{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1561524047470331,
  "eval_steps": 500,
  "global_step": 5000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001561524047470331,
      "grad_norm": 0.0020751953125,
      "learning_rate": 0.00019800000000000002,
      "loss": 1.1655,
      "step": 50
    },
    {
      "epoch": 0.003123048094940662,
      "grad_norm": 0.001617431640625,
      "learning_rate": 0.000196,
      "loss": 0.55,
      "step": 100
    },
    {
      "epoch": 0.004684572142410993,
      "grad_norm": 23.75,
      "learning_rate": 0.000194,
      "loss": 0.6685,
      "step": 150
    },
    {
      "epoch": 0.006246096189881324,
      "grad_norm": 5.53125,
      "learning_rate": 0.000192,
      "loss": 0.7517,
      "step": 200
    },
    {
      "epoch": 0.007807620237351655,
      "grad_norm": 7.34375,
      "learning_rate": 0.00019,
      "loss": 1.0534,
      "step": 250
    },
    {
      "epoch": 0.009369144284821987,
      "grad_norm": 0.06201171875,
      "learning_rate": 0.000188,
      "loss": 0.7181,
      "step": 300
    },
    {
      "epoch": 0.010930668332292318,
      "grad_norm": 6.9375,
      "learning_rate": 0.00018600000000000002,
      "loss": 0.8464,
      "step": 350
    },
    {
      "epoch": 0.012492192379762648,
      "grad_norm": 0.462890625,
      "learning_rate": 0.00018400000000000003,
      "loss": 0.6547,
      "step": 400
    },
    {
      "epoch": 0.014053716427232979,
      "grad_norm": 0.00799560546875,
      "learning_rate": 0.000182,
      "loss": 0.4934,
      "step": 450
    },
    {
      "epoch": 0.01561524047470331,
      "grad_norm": 0.11279296875,
      "learning_rate": 0.00018,
      "loss": 0.9624,
      "step": 500
    },
    {
      "epoch": 0.017176764522173642,
      "grad_norm": 6.4375,
      "learning_rate": 0.00017800000000000002,
      "loss": 0.7832,
      "step": 550
    },
    {
      "epoch": 0.018738288569643973,
      "grad_norm": 6.09375,
      "learning_rate": 0.00017600000000000002,
      "loss": 0.5558,
      "step": 600
    },
    {
      "epoch": 0.020299812617114305,
      "grad_norm": 0.0206298828125,
      "learning_rate": 0.000174,
      "loss": 0.6964,
      "step": 650
    },
    {
      "epoch": 0.021861336664584636,
      "grad_norm": 5.375,
      "learning_rate": 0.000172,
      "loss": 0.9689,
      "step": 700
    },
    {
      "epoch": 0.023422860712054967,
      "grad_norm": 0.0128173828125,
      "learning_rate": 0.00017,
      "loss": 0.5311,
      "step": 750
    },
    {
      "epoch": 0.024984384759525295,
      "grad_norm": 5.90625,
      "learning_rate": 0.000168,
      "loss": 0.7353,
      "step": 800
    },
    {
      "epoch": 0.026545908806995627,
      "grad_norm": 1.546875,
      "learning_rate": 0.000166,
      "loss": 0.8207,
      "step": 850
    },
    {
      "epoch": 0.028107432854465958,
      "grad_norm": 0.099609375,
      "learning_rate": 0.000164,
      "loss": 0.5583,
      "step": 900
    },
    {
      "epoch": 0.02966895690193629,
      "grad_norm": 0.125,
      "learning_rate": 0.000162,
      "loss": 0.4985,
      "step": 950
    },
    {
      "epoch": 0.03123048094940662,
      "grad_norm": 0.0004367828369140625,
      "learning_rate": 0.00016,
      "loss": 0.8198,
      "step": 1000
    },
    {
      "epoch": 0.03279200499687695,
      "grad_norm": 0.000621795654296875,
      "learning_rate": 0.00015800000000000002,
      "loss": 0.7978,
      "step": 1050
    },
    {
      "epoch": 0.034353529044347283,
      "grad_norm": 8.3125,
      "learning_rate": 0.00015600000000000002,
      "loss": 0.6805,
      "step": 1100
    },
    {
      "epoch": 0.03591505309181761,
      "grad_norm": 0.0291748046875,
      "learning_rate": 0.000154,
      "loss": 0.4919,
      "step": 1150
    },
    {
      "epoch": 0.037476577139287946,
      "grad_norm": 0.0013427734375,
      "learning_rate": 0.000152,
      "loss": 0.5838,
      "step": 1200
    },
    {
      "epoch": 0.039038101186758274,
