0.06872852233676977,
      "grad_norm": 0.4496767818927765,
      "learning_rate": 2e-05,
      "loss": 0.8049,
      "step": 800
    },
    {
      "epoch": 0.06958762886597938,
      "grad_norm": 0.47709542512893677,
      "learning_rate": 2e-05,
      "loss": 0.84,
      "step": 810
    },
    {
      "epoch": 0.070446735395189,
      "grad_norm": 0.49228349328041077,
      "learning_rate": 2e-05,
      "loss": 0.8107,
      "step": 820
    },
    {
      "epoch": 0.07130584192439862,
      "grad_norm": 0.4816240072250366,
      "learning_rate": 2e-05,
      "loss": 0.8094,
      "step": 830
    },
    {
      "epoch": 0.07216494845360824,
      "grad_norm": 1.0014556646347046,
      "learning_rate": 2e-05,
      "loss": 0.8432,
      "step": 840
    },
    {
      "epoch": 0.07302405498281787,
      "grad_norm": 0.4686058461666107,
      "learning_rate": 2e-05,
      "loss": 0.8189,
      "step": 850
    },
    {
      "epoch": 0.07388316151202749,
      "grad_norm": 0.4596993923187256,
      "learning_rate": 2e-05,
      "loss": 0.8065,
      "step": 860
    },
    {
      "epoch": 0.07474226804123711,
      "grad_norm": 0.48179084062576294,
      "learning_rate": 2e-05,
      "loss": 0.829,
      "step": 870
    },
    {
      "epoch": 0.07560137457044673,
      "grad_norm": 0.5536651611328125,
      "learning_rate": 2e-05,
      "loss": 0.8229,
      "step": 880
    },
    {
      "epoch": 0.07646048109965636,
      "grad_norm": 0.49012085795402527,
      "learning_rate": 2e-05,
      "loss": 0.8365,
      "step": 890
    },
    {
      "epoch": 0.07731958762886598,
      "grad_norm": 0.46614527702331543,
      "learning_rate": 2e-05,
      "loss": 0.8059,
      "step": 900
    },
    {
      "epoch": 0.0781786941580756,
      "grad_norm": 0.49526447057724,
      "learning_rate": 2e-05,
      "loss": 0.823,
      "step": 910
    },
    {
      "epoch": 0.07903780068728522,
      "grad_norm": 0.4854036271572113,
      "learning_rate": 2e-05,
      "loss": 0.831,
      "step": 920
    },
    {
      "epoch": 0.07989690721649484,
      "grad_norm": 0.46326735615730286,
      "learning_rate": 2e-05,
      "loss": 0.8298,
      "step": 930
    },
    {
      "epoch": 0.08075601374570447,
      "grad_norm": 0.48059317469596863,
      "learning_rate": 2e-05,
      "loss": 0.8074,
      "step": 940
    },
    {
      "epoch": 0.08161512027491409,
      "grad_norm": 0.4574795365333557,
      "learning_rate": 2e-05,
      "loss": 0.8097,
      "step": 950
    },
    {
      "epoch": 0.08247422680412371,
      "grad_norm": 0.44573479890823364,
      "learning_rate": 2e-05,
      "loss": 0.8077,
      "step": 960
    },
    {
      "epoch": 0.08333333333333333,
      "grad_norm": 0.4629650115966797,
      "learning_rate": 2e-05,
      "loss": 0.798,
      "step": 970
    },
    {
      "epoch": 0.08419243986254296,
      "grad_norm": 0.47595855593681335,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 980
    },
    {
      "epoch": 0.08505154639175258,
      "grad_norm": 0.4622196555137634,
      "learning_rate": 2e-05,
      "loss": 0.8058,
      "step": 990
    },
    {
      "epoch": 0.0859106529209622,
      "grad_norm": 0.4406432807445526,
      "learning_rate": 2e-05,
      "loss": 0.849,
      "step": 1000
    },
    {
      "epoch": 0.08676975945017182,
      "grad_norm": 0.47430476546287537,
      "learning_rate": 2e-05,
      "loss": 0.8334,
      "step": 1010
    },
    {
      "epoch": 0.08762886597938144,
      "grad_norm": 0.4646911323070526,
      "learning_rate": 2e-05,
      "loss": 0.8302,
      "step": 1020
    },
    {
      "epoch": 0.08848797250859107,
      "grad_norm": 0.503621518611908,
      "learning_rate": 2e-05,
      "loss": 0.8303,
      "step": 1030
    },
    {
      "epoch": 0.08934707903780069,
      "grad_norm": 0.42737218737602234,
      "learning_rate": 2e-05,
      "loss": 0.7868,
      "step": 1040
    },
    {
      "epoch": 0.09020618556701031,
      "grad_norm": 0.4449130892753601,
      "learning_rate": 2e-05,
      "loss": 0.8059,
      "step": 1050
    },
    {
