{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5183025591188857,
  "eval_steps": 10,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025915127955944283,
      "grad_norm": 12.625,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.7977,
      "step": 1
    },
    {
      "epoch": 0.0051830255911888565,
      "grad_norm": 12.0625,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.7787,
      "step": 2
    },
    {
      "epoch": 0.007774538386783284,
      "grad_norm": 13.0,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.8003,
      "step": 3
    },
    {
      "epoch": 0.010366051182377713,
      "grad_norm": 12.5625,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.787,
      "step": 4
    },
    {
      "epoch": 0.01295756397797214,
      "grad_norm": 12.25,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.7684,
      "step": 5
    },
    {
      "epoch": 0.015549076773566569,
      "grad_norm": 12.625,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.7544,
      "step": 6
    },
    {
      "epoch": 0.018140589569160998,
      "grad_norm": 12.5,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.7769,
      "step": 7
    },
    {
      "epoch": 0.020732102364755426,
      "grad_norm": 11.4375,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.7161,
      "step": 8
    },
    {
      "epoch": 0.023323615160349854,
      "grad_norm": 11.5,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.7165,
      "step": 9
    },
    {
      "epoch": 0.02591512795594428,
      "grad_norm": 12.1875,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.7437,
      "step": 10
    },
    {
      "epoch": 0.02591512795594428,
      "eval_loss": 1.7256978750228882,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5814,
      "eval_samples_per_second": 105.893,
      "eval_steps_per_second": 13.262,
      "step": 10
    },
    {
      "epoch": 0.02850664075153871,
      "grad_norm": 11.4375,
      "learning_rate": 4.4e-06,
      "loss": 1.7068,
      "step": 11
    },
    {
      "epoch": 0.031098153547133137,
      "grad_norm": 11.75,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.688,
      "step": 12
    },
    {
      "epoch": 0.03368966634272757,
      "grad_norm": 11.6875,
      "learning_rate": 5.2e-06,
      "loss": 1.6602,
      "step": 13
    },
    {
      "epoch": 0.036281179138321996,
      "grad_norm": 11.5625,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.6389,
      "step": 14
    },
    {
      "epoch": 0.038872691933916424,
      "grad_norm": 10.75,
      "learning_rate": 6e-06,
      "loss": 1.6228,
      "step": 15
    },
    {
      "epoch": 0.04146420472951085,
      "grad_norm": 10.8125,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.5823,
      "step": 16
    },
    {
      "epoch": 0.04405571752510528,
      "grad_norm": 9.5625,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.5134,
      "step": 17
    },
    {
      "epoch": 0.04664723032069971,
      "grad_norm": 9.125,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.4833,
      "step": 18
    },
    {
      "epoch": 0.049238743116294136,
      "grad_norm": 7.375,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.4966,
      "step": 19
    },
    {
      "epoch": 0.05183025591188856,
      "grad_norm": 7.0,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.4653,
      "step": 20
    },
    {
      "epoch": 0.05183025591188856,
      "eval_loss": 1.4041186571121216,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.6226,
      "eval_samples_per_second": 105.716,
      "eval_steps_per_second": 13.24,
      "step": 20
    },
    {
      "epoch": 0.05442176870748299,
      "grad_norm": 6.0625,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.3844,
      "step": 21
    },
    {
      "epoch": 0.05701328150307742,
      "grad_norm": 5.375,
      "learning_rate": 8.8e-06,
      "loss": 1.3735,
      "step": 22
    },
    {
      "epoch": 0.05960479429867185,
      "grad_norm": 5.09375,
      "learning_rate": 9.200000000000002e-06,
      "loss": 1.3281,
      "step": 23
    },
    {
      "epoch": 0.062196307094266275,
      "grad_norm": 5.25,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.2837,
      "step": 24
    },
    {
      "epoch": 0.06478781988986071,
      "grad_norm": 5.25,
      "learning_rate": 1e-05,
      "loss": 1.2777,
      "step": 25
    },
    {
      "epoch": 0.06737933268545514,
      "grad_norm": 5.03125,
      "learning_rate": 1.04e-05,
      "loss": 1.2465,
      "step": 26
    },
    {
      "epoch": 0.06997084548104957,
      "grad_norm": 5.0625,
      "learning_rate": 1.0800000000000002e-05,