      "grad_norm": 0.000522613525390625,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.8223,
      "step": 1250
    },
    {
      "epoch": 0.04059962523422861,
      "grad_norm": 6.78125,
      "learning_rate": 0.000148,
      "loss": 0.3529,
      "step": 1300
    },
    {
      "epoch": 0.04216114928169894,
      "grad_norm": 0.0035552978515625,
      "learning_rate": 0.000146,
      "loss": 0.359,
      "step": 1350
    },
    {
      "epoch": 0.04372267332916927,
      "grad_norm": 6.15625,
      "learning_rate": 0.000144,
      "loss": 0.9659,
      "step": 1400
    },
    {
      "epoch": 0.0452841973766396,
      "grad_norm": 2.15625,
      "learning_rate": 0.000142,
      "loss": 0.5283,
      "step": 1450
    },
    {
      "epoch": 0.046845721424109935,
      "grad_norm": 0.08740234375,
      "learning_rate": 0.00014,
      "loss": 0.7926,
      "step": 1500
    },
    {
      "epoch": 0.04840724547158026,
      "grad_norm": 4.9375,
      "learning_rate": 0.000138,
      "loss": 0.7535,
      "step": 1550
    },
    {
      "epoch": 0.04996876951905059,
      "grad_norm": 0.050537109375,
      "learning_rate": 0.00013600000000000003,
      "loss": 0.6911,
      "step": 1600
    },
    {
      "epoch": 0.051530293566520925,
      "grad_norm": 0.130859375,
      "learning_rate": 0.000134,
      "loss": 0.5835,
      "step": 1650
    },
    {
      "epoch": 0.05309181761399125,
      "grad_norm": 0.119140625,
      "learning_rate": 0.000132,
      "loss": 0.7359,
      "step": 1700
    },
    {
      "epoch": 0.05465334166146159,
      "grad_norm": 5.4375,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.4318,
      "step": 1750
    },
    {
      "epoch": 0.056214865708931916,
      "grad_norm": 6.09375,
      "learning_rate": 0.00012800000000000002,
      "loss": 0.4924,
      "step": 1800
    },
    {
      "epoch": 0.05777638975640225,
      "grad_norm": 0.0186767578125,
      "learning_rate": 0.000126,
      "loss": 0.8286,
      "step": 1850
    },
    {
      "epoch": 0.05933791380387258,
      "grad_norm": 0.75390625,
      "learning_rate": 0.000124,
      "loss": 0.6285,
      "step": 1900
    },
    {
      "epoch": 0.060899437851342914,
      "grad_norm": 0.0005950927734375,
      "learning_rate": 0.000122,
      "loss": 0.6394,
      "step": 1950
    },
    {
      "epoch": 0.06246096189881324,
      "grad_norm": 3.390625,
      "learning_rate": 0.00012,
      "loss": 0.7705,
      "step": 2000
    },
    {
      "epoch": 0.06402248594628357,
      "grad_norm": 20.25,
      "learning_rate": 0.000118,
      "loss": 0.7837,
      "step": 2050
    },
    {
      "epoch": 0.0655840099937539,
      "grad_norm": 0.0009918212890625,
      "learning_rate": 0.000116,
      "loss": 0.4914,
      "step": 2100
    },
    {
      "epoch": 0.06714553404122424,
      "grad_norm": 0.00162506103515625,
      "learning_rate": 0.00011399999999999999,
      "loss": 0.6094,
      "step": 2150
    },
    {
      "epoch": 0.06870705808869457,
      "grad_norm": 5.65625,
      "learning_rate": 0.00011200000000000001,
      "loss": 0.6238,
      "step": 2200
    },
    {
      "epoch": 0.0702685821361649,
      "grad_norm": 0.11181640625,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.5555,
      "step": 2250
    },
    {
      "epoch": 0.07183010618363522,
      "grad_norm": 0.28515625,
      "learning_rate": 0.00010800000000000001,
      "loss": 0.3776,
      "step": 2300
    },
    {
      "epoch": 0.07339163023110556,
      "grad_norm": 0.00787353515625,
      "learning_rate": 0.00010600000000000002,
      "loss": 0.7962,
      "step": 2350
    },
    {
      "epoch": 0.07495315427857589,
      "grad_norm": 0.07080078125,
      "learning_rate": 0.00010400000000000001,
      "loss": 0.8551,
      "step": 2400
    },
    {
      "epoch": 0.07651467832604622,
      "grad_norm": 0.058837890625,
      "learning_rate": 0.00010200000000000001,
      "loss": 0.5114,
      "step": 2450
    },
    {
      "epoch": 0.07807620237351655,
      "grad_norm": 4.1875,