      "epoch": 0.09106529209621993,
      "grad_norm": 0.4552324414253235,
      "learning_rate": 2e-05,
      "loss": 0.8151,
      "step": 1060
    },
    {
      "epoch": 0.09192439862542956,
      "grad_norm": 0.4285755455493927,
      "learning_rate": 2e-05,
      "loss": 0.7987,
      "step": 1070
    },
    {
      "epoch": 0.09278350515463918,
      "grad_norm": 0.44612982869148254,
      "learning_rate": 2e-05,
      "loss": 0.8091,
      "step": 1080
    },
    {
      "epoch": 0.0936426116838488,
      "grad_norm": 0.41484394669532776,
      "learning_rate": 2e-05,
      "loss": 0.802,
      "step": 1090
    },
    {
      "epoch": 0.09450171821305842,
      "grad_norm": 0.43857651948928833,
      "learning_rate": 2e-05,
      "loss": 0.8051,
      "step": 1100
    },
    {
      "epoch": 0.09536082474226804,
      "grad_norm": 0.4621300995349884,
      "learning_rate": 2e-05,
      "loss": 0.8114,
      "step": 1110
    },
    {
      "epoch": 0.09621993127147767,
      "grad_norm": 0.46743395924568176,
      "learning_rate": 2e-05,
      "loss": 0.791,
      "step": 1120
    },
    {
      "epoch": 0.09707903780068729,
      "grad_norm": 0.4864065945148468,
      "learning_rate": 2e-05,
      "loss": 0.8253,
      "step": 1130
    },
    {
      "epoch": 0.0979381443298969,
      "grad_norm": 0.4746995270252228,
      "learning_rate": 2e-05,
      "loss": 0.8027,
      "step": 1140
    },
    {
      "epoch": 0.09879725085910653,
      "grad_norm": 0.43570324778556824,
      "learning_rate": 2e-05,
      "loss": 0.7926,
      "step": 1150
    },
    {
      "epoch": 0.09965635738831616,
      "grad_norm": 0.6272392868995667,
      "learning_rate": 2e-05,
      "loss": 0.7873,
      "step": 1160
    },
    {
      "epoch": 0.10051546391752578,
      "grad_norm": 0.4445926547050476,
      "learning_rate": 2e-05,
      "loss": 0.801,
      "step": 1170
    },
    {
      "epoch": 0.1013745704467354,
      "grad_norm": 0.44602736830711365,
      "learning_rate": 2e-05,
      "loss": 0.8186,
      "step": 1180
    },
    {
      "epoch": 0.10223367697594501,
      "grad_norm": 0.49426504969596863,
      "learning_rate": 2e-05,
      "loss": 0.8112,
      "step": 1190
    },
    {
      "epoch": 0.10309278350515463,
      "grad_norm": 0.4448431730270386,
      "learning_rate": 2e-05,
      "loss": 0.8012,
      "step": 1200
    },
    {
      "epoch": 0.10395189003436427,
      "grad_norm": 0.49004390835762024,
      "learning_rate": 2e-05,
      "loss": 0.8141,
      "step": 1210
    },
    {
      "epoch": 0.10481099656357389,
      "grad_norm": 0.48352155089378357,
      "learning_rate": 2e-05,
      "loss": 0.8125,
      "step": 1220
    },
    {
      "epoch": 0.1056701030927835,
      "grad_norm": 0.43718385696411133,
      "learning_rate": 2e-05,
      "loss": 0.808,
      "step": 1230
    },
    {
      "epoch": 0.10652920962199312,
      "grad_norm": 0.46456244587898254,
      "learning_rate": 2e-05,
      "loss": 0.8023,
      "step": 1240
    },
    {
      "epoch": 0.10738831615120274,
      "grad_norm": 0.4470098316669464,
      "learning_rate": 2e-05,
      "loss": 0.7836,
      "step": 1250
    },
    {
      "epoch": 0.10824742268041238,
      "grad_norm": 0.44037750363349915,
      "learning_rate": 2e-05,
      "loss": 0.8215,
      "step": 1260
    },
    {
      "epoch": 0.109106529209622,
      "grad_norm": 0.4431336224079132,
      "learning_rate": 2e-05,
      "loss": 0.8164,
      "step": 1270
    },
    {
      "epoch": 0.10996563573883161,
      "grad_norm": 0.4316923916339874,
      "learning_rate": 2e-05,
      "loss": 0.824,
      "step": 1280
    },
    {
      "epoch": 0.11082474226804123,
      "grad_norm": 0.4511774778366089,
      "learning_rate": 2e-05,
      "loss": 0.8211,
      "step": 1290
    },
    {
      "epoch": 0.11168384879725086,
      "grad_norm": 0.41615837812423706,
      "learning_rate": 2e-05,
      "loss": 0.7879,
      "step": 1300
    },
    {
      "epoch": 0.11254295532646048,
      "grad_norm": 0.42174649238586426,
      "learning_rate": 2e-05,
