{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 441,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034013605442176874,
      "grad_norm": 2.7028610706329346,
      "learning_rate": 4.998414279387743e-05,
      "loss": 6.0793,
      "num_input_tokens_seen": 3168,
      "step": 5
    },
    {
      "epoch": 0.06802721088435375,
      "grad_norm": 2.967193603515625,
      "learning_rate": 4.9936591291588586e-05,
      "loss": 5.4017,
      "num_input_tokens_seen": 6544,
      "step": 10
    },
    {
      "epoch": 0.10204081632653061,
      "grad_norm": 1.1446479558944702,
      "learning_rate": 4.985740581585134e-05,
      "loss": 4.3102,
      "num_input_tokens_seen": 10464,
      "step": 15
    },
    {
      "epoch": 0.1360544217687075,
      "grad_norm": 1.7880395650863647,
      "learning_rate": 4.9746686819498546e-05,
      "loss": 4.232,
      "num_input_tokens_seen": 13296,
      "step": 20
    },
    {
      "epoch": 0.17006802721088435,
      "grad_norm": 2.237711191177368,
      "learning_rate": 4.960457475804594e-05,
      "loss": 3.9065,
      "num_input_tokens_seen": 16320,
      "step": 25
    },
    {
      "epoch": 0.20408163265306123,
      "grad_norm": 1.7026973962783813,
      "learning_rate": 4.94312499115136e-05,
      "loss": 3.8348,
      "num_input_tokens_seen": 19504,
      "step": 30
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.4949020147323608,
      "learning_rate": 4.922693215572695e-05,
      "loss": 3.5761,
      "num_input_tokens_seen": 22704,
      "step": 35
    },
    {
      "epoch": 0.272108843537415,
      "grad_norm": 2.234846830368042,
      "learning_rate": 4.899188068338743e-05,
      "loss": 3.7531,
      "num_input_tokens_seen": 25728,
      "step": 40
    },
    {
      "epoch": 0.30612244897959184,
      "grad_norm": 1.7678470611572266,
      "learning_rate": 4.8726393675266716e-05,
      "loss": 3.5748,
      "num_input_tokens_seen": 29024,
      "step": 45
    },
    {
      "epoch": 0.3401360544217687,
      "grad_norm": 1.8059829473495483,
      "learning_rate": 4.84308079219417e-05,
      "loss": 3.772,
      "num_input_tokens_seen": 32464,
      "step": 50
    },
    {
      "epoch": 0.3741496598639456,
      "grad_norm": 2.300635576248169,
      "learning_rate": 4.810549839654973e-05,
      "loss": 3.807,
      "num_input_tokens_seen": 35424,
      "step": 55
    },
    {
      "epoch": 0.40816326530612246,
      "grad_norm": 2.1998870372772217,
      "learning_rate": 4.7750877779106666e-05,
      "loss": 3.5115,
      "num_input_tokens_seen": 38208,
      "step": 60
    },
    {
      "epoch": 0.4421768707482993,
      "grad_norm": 1.6165343523025513,
      "learning_rate": 4.736739593299058e-05,
      "loss": 3.7613,
      "num_input_tokens_seen": 41280,
      "step": 65
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 2.3959059715270996,
      "learning_rate": 4.6955539334255716e-05,
      "loss": 3.6662,
      "num_input_tokens_seen": 44144,
      "step": 70
    },
    {
      "epoch": 0.5102040816326531,
      "grad_norm": 1.5641539096832275,
      "learning_rate": 4.651583045450041e-05,
      "loss": 3.627,
      "num_input_tokens_seen": 47120,
      "step": 75
    },
    {
      "epoch": 0.54421768707483,
      "grad_norm": 1.9732143878936768,
      "learning_rate": 4.604882709807187e-05,
      "loss": 3.6502,
      "num_input_tokens_seen": 50272,
      "step": 80
    },
    {
      "epoch": 0.5782312925170068,
      "grad_norm": 2.6501049995422363,
      "learning_rate": 4.5555121694448735e-05,
      "loss": 3.7163,
      "num_input_tokens_seen": 53056,
      "step": 85
    },
    {
      "epoch": 0.6122448979591837,
      "grad_norm": 1.9555385112762451,
      "learning_rate": 4.503534054669892e-05,
      "loss": 3.6891,
      "num_input_tokens_seen": 55968,
      "step": 90
    },
    {
      "epoch": 0.6462585034013606,
      "grad_norm": 1.728500485420227,
      "learning_rate": 4.44901430369663e-05,
      "loss": 3.6063,
      "num_input_tokens_seen": 58944,
      "step": 95
    },
    {
      "epoch": 0.6802721088435374,
      "grad_norm": 1.6137477159500122,
      "learning_rate": 4.392022078999405e-05,
      "loss": 3.5177,
      "num_input_tokens_seen": 61872,
      "step": 100
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 1.7164677381515503,
      "learning_rate": 4.332629679574566e-05,
      "loss": 3.376,
      "num_input_tokens_seen": 64704,
      "step": 105
    },
    {
      "epoch": 0.7482993197278912,