      "loss": 1.2041,
      "step": 27
    },
    {
      "epoch": 0.07256235827664399,
      "grad_norm": 4.9375,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 1.1524,
      "step": 28
    },
    {
      "epoch": 0.07515387107223842,
      "grad_norm": 4.65625,
      "learning_rate": 1.16e-05,
      "loss": 1.1491,
      "step": 29
    },
    {
      "epoch": 0.07774538386783285,
      "grad_norm": 5.125,
      "learning_rate": 1.2e-05,
      "loss": 1.127,
      "step": 30
    },
    {
      "epoch": 0.07774538386783285,
      "eval_loss": 1.105301856994629,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5195,
      "eval_samples_per_second": 106.161,
      "eval_steps_per_second": 13.296,
      "step": 30
    },
    {
      "epoch": 0.08033689666342728,
      "grad_norm": 5.09375,
      "learning_rate": 1.2400000000000002e-05,
      "loss": 1.0993,
      "step": 31
    },
    {
      "epoch": 0.0829284094590217,
      "grad_norm": 4.9375,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 1.0637,
      "step": 32
    },
    {
      "epoch": 0.08551992225461613,
      "grad_norm": 4.75,
      "learning_rate": 1.3200000000000002e-05,
      "loss": 1.0447,
      "step": 33
    },
    {
      "epoch": 0.08811143505021056,
      "grad_norm": 5.21875,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.047,
      "step": 34
    },
    {
      "epoch": 0.09070294784580499,
      "grad_norm": 4.9375,
      "learning_rate": 1.4e-05,
      "loss": 0.9841,
      "step": 35
    },
    {
      "epoch": 0.09329446064139942,
      "grad_norm": 4.90625,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 0.9735,
      "step": 36
    },
    {
      "epoch": 0.09588597343699384,
      "grad_norm": 5.71875,
      "learning_rate": 1.48e-05,
      "loss": 0.9409,
      "step": 37
    },
    {
      "epoch": 0.09847748623258827,
      "grad_norm": 5.0625,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 0.9108,
      "step": 38
    },
    {
      "epoch": 0.1010689990281827,
      "grad_norm": 4.90625,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.9029,
      "step": 39
    },
    {
      "epoch": 0.10366051182377713,
      "grad_norm": 5.0625,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.8938,
      "step": 40
    },
    {
      "epoch": 0.10366051182377713,
      "eval_loss": 0.8692858815193176,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5016,
      "eval_samples_per_second": 106.238,
      "eval_steps_per_second": 13.305,
      "step": 40
    },
    {
      "epoch": 0.10625202461937155,
      "grad_norm": 5.125,
      "learning_rate": 1.64e-05,
      "loss": 0.8501,
      "step": 41
    },
    {
      "epoch": 0.10884353741496598,
      "grad_norm": 4.53125,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 0.8545,
      "step": 42
    },
    {
      "epoch": 0.11143505021056041,
      "grad_norm": 5.1875,
      "learning_rate": 1.72e-05,
      "loss": 0.8169,
      "step": 43
    },
    {
      "epoch": 0.11402656300615484,
      "grad_norm": 4.5,
      "learning_rate": 1.76e-05,
      "loss": 0.8102,
      "step": 44
    },
    {
      "epoch": 0.11661807580174927,
      "grad_norm": 4.3125,
      "learning_rate": 1.8e-05,
      "loss": 0.8093,
      "step": 45
    },
    {
      "epoch": 0.1192095885973437,
      "grad_norm": 4.28125,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 0.7798,
      "step": 46
    },
    {
      "epoch": 0.12180110139293812,
      "grad_norm": 4.09375,
      "learning_rate": 1.88e-05,
      "loss": 0.7761,
      "step": 47
    },
    {
      "epoch": 0.12439261418853255,
      "grad_norm": 4.125,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 0.7647,
      "step": 48
    },
    {
      "epoch": 0.12698412698412698,
      "grad_norm": 3.765625,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.7612,
      "step": 49
    },
    {
      "epoch": 0.12957563977972142,
      "grad_norm": 4.0,
      "learning_rate": 2e-05,
      "loss": 0.7498,
      "step": 50
    },
    {
      "epoch": 0.12957563977972142,
      "eval_loss": 0.744697093963623,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.6181,
      "eval_samples_per_second": 105.735,
      "eval_steps_per_second": 13.242,
      "step": 50
    },
    {
      "epoch": 0.13216715257531583,
      "grad_norm": 4.5,
      "learning_rate": 1.9999560279257315e-05,
      "loss": 0.7504,
      "step": 51
    },
    {
      "epoch": 0.13475866537091027,
      "grad_norm": 3.796875,
      "learning_rate": 1.999824115570012e-05,
      "loss": 0.7181,
      "step": 52
    },
    {
      "epoch": 0.1373501781665047,