      "loss": 0.7917,
      "step": 1310
    },
    {
      "epoch": 0.1134020618556701,
      "grad_norm": 0.5034571886062622,
      "learning_rate": 2e-05,
      "loss": 0.8056,
      "step": 1320
    },
    {
      "epoch": 0.11426116838487972,
      "grad_norm": 0.4601093530654907,
      "learning_rate": 2e-05,
      "loss": 0.819,
      "step": 1330
    },
    {
      "epoch": 0.11512027491408934,
      "grad_norm": 0.4226849377155304,
      "learning_rate": 2e-05,
      "loss": 0.7694,
      "step": 1340
    },
    {
      "epoch": 0.11597938144329897,
      "grad_norm": 0.4490329921245575,
      "learning_rate": 2e-05,
      "loss": 0.8005,
      "step": 1350
    },
    {
      "epoch": 0.11683848797250859,
      "grad_norm": 0.43054598569869995,
      "learning_rate": 2e-05,
      "loss": 0.7899,
      "step": 1360
    },
    {
      "epoch": 0.11769759450171821,
      "grad_norm": 0.4534497559070587,
      "learning_rate": 2e-05,
      "loss": 0.7901,
      "step": 1370
    },
    {
      "epoch": 0.11855670103092783,
      "grad_norm": 0.4433537423610687,
      "learning_rate": 2e-05,
      "loss": 0.8133,
      "step": 1380
    },
    {
      "epoch": 0.11941580756013746,
      "grad_norm": 0.4343333840370178,
      "learning_rate": 2e-05,
      "loss": 0.7982,
      "step": 1390
    },
    {
      "epoch": 0.12027491408934708,
      "grad_norm": 0.42904624342918396,
      "learning_rate": 2e-05,
      "loss": 0.799,
      "step": 1400
    },
    {
      "epoch": 0.1211340206185567,
      "grad_norm": 0.4655359983444214,
      "learning_rate": 2e-05,
      "loss": 0.8211,
      "step": 1410
    },
    {
      "epoch": 0.12199312714776632,
      "grad_norm": 0.4095928966999054,
      "learning_rate": 2e-05,
      "loss": 0.812,
      "step": 1420
    },
    {
      "epoch": 0.12285223367697594,
      "grad_norm": 0.41238921880722046,
      "learning_rate": 2e-05,
      "loss": 0.7756,
      "step": 1430
    },
    {
      "epoch": 0.12371134020618557,
      "grad_norm": 0.4852188229560852,
      "learning_rate": 2e-05,
      "loss": 0.8303,
      "step": 1440
    },
    {
      "epoch": 0.12457044673539519,
      "grad_norm": 0.44924116134643555,
      "learning_rate": 2e-05,
      "loss": 0.8325,
      "step": 1450
    },
    {
      "epoch": 0.1254295532646048,
      "grad_norm": 0.4346265494823456,
      "learning_rate": 2e-05,
      "loss": 0.7992,
      "step": 1460
    },
    {
      "epoch": 0.12628865979381443,
      "grad_norm": 0.4454062581062317,
      "learning_rate": 2e-05,
      "loss": 0.797,
      "step": 1470
    },
    {
      "epoch": 0.12714776632302405,
      "grad_norm": 0.4472755193710327,
      "learning_rate": 2e-05,
      "loss": 0.8058,
      "step": 1480
    },
    {
      "epoch": 0.12800687285223367,
      "grad_norm": 0.43495413661003113,
      "learning_rate": 2e-05,
      "loss": 0.799,
      "step": 1490
    },
    {
      "epoch": 0.12886597938144329,
      "grad_norm": 0.42517977952957153,
      "learning_rate": 2e-05,
      "loss": 0.8023,
      "step": 1500
    },
    {
      "epoch": 0.12972508591065293,
      "grad_norm": 0.5048529505729675,
      "learning_rate": 2e-05,
      "loss": 0.7935,
      "step": 1510
    },
    {
      "epoch": 0.13058419243986255,
      "grad_norm": 0.41410166025161743,
      "learning_rate": 2e-05,
      "loss": 0.7798,
      "step": 1520
    },
    {
      "epoch": 0.13144329896907217,
      "grad_norm": 0.4294983744621277,
      "learning_rate": 2e-05,
      "loss": 0.7878,
      "step": 1530
    },
    {
      "epoch": 0.1323024054982818,
      "grad_norm": 0.42941445112228394,
      "learning_rate": 2e-05,
      "loss": 0.7884,
      "step": 1540
    },
    {
      "epoch": 0.1331615120274914,
      "grad_norm": 0.4035552740097046,
      "learning_rate": 2e-05,
      "loss": 0.792,
      "step": 1550
    },
    {
      "epoch": 0.13402061855670103,
      "grad_norm": 0.4652338922023773,
      "learning_rate": 2e-05,
      "loss": 0.777,
      "step": 1560
    },
    {
      "epoch": 0.13487972508591065,