      "learning_rate": 0.0001,
      "loss": 0.5047,
      "step": 2500
    },
    {
      "epoch": 0.07963772642098688,
      "grad_norm": 0.0181884765625,
      "learning_rate": 9.8e-05,
      "loss": 0.561,
      "step": 2550
    },
    {
      "epoch": 0.08119925046845722,
      "grad_norm": 6.96875,
      "learning_rate": 9.6e-05,
      "loss": 0.6499,
      "step": 2600
    },
    {
      "epoch": 0.08276077451592755,
      "grad_norm": 5.5625,
      "learning_rate": 9.4e-05,
      "loss": 0.5555,
      "step": 2650
    },
    {
      "epoch": 0.08432229856339787,
      "grad_norm": 0.1015625,
      "learning_rate": 9.200000000000001e-05,
      "loss": 0.86,
      "step": 2700
    },
    {
      "epoch": 0.0858838226108682,
      "grad_norm": 0.021240234375,
      "learning_rate": 9e-05,
      "loss": 0.7037,
      "step": 2750
    },
    {
      "epoch": 0.08744534665833854,
      "grad_norm": 6.1875,
      "learning_rate": 8.800000000000001e-05,
      "loss": 0.6467,
      "step": 2800
    },
    {
      "epoch": 0.08900687070580887,
      "grad_norm": 0.004608154296875,
      "learning_rate": 8.6e-05,
      "loss": 0.4786,
      "step": 2850
    },
    {
      "epoch": 0.0905683947532792,
      "grad_norm": 0.396484375,
      "learning_rate": 8.4e-05,
      "loss": 0.9433,
      "step": 2900
    },
    {
      "epoch": 0.09212991880074953,
      "grad_norm": 6.3125,
      "learning_rate": 8.2e-05,
      "loss": 0.7547,
      "step": 2950
    },
    {
      "epoch": 0.09369144284821987,
      "grad_norm": 0.000637054443359375,
      "learning_rate": 8e-05,
      "loss": 0.4408,
      "step": 3000
    },
    {
      "epoch": 0.0952529668956902,
      "grad_norm": 0.0029449462890625,
      "learning_rate": 7.800000000000001e-05,
      "loss": 0.6513,
      "step": 3050
    },
    {
      "epoch": 0.09681449094316052,
      "grad_norm": 3.546875,
      "learning_rate": 7.6e-05,
      "loss": 0.8695,
      "step": 3100
    },
    {
      "epoch": 0.09837601499063085,
      "grad_norm": 9.875,
      "learning_rate": 7.4e-05,
      "loss": 0.3289,
      "step": 3150
    },
    {
      "epoch": 0.09993753903810118,
      "grad_norm": 0.0277099609375,
      "learning_rate": 7.2e-05,
      "loss": 1.0484,
      "step": 3200
    },
    {
      "epoch": 0.10149906308557152,
      "grad_norm": 0.0023956298828125,
      "learning_rate": 7e-05,
      "loss": 0.4233,
      "step": 3250
    },
    {
      "epoch": 0.10306058713304185,
      "grad_norm": 4.625,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.1324,
      "step": 3300
    },
    {
      "epoch": 0.10462211118051218,
      "grad_norm": 0.016357421875,
      "learning_rate": 6.6e-05,
      "loss": 0.7022,
      "step": 3350
    },
    {
      "epoch": 0.1061836352279825,
      "grad_norm": 0.0027618408203125,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.7385,
      "step": 3400
    },
    {
      "epoch": 0.10774515927545285,
      "grad_norm": 0.024658203125,
      "learning_rate": 6.2e-05,
      "loss": 0.8815,
      "step": 3450
    },
    {
      "epoch": 0.10930668332292318,
      "grad_norm": 3.953125,
      "learning_rate": 6e-05,
      "loss": 0.7281,
      "step": 3500
    },
    {
      "epoch": 0.1108682073703935,
      "grad_norm": 6.0,
      "learning_rate": 5.8e-05,
      "loss": 0.666,
      "step": 3550
    },
    {
      "epoch": 0.11242973141786383,
      "grad_norm": 0.0004177093505859375,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 0.6714,
      "step": 3600
    },
    {
      "epoch": 0.11399125546533416,
      "grad_norm": 5.5625,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 0.7718,
      "step": 3650
    },
    {
      "epoch": 0.1155527795128045,
      "grad_norm": 5.65625,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 0.6455,
      "step": 3700
    },
    {
      "epoch": 0.11711430356027483,
      "grad_norm": 0.0012969970703125,
      "learning_rate": 5e-05,
      "loss": 0.8328,
      "step": 3750
    },
    {
      "epoch": 0.11867582760774516,