      "grad_norm": 3.703125,
      "learning_rate": 1.9996042745337617e-05,
      "loss": 0.7195,
      "step": 53
    },
    {
      "epoch": 0.13994169096209913,
      "grad_norm": 3.921875,
      "learning_rate": 1.999296524150713e-05,
      "loss": 0.7232,
      "step": 54
    },
    {
      "epoch": 0.14253320375769354,
      "grad_norm": 3.6875,
      "learning_rate": 1.9989008914857115e-05,
      "loss": 0.725,
      "step": 55
    },
    {
      "epoch": 0.14512471655328799,
      "grad_norm": 3.734375,
      "learning_rate": 1.9984174113323352e-05,
      "loss": 0.6972,
      "step": 56
    },
    {
      "epoch": 0.1477162293488824,
      "grad_norm": 3.5,
      "learning_rate": 1.9978461262098342e-05,
      "loss": 0.6792,
      "step": 57
    },
    {
      "epoch": 0.15030774214447684,
      "grad_norm": 4.0625,
      "learning_rate": 1.9971870863593924e-05,
      "loss": 0.7192,
      "step": 58
    },
    {
      "epoch": 0.15289925494007126,
      "grad_norm": 3.75,
      "learning_rate": 1.9964403497397086e-05,
      "loss": 0.7107,
      "step": 59
    },
    {
      "epoch": 0.1554907677356657,
      "grad_norm": 3.953125,
      "learning_rate": 1.9956059820218982e-05,
      "loss": 0.6866,
      "step": 60
    },
    {
      "epoch": 0.1554907677356657,
      "eval_loss": 0.6849498152732849,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5203,
      "eval_samples_per_second": 106.157,
      "eval_steps_per_second": 13.295,
      "step": 60
    },
    {
      "epoch": 0.1580822805312601,
      "grad_norm": 3.953125,
      "learning_rate": 1.9946840565837206e-05,
      "loss": 0.6818,
      "step": 61
    },
    {
      "epoch": 0.16067379332685455,
      "grad_norm": 3.546875,
      "learning_rate": 1.9936746545031225e-05,
      "loss": 0.6855,
      "step": 62
    },
    {
      "epoch": 0.16326530612244897,
      "grad_norm": 3.359375,
      "learning_rate": 1.9925778645511112e-05,
      "loss": 0.6799,
      "step": 63
    },
    {
      "epoch": 0.1658568189180434,
      "grad_norm": 3.828125,
      "learning_rate": 1.991393783183945e-05,
      "loss": 0.6719,
      "step": 64
    },
    {
      "epoch": 0.16844833171363785,
      "grad_norm": 3.0,
      "learning_rate": 1.990122514534651e-05,
      "loss": 0.66,
      "step": 65
    },
    {
      "epoch": 0.17103984450923226,
      "grad_norm": 2.96875,
      "learning_rate": 1.988764170403869e-05,
      "loss": 0.6718,
      "step": 66
    },
    {
      "epoch": 0.1736313573048267,
      "grad_norm": 3.15625,
      "learning_rate": 1.9873188702500163e-05,
      "loss": 0.6661,
      "step": 67
    },
    {
      "epoch": 0.17622287010042112,
      "grad_norm": 2.828125,
      "learning_rate": 1.9857867411787847e-05,
      "loss": 0.6523,
      "step": 68
    },
    {
      "epoch": 0.17881438289601556,
      "grad_norm": 3.203125,
      "learning_rate": 1.9841679179319605e-05,
      "loss": 0.6494,
      "step": 69
    },
    {
      "epoch": 0.18140589569160998,
      "grad_norm": 2.875,
      "learning_rate": 1.982462542875576e-05,
      "loss": 0.6411,
      "step": 70
    },
    {
      "epoch": 0.18140589569160998,
      "eval_loss": 0.6511064171791077,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5304,
      "eval_samples_per_second": 106.113,
      "eval_steps_per_second": 13.29,
      "step": 70
    },
    {
      "epoch": 0.18399740848720442,
      "grad_norm": 3.296875,
      "learning_rate": 1.9806707659873886e-05,
      "loss": 0.6463,
      "step": 71
    },
    {
      "epoch": 0.18658892128279883,
      "grad_norm": 3.0625,
      "learning_rate": 1.9787927448436913e-05,
      "loss": 0.6375,
      "step": 72
    },
    {
      "epoch": 0.18918043407839327,
      "grad_norm": 2.75,
      "learning_rate": 1.9768286446054533e-05,
      "loss": 0.6386,
      "step": 73
    },
    {
      "epoch": 0.1917719468739877,
      "grad_norm": 2.875,
      "learning_rate": 1.974778638003799e-05,
      "loss": 0.6368,
      "step": 74
    },
    {
      "epoch": 0.19436345966958213,
      "grad_norm": 2.953125,
      "learning_rate": 1.972642905324813e-05,
      "loss": 0.6271,
      "step": 75
    },
    {
      "epoch": 0.19695497246517654,
      "grad_norm": 2.921875,
      "learning_rate": 1.9704216343936875e-05,
      "loss": 0.6501,
      "step": 76
    },
    {
      "epoch": 0.19954648526077098,
      "grad_norm": 3.015625,
      "learning_rate": 1.9681150205582025e-05,
      "loss": 0.6111,
      "step": 77
    },
    {
      "epoch": 0.2021379980563654,
      "grad_norm": 3.171875,
      "learning_rate": 1.9657232666715485e-05,
      "loss": 0.651,
      "step": 78
    },