      "grad_norm": 0.4364311993122101,
      "learning_rate": 2e-05,
      "loss": 0.7723,
      "step": 1570
    },
    {
      "epoch": 0.13573883161512026,
      "grad_norm": 0.4207146465778351,
      "learning_rate": 2e-05,
      "loss": 0.7612,
      "step": 1580
    },
    {
      "epoch": 0.13659793814432988,
      "grad_norm": 0.4272591769695282,
      "learning_rate": 2e-05,
      "loss": 0.8061,
      "step": 1590
    },
    {
      "epoch": 0.13745704467353953,
      "grad_norm": 0.4509749710559845,
      "learning_rate": 2e-05,
      "loss": 0.7926,
      "step": 1600
    },
    {
      "epoch": 0.13831615120274915,
      "grad_norm": 0.4478810429573059,
      "learning_rate": 2e-05,
      "loss": 0.7896,
      "step": 1610
    },
    {
      "epoch": 0.13917525773195877,
      "grad_norm": 0.4207334518432617,
      "learning_rate": 2e-05,
      "loss": 0.7678,
      "step": 1620
    },
    {
      "epoch": 0.1400343642611684,
      "grad_norm": 0.4360485374927521,
      "learning_rate": 2e-05,
      "loss": 0.7909,
      "step": 1630
    },
    {
      "epoch": 0.140893470790378,
      "grad_norm": 0.4345305562019348,
      "learning_rate": 2e-05,
      "loss": 0.8139,
      "step": 1640
    },
    {
      "epoch": 0.14175257731958762,
      "grad_norm": 0.43382421135902405,
      "learning_rate": 2e-05,
      "loss": 0.797,
      "step": 1650
    },
    {
      "epoch": 0.14261168384879724,
      "grad_norm": 0.42108669877052307,
      "learning_rate": 2e-05,
      "loss": 0.804,
      "step": 1660
    },
    {
      "epoch": 0.14347079037800686,
      "grad_norm": 0.45418545603752136,
      "learning_rate": 2e-05,
      "loss": 0.7852,
      "step": 1670
    },
    {
      "epoch": 0.14432989690721648,
      "grad_norm": 0.4910484552383423,
      "learning_rate": 2e-05,
      "loss": 0.7669,
      "step": 1680
    },
    {
      "epoch": 0.14518900343642613,
      "grad_norm": 0.4287989139556885,
      "learning_rate": 2e-05,
      "loss": 0.8165,
      "step": 1690
    },
    {
      "epoch": 0.14604810996563575,
      "grad_norm": 0.5834421515464783,
      "learning_rate": 2e-05,
      "loss": 0.7962,
      "step": 1700
    },
    {
      "epoch": 0.14690721649484537,
      "grad_norm": 0.5063323378562927,
      "learning_rate": 2e-05,
      "loss": 0.7734,
      "step": 1710
    },
    {
      "epoch": 0.14776632302405499,
      "grad_norm": 0.4238131046295166,
      "learning_rate": 2e-05,
      "loss": 0.8028,
      "step": 1720
    },
    {
      "epoch": 0.1486254295532646,
      "grad_norm": 0.38663214445114136,
      "learning_rate": 2e-05,
      "loss": 0.7988,
      "step": 1730
    },
    {
      "epoch": 0.14948453608247422,
      "grad_norm": 0.44796040654182434,
      "learning_rate": 2e-05,
      "loss": 0.7949,
      "step": 1740
    },
    {
      "epoch": 0.15034364261168384,
      "grad_norm": 0.41491448879241943,
      "learning_rate": 2e-05,
      "loss": 0.7628,
      "step": 1750
    },
    {
      "epoch": 0.15120274914089346,
      "grad_norm": 0.4768643379211426,
      "learning_rate": 2e-05,
      "loss": 0.7741,
      "step": 1760
    },
    {
      "epoch": 0.15206185567010308,
      "grad_norm": 0.42717429995536804,
      "learning_rate": 2e-05,
      "loss": 0.7955,
      "step": 1770
    },
    {
      "epoch": 0.15292096219931273,
      "grad_norm": 0.43356406688690186,
      "learning_rate": 2e-05,
      "loss": 0.7826,
      "step": 1780
    },
    {
      "epoch": 0.15378006872852235,
      "grad_norm": 0.45616310834884644,
      "learning_rate": 2e-05,
      "loss": 0.7821,
      "step": 1790
    },
    {
      "epoch": 0.15463917525773196,
      "grad_norm": 0.4642743468284607,
      "learning_rate": 2e-05,
      "loss": 0.7832,
      "step": 1800
    },
    {
      "epoch": 0.15549828178694158,
      "grad_norm": 0.42061248421669006,
      "learning_rate": 2e-05,
      "loss": 0.7829,
      "step": 1810
    },
    {
      "epoch": 0.1563573883161512,
      "grad_norm": 0.473254919052124,
      "learning_rate": 2e-05,
      "loss": 0.7968,
      "step": 1820
    },
    {