      "grad_norm": 0.0003147125244140625,
      "learning_rate": 4.8e-05,
      "loss": 0.6205,
      "step": 3800
    },
    {
      "epoch": 0.12023735165521549,
      "grad_norm": 0.00146484375,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.6064,
      "step": 3850
    },
    {
      "epoch": 0.12179887570268583,
      "grad_norm": 0.11474609375,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.6402,
      "step": 3900
    },
    {
      "epoch": 0.12336039975015615,
      "grad_norm": 0.0016021728515625,
      "learning_rate": 4.2e-05,
      "loss": 0.2071,
      "step": 3950
    },
    {
      "epoch": 0.12492192379762648,
      "grad_norm": 0.000591278076171875,
      "learning_rate": 4e-05,
      "loss": 0.4755,
      "step": 4000
    },
    {
      "epoch": 0.12648344784509682,
      "grad_norm": 0.0157470703125,
      "learning_rate": 3.8e-05,
      "loss": 0.4945,
      "step": 4050
    },
    {
      "epoch": 0.12804497189256714,
      "grad_norm": 8.9375,
      "learning_rate": 3.6e-05,
      "loss": 0.5449,
      "step": 4100
    },
    {
      "epoch": 0.12960649594003748,
      "grad_norm": 0.00732421875,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 0.5369,
      "step": 4150
    },
    {
      "epoch": 0.1311680199875078,
      "grad_norm": 8.625,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.8617,
      "step": 4200
    },
    {
      "epoch": 0.13272954403497814,
      "grad_norm": 5.5625,
      "learning_rate": 3e-05,
      "loss": 0.3852,
      "step": 4250
    },
    {
      "epoch": 0.13429106808244848,
      "grad_norm": 7.6875,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 0.7667,
      "step": 4300
    },
    {
      "epoch": 0.1358525921299188,
      "grad_norm": 0.000286102294921875,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 0.8205,
      "step": 4350
    },
    {
      "epoch": 0.13741411617738913,
      "grad_norm": 5.96875,
      "learning_rate": 2.4e-05,
      "loss": 0.8517,
      "step": 4400
    },
    {
      "epoch": 0.13897564022485948,
      "grad_norm": 4.9375,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 0.9827,
      "step": 4450
    },
    {
      "epoch": 0.1405371642723298,
      "grad_norm": 5.46875,
      "learning_rate": 2e-05,
      "loss": 0.499,
      "step": 4500
    },
    {
      "epoch": 0.14209868831980013,
      "grad_norm": 0.00156402587890625,
      "learning_rate": 1.8e-05,
      "loss": 0.6781,
      "step": 4550
    },
    {
      "epoch": 0.14366021236727045,
      "grad_norm": 0.000255584716796875,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.5317,
      "step": 4600
    },
    {
      "epoch": 0.1452217364147408,
      "grad_norm": 7.59375,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 0.7491,
      "step": 4650
    },
    {
      "epoch": 0.14678326046221113,
      "grad_norm": 8.25,
      "learning_rate": 1.2e-05,
      "loss": 0.7373,
      "step": 4700
    },
    {
      "epoch": 0.14834478450968144,
      "grad_norm": 0.00445556640625,
      "learning_rate": 1e-05,
      "loss": 0.4924,
      "step": 4750
    },
    {
      "epoch": 0.14990630855715179,
      "grad_norm": 7.25,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.7882,
      "step": 4800
    },
    {
      "epoch": 0.1514678326046221,
      "grad_norm": 2.375,
      "learning_rate": 6e-06,
      "loss": 0.5924,
      "step": 4850
    },
    {
      "epoch": 0.15302935665209244,
      "grad_norm": 0.09814453125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.3448,
      "step": 4900
    },
    {
      "epoch": 0.15459088069956278,
      "grad_norm": 0.0004730224609375,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.8267,
      "step": 4950
    },
    {
      "epoch": 0.1561524047470331,
      "grad_norm": 0.034423828125,
      "learning_rate": 0.0,
      "loss": 0.5791,
      "step": 5000
    }
  ],
  "logging_steps": 50,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.784334008901632e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}