    {
      "epoch": 0.20472951085195984,
      "grad_norm": 3.0625,
      "learning_rate": 1.9632465830744846e-05,
      "loss": 0.6184,
      "step": 79
    },
    {
      "epoch": 0.20732102364755425,
      "grad_norm": 3.25,
      "learning_rate": 1.9606851875768404e-05,
      "loss": 0.6259,
      "step": 80
    },
    {
      "epoch": 0.20732102364755425,
      "eval_loss": 0.6278263330459595,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.4892,
      "eval_samples_per_second": 106.292,
      "eval_steps_per_second": 13.312,
      "step": 80
    },
    {
      "epoch": 0.2099125364431487,
      "grad_norm": 2.875,
      "learning_rate": 1.9580393054383622e-05,
      "loss": 0.6288,
      "step": 81
    },
    {
      "epoch": 0.2125040492387431,
      "grad_norm": 3.359375,
      "learning_rate": 1.9553091693489018e-05,
      "loss": 0.6403,
      "step": 82
    },
    {
      "epoch": 0.21509556203433755,
      "grad_norm": 2.921875,
      "learning_rate": 1.9524950194079534e-05,
      "loss": 0.621,
      "step": 83
    },
    {
      "epoch": 0.21768707482993196,
      "grad_norm": 2.84375,
      "learning_rate": 1.9495971031035367e-05,
      "loss": 0.6135,
      "step": 84
    },
    {
      "epoch": 0.2202785876255264,
      "grad_norm": 2.921875,
      "learning_rate": 1.9466156752904344e-05,
      "loss": 0.6211,
      "step": 85
    },
    {
      "epoch": 0.22287010042112082,
      "grad_norm": 3.109375,
      "learning_rate": 1.9435509981677764e-05,
      "loss": 0.6198,
      "step": 86
    },
    {
      "epoch": 0.22546161321671526,
      "grad_norm": 2.625,
      "learning_rate": 1.9404033412559828e-05,
      "loss": 0.5972,
      "step": 87
    },
    {
      "epoch": 0.22805312601230968,
      "grad_norm": 3.0,
      "learning_rate": 1.9371729813730606e-05,
      "loss": 0.614,
      "step": 88
    },
    {
      "epoch": 0.23064463880790412,
      "grad_norm": 2.75,
      "learning_rate": 1.9338602026102594e-05,
      "loss": 0.5998,
      "step": 89
    },
    {
      "epoch": 0.23323615160349853,
      "grad_norm": 2.796875,
      "learning_rate": 1.9304652963070868e-05,
      "loss": 0.6181,
      "step": 90
    },
    {
      "epoch": 0.23323615160349853,
      "eval_loss": 0.6108965277671814,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.4982,
      "eval_samples_per_second": 106.253,
      "eval_steps_per_second": 13.307,
      "step": 90
    },
    {
      "epoch": 0.23582766439909297,
      "grad_norm": 2.8125,
      "learning_rate": 1.9269885610256866e-05,
      "loss": 0.6059,
      "step": 91
    },
    {
      "epoch": 0.2384191771946874,
      "grad_norm": 2.734375,
      "learning_rate": 1.9234303025245835e-05,
      "loss": 0.6165,
      "step": 92
    },
    {
      "epoch": 0.24101068999028183,
      "grad_norm": 2.984375,
      "learning_rate": 1.919790833731791e-05,
      "loss": 0.6241,
      "step": 93
    },
    {
      "epoch": 0.24360220278587624,
      "grad_norm": 3.015625,
      "learning_rate": 1.9160704747172935e-05,
      "loss": 0.5913,
      "step": 94
    },
    {
      "epoch": 0.24619371558147068,
      "grad_norm": 2.84375,
      "learning_rate": 1.9122695526648968e-05,
      "loss": 0.585,
      "step": 95
    },
    {
      "epoch": 0.2487852283770651,
      "grad_norm": 3.484375,
      "learning_rate": 1.9083884018434545e-05,
      "loss": 0.5897,
      "step": 96
    },
    {
      "epoch": 0.2513767411726595,
      "grad_norm": 2.84375,
      "learning_rate": 1.9044273635774707e-05,
      "loss": 0.6032,
      "step": 97
    },
    {
      "epoch": 0.25396825396825395,
      "grad_norm": 2.75,
      "learning_rate": 1.900386786217083e-05,
      "loss": 0.594,
      "step": 98
    },
    {
      "epoch": 0.2565597667638484,
      "grad_norm": 2.8125,
      "learning_rate": 1.8962670251074276e-05,
      "loss": 0.5958,
      "step": 99
    },
    {
      "epoch": 0.25915127955944284,
      "grad_norm": 2.65625,
      "learning_rate": 1.8920684425573865e-05,
      "loss": 0.5821,
      "step": 100
    },
    {
      "epoch": 0.25915127955944284,
      "eval_loss": 0.5988509058952332,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.4884,
      "eval_samples_per_second": 106.295,
      "eval_steps_per_second": 13.312,
      "step": 100
    },
    {
      "epoch": 0.2617427923550373,
      "grad_norm": 2.65625,
      "learning_rate": 1.887791407807728e-05,
      "loss": 0.5904,
      "step": 101
    },
    {
      "epoch": 0.26433430515063167,
      "grad_norm": 2.359375,
      "learning_rate": 1.883436296998631e-05,
      "loss": 0.5913,
      "step": 102
    },
    {