      "epoch": 0.15721649484536082,
      "grad_norm": 0.4449467957019806,
      "learning_rate": 2e-05,
      "loss": 0.7904,
      "step": 1830
    },
    {
      "epoch": 0.15807560137457044,
      "grad_norm": 0.4272187054157257,
      "learning_rate": 2e-05,
      "loss": 0.7939,
      "step": 1840
    },
    {
      "epoch": 0.15893470790378006,
      "grad_norm": 0.4838572144508362,
      "learning_rate": 2e-05,
      "loss": 0.808,
      "step": 1850
    },
    {
      "epoch": 0.15979381443298968,
      "grad_norm": 0.44314128160476685,
      "learning_rate": 2e-05,
      "loss": 0.7635,
      "step": 1860
    },
    {
      "epoch": 0.16065292096219932,
      "grad_norm": 0.44182509183883667,
      "learning_rate": 2e-05,
      "loss": 0.7908,
      "step": 1870
    },
    {
      "epoch": 0.16151202749140894,
      "grad_norm": 0.4147513508796692,
      "learning_rate": 2e-05,
      "loss": 0.7883,
      "step": 1880
    },
    {
      "epoch": 0.16237113402061856,
      "grad_norm": 0.44913968443870544,
      "learning_rate": 2e-05,
      "loss": 0.83,
      "step": 1890
    },
    {
      "epoch": 0.16323024054982818,
      "grad_norm": 0.43962720036506653,
      "learning_rate": 2e-05,
      "loss": 0.7889,
      "step": 1900
    },
    {
      "epoch": 0.1640893470790378,
      "grad_norm": 0.41255542635917664,
      "learning_rate": 2e-05,
      "loss": 0.7715,
      "step": 1910
    },
    {
      "epoch": 0.16494845360824742,
      "grad_norm": 0.4223017692565918,
      "learning_rate": 2e-05,
      "loss": 0.7746,
      "step": 1920
    },
    {
      "epoch": 0.16580756013745704,
      "grad_norm": 0.4158386290073395,
      "learning_rate": 2e-05,
      "loss": 0.7717,
      "step": 1930
    },
    {
      "epoch": 0.16666666666666666,
      "grad_norm": 0.42182308435440063,
      "learning_rate": 2e-05,
      "loss": 0.7707,
      "step": 1940
    },
    {
      "epoch": 0.16752577319587628,
      "grad_norm": 0.43559759855270386,
      "learning_rate": 2e-05,
      "loss": 0.7756,
      "step": 1950
    },
    {
      "epoch": 0.16838487972508592,
      "grad_norm": 0.4135313332080841,
      "learning_rate": 2e-05,
      "loss": 0.7793,
      "step": 1960
    },
    {
      "epoch": 0.16924398625429554,
      "grad_norm": 0.4393354058265686,
      "learning_rate": 2e-05,
      "loss": 0.7774,
      "step": 1970
    },
    {
      "epoch": 0.17010309278350516,
      "grad_norm": 0.40443214774131775,
      "learning_rate": 2e-05,
      "loss": 0.7891,
      "step": 1980
    },
    {
      "epoch": 0.17096219931271478,
      "grad_norm": 0.44918447732925415,
      "learning_rate": 2e-05,
      "loss": 0.7923,
      "step": 1990
    },
    {
      "epoch": 0.1718213058419244,
      "grad_norm": 0.4612440764904022,
      "learning_rate": 2e-05,
      "loss": 0.7896,
      "step": 2000
    },
    {
      "epoch": 0.17268041237113402,
      "grad_norm": 0.43252137303352356,
      "learning_rate": 2e-05,
      "loss": 0.7628,
      "step": 2010
    },
    {
      "epoch": 0.17353951890034364,
      "grad_norm": 0.4581339657306671,
      "learning_rate": 2e-05,
      "loss": 0.8109,
      "step": 2020
    },
    {
      "epoch": 0.17439862542955326,
      "grad_norm": 0.4455418884754181,
      "learning_rate": 2e-05,
      "loss": 0.7978,
      "step": 2030
    },
    {
      "epoch": 0.17525773195876287,
      "grad_norm": 0.4451400637626648,
      "learning_rate": 2e-05,
      "loss": 0.7832,
      "step": 2040
    },
    {
      "epoch": 0.17611683848797252,
      "grad_norm": 0.4293883144855499,
      "learning_rate": 2e-05,
      "loss": 0.8197,
      "step": 2050
    },
    {
      "epoch": 0.17697594501718214,
      "grad_norm": 0.41408681869506836,
      "learning_rate": 2e-05,
      "loss": 0.7809,
      "step": 2060
    },
    {
      "epoch": 0.17783505154639176,
      "grad_norm": 0.4040951132774353,
      "learning_rate": 2e-05,
      "loss": 0.794,
      "step": 2070
    },
    {
      "epoch": 0.17869415807560138,
      "grad_norm": 0.8779594898223877,
      "learning_rate": 2e-05,
      "loss": 0.7654,
      "step": 2080
    },
    {
      "epoch": 0.179553264604811,
      "grad_norm": 0.45652055740356445,
      "learning_rate": 2e-05,
      "loss": 0.7794,
      "step": 2090
    },
    {
      "epoch": 0.18041237113402062,
      "grad_norm": 0.42162561416625977,
      "learning_rate": 2e-05,
      "loss": 0.7856,
      "step": 2100
    },
    {
      "epoch": 0.18127147766323023,
      "grad_norm": 0.4086996614933014,
      "learning_rate": 2e-05,
      "loss": 0.7851,
      "step": 2110
    },
    {
      "epoch": 0.18213058419243985,
      "grad_norm": 0.4172867238521576,
      "learning_rate": 2e-05,
      "loss": 0.8041,
      "step": 2120
    },
    {
      "epoch": 0.18298969072164947,
      "grad_norm": 0.4956143796443939,
      "learning_rate": 2e-05,
      "loss": 0.7823,
      "step": 2130
    },
    {
      "epoch": 0.18384879725085912,
      "grad_norm": 0.41764020919799805,
      "learning_rate": 2e-05,
      "loss": 0.7866,
      "step": 2140
    },
    {
      "epoch": 0.18470790378006874,
      "grad_norm": 0.40405750274658203,
      "learning_rate": 2e-05,
      "loss": 0.8238,
      "step": 2150
    },
    {
      "epoch": 0.18556701030927836,
      "grad_norm": 0.4923059642314911,
      "learning_rate": 2e-05,
      "loss": 0.83,
      "step": 2160
    },
    {
      "epoch": 0.18642611683848798,
      "grad_norm": 0.44558045268058777,
      "learning_rate": 2e-05,
      "loss": 0.7791,
      "step": 2170
    },
    {
      "epoch": 0.1872852233676976,
      "grad_norm": 0.395918071269989,
      "learning_rate": 2e-05,
      "loss": 0.7709,
      "step": 2180
    },
    {
      "epoch": 0.18814432989690721,
      "grad_norm": 0.40383675694465637,
      "learning_rate": 2e-05,
      "loss": 0.7824,
      "step": 2190
    },
    {
      "epoch": 0.18900343642611683,
      "grad_norm": 0.42041248083114624,
      "learning_rate": 2e-05,
      "loss": 0.7589,
      "step": 2200
    },
    {
      "epoch": 0.18986254295532645,
      "grad_norm": 0.406876802444458,
      "learning_rate": 2e-05,
      "loss": 0.7947,
      "step": 2210
    },
    {
      "epoch": 0.19072164948453607,
      "grad_norm": 0.4463612139225006,
      "learning_rate": 2e-05,
      "loss": 0.7608,
      "step": 2220
    },
    {
      "epoch": 0.19158075601374572,
      "grad_norm": 0.42114925384521484,
      "learning_rate": 2e-05,
      "loss": 0.8017,
      "step": 2230
    },
    {
      "epoch": 0.19243986254295534,
      "grad_norm": 0.5391575694084167,
      "learning_rate": 2e-05,
      "loss": 0.8105,
      "step": 2240
    },
    {
      "epoch": 0.19329896907216496,
      "grad_norm": 0.4293856620788574,
      "learning_rate": 2e-05,
      "loss": 0.803,
      "step": 2250
    },
    {
      "epoch": 0.19415807560137457,
      "grad_norm": 0.4132872521877289,
      "learning_rate": 2e-05,
      "loss": 0.773,
      "step": 2260
    },
    {
      "epoch": 0.1950171821305842,
      "grad_norm": 0.42714643478393555,
      "learning_rate": 2e-05,
      "loss": 0.7969,
      "step": 2270
    },
    {
      "epoch": 0.1958762886597938,
      "grad_norm": 0.416900634765625,
      "learning_rate": 2e-05,
      "loss": 0.7813,
      "step": 2280
    },
    {
      "epoch": 0.19673539518900343,
      "grad_norm": 0.40540578961372375,
      "learning_rate": 2e-05,
      "loss": 0.7846,
      "step": 2290
    },
    {
      "epoch": 0.19759450171821305,
      "grad_norm": 0.3905494511127472,
      "learning_rate": 2e-05,
      "loss": 0.7636,
      "step": 2300
    },
    {
      "epoch": 0.19845360824742267,
      "grad_norm": 0.4042344391345978,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "step": 2310
    },
    {
      "epoch": 0.19931271477663232,
      "grad_norm": 0.41851627826690674,
      "learning_rate": 2e-05,
      "loss": 0.7524,
      "step": 2320
    },
    {
      "epoch": 0.20017182130584193,
      "grad_norm": 0.45878472924232483,
      "learning_rate": 2e-05,
      "loss": 0.7791,
      "step": 2330
    },
    {
      "epoch": 0.20103092783505155,