      "epoch": 0.2669258179462261,
      "grad_norm": 2.46875,
      "learning_rate": 1.8790034931366073e-05,
      "loss": 0.6114,
      "step": 103
    },
    {
      "epoch": 0.26951733074182055,
      "grad_norm": 2.359375,
      "learning_rate": 1.8744933860608183e-05,
      "loss": 0.5803,
      "step": 104
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 3.40625,
      "learning_rate": 1.8699063724087905e-05,
      "loss": 0.5865,
      "step": 105
    },
    {
      "epoch": 0.2747003563330094,
      "grad_norm": 2.28125,
      "learning_rate": 1.865242855581534e-05,
      "loss": 0.586,
      "step": 106
    },
    {
      "epoch": 0.2772918691286038,
      "grad_norm": 2.453125,
      "learning_rate": 1.8605032457080655e-05,
      "loss": 0.5926,
      "step": 107
    },
    {
      "epoch": 0.27988338192419826,
      "grad_norm": 2.203125,
      "learning_rate": 1.8556879596093393e-05,
      "loss": 0.5927,
      "step": 108
    },
    {
      "epoch": 0.2824748947197927,
      "grad_norm": 2.890625,
      "learning_rate": 1.850797420761592e-05,
      "loss": 0.5937,
      "step": 109
    },
    {
      "epoch": 0.2850664075153871,
      "grad_norm": 2.390625,
      "learning_rate": 1.8458320592590976e-05,
      "loss": 0.5644,
      "step": 110
    },
    {
      "epoch": 0.2850664075153871,
      "eval_loss": 0.5878391265869141,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.539,
      "eval_samples_per_second": 106.076,
      "eval_steps_per_second": 13.285,
      "step": 110
    },
    {
      "epoch": 0.28765792031098153,
      "grad_norm": 2.75,
      "learning_rate": 1.840792311776346e-05,
      "loss": 0.5783,
      "step": 111
    },
    {
      "epoch": 0.29024943310657597,
      "grad_norm": 2.375,
      "learning_rate": 1.8356786215296387e-05,
      "loss": 0.5813,
      "step": 112
    },
    {
      "epoch": 0.2928409459021704,
      "grad_norm": 2.46875,
      "learning_rate": 1.83049143823811e-05,
      "loss": 0.5788,
      "step": 113
    },
    {
      "epoch": 0.2954324586977648,
      "grad_norm": 2.71875,
      "learning_rate": 1.825231218084178e-05,
      "loss": 0.5831,
      "step": 114
    },
    {
      "epoch": 0.29802397149335924,
      "grad_norm": 2.484375,
      "learning_rate": 1.8198984236734246e-05,
      "loss": 0.5715,
      "step": 115
    },
    {
      "epoch": 0.3006154842889537,
      "grad_norm": 2.546875,
      "learning_rate": 1.8144935239939147e-05,
      "loss": 0.5938,
      "step": 116
    },
    {
      "epoch": 0.3032069970845481,
      "grad_norm": 2.90625,
      "learning_rate": 1.8090169943749477e-05,
      "loss": 0.5911,
      "step": 117
    },
    {
      "epoch": 0.3057985098801425,
      "grad_norm": 2.859375,
      "learning_rate": 1.8034693164452578e-05,
      "loss": 0.5815,
      "step": 118
    },
    {
      "epoch": 0.30839002267573695,
      "grad_norm": 2.65625,
      "learning_rate": 1.7978509780906578e-05,
      "loss": 0.5804,
      "step": 119
    },
    {
      "epoch": 0.3109815354713314,
      "grad_norm": 2.828125,
      "learning_rate": 1.7921624734111292e-05,
      "loss": 0.5749,
      "step": 120
    },
    {
      "epoch": 0.3109815354713314,
      "eval_loss": 0.5794549584388733,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5897,
      "eval_samples_per_second": 105.857,
      "eval_steps_per_second": 13.258,
      "step": 120
    },
    {
      "epoch": 0.31357304826692584,
      "grad_norm": 2.703125,
      "learning_rate": 1.786404302677374e-05,
      "loss": 0.5873,
      "step": 121
    },
    {
      "epoch": 0.3161645610625202,
      "grad_norm": 2.375,
      "learning_rate": 1.7805769722868132e-05,
      "loss": 0.5856,
      "step": 122
    },
    {
      "epoch": 0.31875607385811466,
      "grad_norm": 2.984375,
      "learning_rate": 1.7746809947190567e-05,
      "loss": 0.578,
      "step": 123
    },
    {
      "epoch": 0.3213475866537091,
      "grad_norm": 3.421875,
      "learning_rate": 1.768716888490832e-05,
      "loss": 0.5566,
      "step": 124
    },
    {
      "epoch": 0.32393909944930355,
      "grad_norm": 2.5625,
      "learning_rate": 1.762685178110382e-05,
      "loss": 0.5638,
      "step": 125
    },
    {
      "epoch": 0.32653061224489793,
      "grad_norm": 3.125,
      "learning_rate": 1.7565863940313416e-05,
      "loss": 0.5827,
      "step": 126
    },
    {
      "epoch": 0.3291221250404924,
      "grad_norm": 3.1875,
      "learning_rate": 1.7504210726060828e-05,
      "loss": 0.5596,
      "step": 127
    },
    {
      "epoch": 0.3317136378360868,
      "grad_norm": 2.984375,
      "learning_rate": 1.7441897560385493e-05,