      "grad_norm": 0.3952105641365051,
      "learning_rate": 2e-05,
      "loss": 0.7652,
      "step": 2340
    },
    {
      "epoch": 0.20189003436426117,
      "grad_norm": 0.4032493829727173,
      "learning_rate": 2e-05,
      "loss": 0.7915,
      "step": 2350
    },
    {
      "epoch": 0.2027491408934708,
      "grad_norm": 0.4258342981338501,
      "learning_rate": 2e-05,
      "loss": 0.7769,
      "step": 2360
    },
    {
      "epoch": 0.2036082474226804,
      "grad_norm": 0.43611422181129456,
      "learning_rate": 2e-05,
      "loss": 0.8027,
      "step": 2370
    },
    {
      "epoch": 0.20446735395189003,
      "grad_norm": 0.41574737429618835,
      "learning_rate": 2e-05,
      "loss": 0.7815,
      "step": 2380
    },
    {
      "epoch": 0.20532646048109965,
      "grad_norm": 0.4091911017894745,
      "learning_rate": 2e-05,
      "loss": 0.7698,
      "step": 2390
    },
    {
      "epoch": 0.20618556701030927,
      "grad_norm": 0.4178768992424011,
      "learning_rate": 2e-05,
      "loss": 0.7955,
      "step": 2400
    },
    {
      "epoch": 0.20704467353951891,
      "grad_norm": 0.4205310046672821,
      "learning_rate": 2e-05,
      "loss": 0.754,
      "step": 2410
    },
    {
      "epoch": 0.20790378006872853,
      "grad_norm": 0.3947570323944092,
      "learning_rate": 2e-05,
      "loss": 0.7749,
      "step": 2420
    },
    {
      "epoch": 0.20876288659793815,
      "grad_norm": 0.425428181886673,
      "learning_rate": 2e-05,
      "loss": 0.7831,
      "step": 2430
    },
    {
      "epoch": 0.20962199312714777,
      "grad_norm": 0.4144151210784912,
      "learning_rate": 2e-05,
      "loss": 0.7924,
      "step": 2440
    },
    {
      "epoch": 0.2104810996563574,
      "grad_norm": 0.40834271907806396,
      "learning_rate": 2e-05,
      "loss": 0.7712,
      "step": 2450
    },
    {
      "epoch": 0.211340206185567,
      "grad_norm": 0.570460855960846,
      "learning_rate": 2e-05,
      "loss": 0.7918,
      "step": 2460
    },
    {
      "epoch": 0.21219931271477663,
      "grad_norm": 0.41472381353378296,
      "learning_rate": 2e-05,
      "loss": 0.7746,
      "step": 2470
    },
    {
      "epoch": 0.21305841924398625,
      "grad_norm": 0.4356991648674011,
      "learning_rate": 2e-05,
      "loss": 0.793,
      "step": 2480
    },
    {
      "epoch": 0.21391752577319587,
      "grad_norm": 0.425836443901062,
      "learning_rate": 2e-05,
      "loss": 0.7826,
      "step": 2490
    },
    {
      "epoch": 0.21477663230240548,
      "grad_norm": 0.9032119512557983,
      "learning_rate": 2e-05,
      "loss": 0.7696,
      "step": 2500
    },
    {
      "epoch": 0.21563573883161513,
      "grad_norm": 0.4030701518058777,
      "learning_rate": 2e-05,
      "loss": 0.7539,
      "step": 2510
    },
    {
      "epoch": 0.21649484536082475,
      "grad_norm": 0.4129731357097626,
      "learning_rate": 2e-05,
      "loss": 0.7652,
      "step": 2520
    },
    {
      "epoch": 0.21735395189003437,
      "grad_norm": 0.4277688264846802,
      "learning_rate": 2e-05,
      "loss": 0.7767,
      "step": 2530
    },
    {
      "epoch": 0.218213058419244,
      "grad_norm": 0.40256595611572266,
      "learning_rate": 2e-05,
      "loss": 0.7498,
      "step": 2540
    },
    {
      "epoch": 0.2190721649484536,
      "grad_norm": 0.4041889011859894,
      "learning_rate": 1.9980979278401095e-05,
      "loss": 0.7449,
      "step": 2550
    },
    {
      "epoch": 0.21993127147766323,
      "grad_norm": 0.4215486943721771,
      "learning_rate": 1.982924955463327e-05,
      "loss": 0.7658,
      "step": 2560
    },
    {
      "epoch": 0.22079037800687284,
      "grad_norm": 0.4209129512310028,
      "learning_rate": 1.9528108298328235e-05,
      "loss": 0.7378,
      "step": 2570
    },
    {
      "epoch": 0.22164948453608246,
      "grad_norm": 0.4091986119747162,
      "learning_rate": 1.9082156473635994e-05,
      "loss": 0.7621,
      "step": 2580
    },
    {
      "epoch": 0.22250859106529208,
      "grad_norm": 0.40685099363327026,