      "loss": 0.5768,
      "step": 128
    },
    {
      "epoch": 0.33430515063168126,
      "grad_norm": 2.546875,
      "learning_rate": 1.7378929923365706e-05,
      "loss": 0.5732,
      "step": 129
    },
    {
      "epoch": 0.3368966634272757,
      "grad_norm": 2.78125,
      "learning_rate": 1.731531335263669e-05,
      "loss": 0.5781,
      "step": 130
    },
    {
      "epoch": 0.3368966634272757,
      "eval_loss": 0.572753369808197,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5459,
      "eval_samples_per_second": 106.046,
      "eval_steps_per_second": 13.281,
      "step": 130
    },
    {
      "epoch": 0.3394881762228701,
      "grad_norm": 2.421875,
      "learning_rate": 1.7251053442903597e-05,
      "loss": 0.5689,
      "step": 131
    },
    {
      "epoch": 0.34207968901846453,
      "grad_norm": 3.546875,
      "learning_rate": 1.7186155845449465e-05,
      "loss": 0.5695,
      "step": 132
    },
    {
      "epoch": 0.34467120181405897,
      "grad_norm": 2.4375,
      "learning_rate": 1.712062626763825e-05,
      "loss": 0.5627,
      "step": 133
    },
    {
      "epoch": 0.3472627146096534,
      "grad_norm": 2.796875,
      "learning_rate": 1.7054470472412876e-05,
      "loss": 0.5759,
      "step": 134
    },
    {
      "epoch": 0.3498542274052478,
      "grad_norm": 2.4375,
      "learning_rate": 1.698769427778842e-05,
      "loss": 0.5662,
      "step": 135
    },
    {
      "epoch": 0.35244574020084224,
      "grad_norm": 2.40625,
      "learning_rate": 1.6920303556340462e-05,
      "loss": 0.5671,
      "step": 136
    },
    {
      "epoch": 0.3550372529964367,
      "grad_norm": 2.890625,
      "learning_rate": 1.6852304234688627e-05,
      "loss": 0.5572,
      "step": 137
    },
    {
      "epoch": 0.3576287657920311,
      "grad_norm": 2.890625,
      "learning_rate": 1.678370229297535e-05,
      "loss": 0.5796,
      "step": 138
    },
    {
      "epoch": 0.3602202785876255,
      "grad_norm": 3.03125,
      "learning_rate": 1.6714503764339986e-05,
      "loss": 0.5642,
      "step": 139
    },
    {
      "epoch": 0.36281179138321995,
      "grad_norm": 2.3125,
      "learning_rate": 1.664471473438822e-05,
      "loss": 0.5711,
      "step": 140
    },
    {
      "epoch": 0.36281179138321995,
      "eval_loss": 0.566669762134552,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5724,
      "eval_samples_per_second": 105.932,
      "eval_steps_per_second": 13.267,
      "step": 140
    },
    {
      "epoch": 0.3654033041788144,
      "grad_norm": 2.625,
      "learning_rate": 1.657434134065686e-05,
      "loss": 0.5559,
      "step": 141
    },
    {
      "epoch": 0.36799481697440883,
      "grad_norm": 3.015625,
      "learning_rate": 1.6503389772074104e-05,
      "loss": 0.575,
      "step": 142
    },
    {
      "epoch": 0.3705863297700032,
      "grad_norm": 2.984375,
      "learning_rate": 1.643186626841524e-05,
      "loss": 0.5851,
      "step": 143
    },
    {
      "epoch": 0.37317784256559766,
      "grad_norm": 2.609375,
      "learning_rate": 1.6359777119753887e-05,
      "loss": 0.559,
      "step": 144
    },
    {
      "epoch": 0.3757693553611921,
      "grad_norm": 2.40625,
      "learning_rate": 1.628712866590885e-05,
      "loss": 0.5759,
      "step": 145
    },
    {
      "epoch": 0.37836086815678655,
      "grad_norm": 2.328125,
      "learning_rate": 1.6213927295886547e-05,
      "loss": 0.5579,
      "step": 146
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 2.453125,
      "learning_rate": 1.6140179447319134e-05,
      "loss": 0.5717,
      "step": 147
    },
    {
      "epoch": 0.3835438937479754,
      "grad_norm": 2.4375,
      "learning_rate": 1.6065891605898358e-05,
      "loss": 0.5531,
      "step": 148
    },
    {
      "epoch": 0.3861354065435698,
      "grad_norm": 2.484375,
      "learning_rate": 1.5991070304805184e-05,
      "loss": 0.5358,
      "step": 149
    },
    {
      "epoch": 0.38872691933916426,
      "grad_norm": 2.46875,
      "learning_rate": 1.5915722124135227e-05,
      "loss": 0.5715,
      "step": 150
    },
    {
      "epoch": 0.38872691933916426,
      "eval_loss": 0.5618191361427307,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5943,
      "eval_samples_per_second": 105.838,
      "eval_steps_per_second": 13.255,
      "step": 150
    },
    {
      "epoch": 0.39131843213475864,
      "grad_norm": 2.390625,
      "learning_rate": 1.5839853690320074e-05,
      "loss": 0.5413,
      "step": 151
    },
    {
      "epoch": 0.3939099449303531,
      "grad_norm": 2.28125,
      "learning_rate": 1.5763471675544547e-05,
      "loss": 0.5652,
      "step": 152
    },
    {
      "epoch": 0.3965014577259475,
      "grad_norm": 2.609375,
      "learning_rate": 1.5686582797159892e-05,
      "loss": 0.5682,
      "step": 153
    },
    {
      "epoch": 0.39909297052154197,
      "grad_norm": 2.71875,
      "learning_rate": 1.5609193817093057e-05,
      "loss": 0.5577,
      "step": 154
    },
    {
      "epoch": 0.40168448331713635,
      "grad_norm": 2.65625,
      "learning_rate": 1.5531311541251995e-05,
      "loss": 0.5412,
      "step": 155
    },
    {
      "epoch": 0.4042759961127308,
      "grad_norm": 2.4375,
      "learning_rate": 1.5452942818927144e-05,
      "loss": 0.5441,
      "step": 156
    },
    {
      "epoch": 0.40686750890832524,
      "grad_norm": 2.390625,
      "learning_rate": 1.5374094542189055e-05,
      "loss": 0.5764,
      "step": 157
    },
    {
      "epoch": 0.4094590217039197,
      "grad_norm": 3.078125,
      "learning_rate": 1.52947736452823e-05,
      "loss": 0.5763,
      "step": 158
    },
    {
      "epoch": 0.41205053449951407,
      "grad_norm": 2.5625,
      "learning_rate": 1.521498710401561e-05,
      "loss": 0.5482,
      "step": 159
    },
    {
      "epoch": 0.4146420472951085,
      "grad_norm": 2.375,
      "learning_rate": 1.513474193514842e-05,
      "loss": 0.559,
      "step": 160
    },
    {
      "epoch": 0.4146420472951085,
      "eval_loss": 0.5573883056640625,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5874,
      "eval_samples_per_second": 105.867,
      "eval_steps_per_second": 13.259,
      "step": 160
    },
    {
      "epoch": 0.41723356009070295,
      "grad_norm": 2.28125,
      "learning_rate": 1.505404519577379e-05,
      "loss": 0.5642,
      "step": 161
    },
    {
      "epoch": 0.4198250728862974,
      "grad_norm": 2.40625,
      "learning_rate": 1.4972903982697744e-05,
      "loss": 0.5535,
      "step": 162
    },
    {
      "epoch": 0.42241658568189183,
      "grad_norm": 2.34375,
      "learning_rate": 1.4891325431815182e-05,
      "loss": 0.5519,
      "step": 163
    },
    {
      "epoch": 0.4250080984774862,
      "grad_norm": 2.0,
      "learning_rate": 1.48093167174823e-05,
      "loss": 0.5611,
      "step": 164
    },
    {
      "epoch": 0.42759961127308066,
      "grad_norm": 2.140625,
      "learning_rate": 1.4726885051885654e-05,
      "loss": 0.5556,
      "step": 165
    },
    {
      "epoch": 0.4301911240686751,
      "grad_norm": 2.40625,
      "learning_rate": 1.4644037684407883e-05,
      "loss": 0.5289,
      "step": 166
    },
    {
      "epoch": 0.43278263686426954,
      "grad_norm": 2.09375,
      "learning_rate": 1.4560781900990187e-05,
      "loss": 0.5538,
      "step": 167
    },
    {
      "epoch": 0.43537414965986393,
      "grad_norm": 2.34375,
      "learning_rate": 1.4477125023491536e-05,
      "loss": 0.5589,
      "step": 168
    },
    {
      "epoch": 0.43796566245545837,
      "grad_norm": 2.359375,
      "learning_rate": 1.4393074409044802e-05,
      "loss": 0.5423,
      "step": 169
    },
    {
      "epoch": 0.4405571752510528,
      "grad_norm": 2.15625,
      "learning_rate": 1.4308637449409705e-05,
      "loss": 0.5593,
      "step": 170
    },
    {
      "epoch": 0.4405571752510528,
      "eval_loss": 0.553532063961029,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5188,
      "eval_samples_per_second": 106.163,
      "eval_steps_per_second": 13.296,
      "step": 170
    },
    {
      "epoch": 0.44314868804664725,
      "grad_norm": 2.421875,
      "learning_rate": 1.4223821570322762e-05,
      "loss": 0.5789,
      "step": 171
    },
    {
      "epoch": 0.44574020084224164,
      "grad_norm": 2.4375,
      "learning_rate": 1.4138634230844242e-05,
      "loss": 0.5693,
      "step": 172
    },
    {
      "epoch": 0.4483317136378361,
      "grad_norm": 2.296875,
      "learning_rate": 1.4053082922702183e-05,
      "loss": 0.5496,
      "step": 173
    },
    {
      "epoch": 0.4509232264334305,
      "grad_norm": 2.21875,
      "learning_rate": 1.3967175169633537e-05,
      "loss": 0.5362,
      "step": 174
    },
    {
      "epoch": 0.45351473922902497,
      "grad_norm": 2.1875,
      "learning_rate": 1.3880918526722497e-05,
      "loss": 0.5739,
      "step": 175
    },
    {
      "epoch": 0.45610625202461935,
      "grad_norm": 2.421875,
      "learning_rate": 1.3794320579736084e-05,
      "loss": 0.5493,
      "step": 176
    },
    {
      "epoch": 0.4586977648202138,
      "grad_norm": 2.59375,
      "learning_rate": 1.3707388944457007e-05,
      "loss": 0.5665,
      "step": 177
    },
    {