      "learning_rate": 1.8498207522139434e-05,
      "loss": 0.7432,
      "step": 2590
    },
    {
      "epoch": 0.22336769759450173,
      "grad_norm": 0.42579126358032227,
      "learning_rate": 1.7785183264196977e-05,
      "loss": 0.781,
      "step": 2600
    },
    {
      "epoch": 0.22422680412371135,
      "grad_norm": 0.44667190313339233,
      "learning_rate": 1.6953977587577846e-05,
      "loss": 0.7386,
      "step": 2610
    },
    {
      "epoch": 0.22508591065292097,
      "grad_norm": 0.41336899995803833,
      "learning_rate": 1.601729000601297e-05,
      "loss": 0.7933,
      "step": 2620
    },
    {
      "epoch": 0.2259450171821306,
      "grad_norm": 0.4215777814388275,
      "learning_rate": 1.4989431630624763e-05,
      "loss": 0.7706,
      "step": 2630
    },
    {
      "epoch": 0.2268041237113402,
      "grad_norm": 0.3887019455432892,
      "learning_rate": 1.3886106518686746e-05,
      "loss": 0.7439,
      "step": 2640
    },
    {
      "epoch": 0.22766323024054982,
      "grad_norm": 0.402194082736969,
      "learning_rate": 1.2724171740359612e-05,
      "loss": 0.7761,
      "step": 2650
    },
    {
      "epoch": 0.22852233676975944,
      "grad_norm": 0.39169350266456604,
      "learning_rate": 1.1521379829206218e-05,
      "loss": 0.7461,
      "step": 2660
    },
    {
      "epoch": 0.22938144329896906,
      "grad_norm": 0.40287256240844727,
      "learning_rate": 1.029610755143595e-05,
      "loss": 0.7495,
      "step": 2670
    },
    {
      "epoch": 0.23024054982817868,
      "grad_norm": 0.5714935660362244,
      "learning_rate": 9.067075137857348e-06,
      "loss": 0.7596,
      "step": 2680
    },
    {
      "epoch": 0.23109965635738833,
      "grad_norm": 0.4107722043991089,
      "learning_rate": 7.853060268232525e-06,
      "loss": 0.7587,
      "step": 2690
    },
    {
      "epoch": 0.23195876288659795,
      "grad_norm": 0.383517861366272,
      "learning_rate": 6.672611177902054e-06,
      "loss": 0.7435,
      "step": 2700
    },
    {
      "epoch": 0.23281786941580757,
      "grad_norm": 0.4090166985988617,
      "learning_rate": 5.543763269959312e-06,
      "loss": 0.771,
      "step": 2710
    },
    {
      "epoch": 0.23367697594501718,
      "grad_norm": 0.38220787048339844,
      "learning_rate": 4.483763562693867e-06,
      "loss": 0.7579,
      "step": 2720
    },
    {
      "epoch": 0.2345360824742268,
      "grad_norm": 0.3833133280277252,
      "learning_rate": 3.508807182313187e-06,
      "loss": 0.7575,
      "step": 2730
    },
    {
      "epoch": 0.23539518900343642,
      "grad_norm": 0.3855336010456085,
      "learning_rate": 2.6337899269187294e-06,
      "loss": 0.7554,
      "step": 2740
    },
    {
      "epoch": 0.23625429553264604,
      "grad_norm": 0.3928573727607727,
      "learning_rate": 1.8720806821693126e-06,
      "loss": 0.7696,
      "step": 2750
    },
    {
      "epoch": 0.23711340206185566,
      "grad_norm": 0.3914242088794708,
      "learning_rate": 1.2353171657619887e-06,
      "loss": 0.7232,
      "step": 2760
    },
    {
      "epoch": 0.23797250859106528,
      "grad_norm": 0.39246296882629395,
      "learning_rate": 7.332281214330356e-07,
      "loss": 0.7544,
      "step": 2770
    },
    {
      "epoch": 0.23883161512027493,
      "grad_norm": 0.38715675473213196,
      "learning_rate": 3.73484679074808e-07,
      "loss": 0.7675,
      "step": 2780
    },
    {
      "epoch": 0.23969072164948454,
      "grad_norm": 0.3912203311920166,
      "learning_rate": 1.61583151951702e-07,
      "loss": 0.7775,
      "step": 2790
    },
    {
      "epoch": 0.24037800687285224,
      "step": 2798,
      "total_flos": 1.1366756130249245e+19,
      "train_loss": 0.06909040999122822,
      "train_runtime": 2327.0142,
      "train_samples_per_second": 14.429,
      "train_steps_per_second": 1.202
    }
  ],
  "logging_steps": 10,
  "max_steps": 2798,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 159,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1366756130249245e+19,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}