      "epoch": 0.46128927761580824,
      "grad_norm": 2.125,
      "learning_rate": 1.3620131266013912e-05,
      "loss": 0.5557,
      "step": 178
    },
    {
      "epoch": 0.4638807904114027,
      "grad_norm": 2.34375,
      "learning_rate": 1.3532555218209037e-05,
      "loss": 0.5402,
      "step": 179
    },
    {
      "epoch": 0.46647230320699706,
      "grad_norm": 2.375,
      "learning_rate": 1.344466850284333e-05,
      "loss": 0.5625,
      "step": 180
    },
    {
      "epoch": 0.46647230320699706,
      "eval_loss": 0.5502737164497375,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.6233,
      "eval_samples_per_second": 105.713,
      "eval_steps_per_second": 13.239,
      "step": 180
    },
    {
      "epoch": 0.4690638160025915,
      "grad_norm": 2.34375,
      "learning_rate": 1.335647884903915e-05,
      "loss": 0.5492,
      "step": 181
    },
    {
      "epoch": 0.47165532879818595,
      "grad_norm": 2.390625,
      "learning_rate": 1.3267994012560505e-05,
      "loss": 0.5493,
      "step": 182
    },
    {
      "epoch": 0.4742468415937804,
      "grad_norm": 2.453125,
      "learning_rate": 1.3179221775131005e-05,
      "loss": 0.5508,
      "step": 183
    },
    {
      "epoch": 0.4768383543893748,
      "grad_norm": 3.34375,
      "learning_rate": 1.3090169943749475e-05,
      "loss": 0.5427,
      "step": 184
    },
    {
      "epoch": 0.4794298671849692,
      "grad_norm": 2.078125,
      "learning_rate": 1.300084635000341e-05,
      "loss": 0.568,
      "step": 185
    },
    {
      "epoch": 0.48202137998056366,
      "grad_norm": 2.15625,
      "learning_rate": 1.2911258849380199e-05,
      "loss": 0.5478,
      "step": 186
    },
    {
      "epoch": 0.4846128927761581,
      "grad_norm": 2.15625,
      "learning_rate": 1.2821415320576309e-05,
      "loss": 0.5582,
      "step": 187
    },
    {
      "epoch": 0.4872044055717525,
      "grad_norm": 3.0,
      "learning_rate": 1.273132366480438e-05,
      "loss": 0.5368,
      "step": 188
    },
    {
      "epoch": 0.4897959183673469,
      "grad_norm": 2.71875,
      "learning_rate": 1.2640991805098369e-05,
      "loss": 0.5608,
      "step": 189
    },
    {
      "epoch": 0.49238743116294137,
      "grad_norm": 2.203125,
      "learning_rate": 1.2550427685616767e-05,
      "loss": 0.5482,
      "step": 190
    },
    {
      "epoch": 0.49238743116294137,
      "eval_loss": 0.547302782535553,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.5429,
      "eval_samples_per_second": 106.059,
      "eval_steps_per_second": 13.283,
      "step": 190
    },
    {
      "epoch": 0.4949789439585358,
      "grad_norm": 2.640625,
      "learning_rate": 1.2459639270943944e-05,
      "loss": 0.5508,
      "step": 191
    },
    {
      "epoch": 0.4975704567541302,
      "grad_norm": 2.65625,
      "learning_rate": 1.2368634545389732e-05,
      "loss": 0.5402,
      "step": 192
    },
    {
      "epoch": 0.5001619695497247,
      "grad_norm": 2.25,
      "learning_rate": 1.2277421512287227e-05,
      "loss": 0.5313,
      "step": 193
    },
    {
      "epoch": 0.502753482345319,
      "grad_norm": 2.296875,
      "learning_rate": 1.2186008193288963e-05,
      "loss": 0.5535,
      "step": 194
    },
    {
      "epoch": 0.5053449951409135,
      "grad_norm": 2.234375,
      "learning_rate": 1.2094402627661447e-05,
      "loss": 0.5375,
      "step": 195
    },
    {
      "epoch": 0.5079365079365079,
      "grad_norm": 2.375,
      "learning_rate": 1.2002612871578143e-05,
      "loss": 0.5564,
      "step": 196
    },
    {
      "epoch": 0.5105280207321024,
      "grad_norm": 2.5,
      "learning_rate": 1.1910646997411002e-05,
      "loss": 0.5459,
      "step": 197
    },
    {
      "epoch": 0.5131195335276968,
      "grad_norm": 2.3125,
      "learning_rate": 1.1818513093020514e-05,
      "loss": 0.5545,
      "step": 198
    },
    {
      "epoch": 0.5157110463232912,
      "grad_norm": 2.21875,
      "learning_rate": 1.172621926104446e-05,
      "loss": 0.535,
      "step": 199
    },
    {
      "epoch": 0.5183025591188857,
      "grad_norm": 2.234375,
      "learning_rate": 1.1633773618185302e-05,
      "loss": 0.5469,
      "step": 200
    },
    {
      "epoch": 0.5183025591188857,
      "eval_loss": 0.545219898223877,
      "eval_model_preparation_time": 0.0003,
      "eval_runtime": 24.4828,
      "eval_samples_per_second": 106.319,
      "eval_steps_per_second": 13.315,
      "step": 200
    }
  ],
  "logging_steps": 1,
  "max_steps": 385,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.5651501867008e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}