      "grad_norm": 1.568602442741394,
      "learning_rate": 4.270912449223699e-05,
      "loss": 3.4565,
      "num_input_tokens_seen": 67776,
      "step": 110
    },
    {
      "epoch": 0.782312925170068,
      "grad_norm": 2.5001213550567627,
      "learning_rate": 4.206948680974242e-05,
      "loss": 3.6683,
      "num_input_tokens_seen": 70784,
      "step": 115
    },
    {
      "epoch": 0.8163265306122449,
      "grad_norm": 2.0534141063690186,
      "learning_rate": 4.140819517758795e-05,
      "loss": 3.5794,
      "num_input_tokens_seen": 74336,
      "step": 120
    },
    {
      "epoch": 0.8503401360544217,
      "grad_norm": 2.1421139240264893,
      "learning_rate": 4.072608849479106e-05,
      "loss": 3.6307,
      "num_input_tokens_seen": 77232,
      "step": 125
    },
    {
      "epoch": 0.8843537414965986,
      "grad_norm": 1.939579963684082,
      "learning_rate": 4.002403206585307e-05,
      "loss": 3.5575,
      "num_input_tokens_seen": 80352,
      "step": 130
    },
    {
      "epoch": 0.9183673469387755,
      "grad_norm": 2.4437503814697266,
      "learning_rate": 3.9302916503054246e-05,
      "loss": 3.5487,
      "num_input_tokens_seen": 84016,
      "step": 135
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 2.416694164276123,
      "learning_rate": 3.856365659664399e-05,
      "loss": 3.6761,
      "num_input_tokens_seen": 87120,
      "step": 140
    },
    {
      "epoch": 0.9863945578231292,
      "grad_norm": 2.3587541580200195,
      "learning_rate": 3.780719015435943e-05,
      "loss": 3.1846,
      "num_input_tokens_seen": 90544,
      "step": 145
    },
    {
      "epoch": 1.0204081632653061,
      "grad_norm": 2.34908390045166,
      "learning_rate": 3.703447681174458e-05,
      "loss": 3.2783,
      "num_input_tokens_seen": 94712,
      "step": 150
    },
    {
      "epoch": 1.054421768707483,
      "grad_norm": 2.1918578147888184,
      "learning_rate": 3.624649681477923e-05,
      "loss": 3.494,
      "num_input_tokens_seen": 97912,
      "step": 155
    },
    {
      "epoch": 1.08843537414966,
      "grad_norm": 2.6867949962615967,
      "learning_rate": 3.544424977636198e-05,
      "loss": 3.2551,
      "num_input_tokens_seen": 100696,
      "step": 160
    },
    {
      "epoch": 1.1224489795918366,
      "grad_norm": 3.030991315841675,
      "learning_rate": 3.4628753408224765e-05,
      "loss": 3.4821,
      "num_input_tokens_seen": 104552,
      "step": 165
    },
    {
      "epoch": 1.1564625850340136,
      "grad_norm": 2.9311370849609375,
      "learning_rate": 3.3801042229887756e-05,
      "loss": 3.4083,
      "num_input_tokens_seen": 107800,
      "step": 170
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 2.682126760482788,
      "learning_rate": 3.2962166256292113e-05,
      "loss": 3.4593,
      "num_input_tokens_seen": 110840,
      "step": 175
    },
    {
      "epoch": 1.2244897959183674,
      "grad_norm": 2.8780510425567627,
      "learning_rate": 3.211318966577581e-05,
      "loss": 3.5256,
      "num_input_tokens_seen": 113640,
      "step": 180
    },
    {
      "epoch": 1.2585034013605443,
      "grad_norm": 2.4468441009521484,
      "learning_rate": 3.1255189450081977e-05,
      "loss": 2.9337,
      "num_input_tokens_seen": 117752,
      "step": 185
    },
    {
      "epoch": 1.2925170068027212,
      "grad_norm": 2.369248628616333,
      "learning_rate": 3.0389254048112493e-05,
      "loss": 3.2217,
      "num_input_tokens_seen": 121512,
      "step": 190
    },
    {
      "epoch": 1.3265306122448979,
      "grad_norm": 1.5555424690246582,
      "learning_rate": 2.9516481965159975e-05,
      "loss": 3.4546,
      "num_input_tokens_seen": 124840,
      "step": 195
    },
    {
      "epoch": 1.3605442176870748,
      "grad_norm": 2.8310885429382324,
      "learning_rate": 2.863798037936983e-05,
      "loss": 3.559,
      "num_input_tokens_seen": 127960,
      "step": 200
    },
    {
      "epoch": 1.3945578231292517,
      "grad_norm": 2.4837112426757812,
      "learning_rate": 2.775486373720003e-05,
      "loss": 3.2782,
      "num_input_tokens_seen": 130968,
      "step": 205
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 2.7569165229797363,
      "learning_rate": 2.686825233966061e-05,
      "loss": 3.4279,
      "num_input_tokens_seen": 133736,
      "step": 210
    },
    {
      "epoch": 1.4625850340136055,
      "grad_norm": 2.901097297668457,
      "learning_rate": 2.597927092112607e-05,
      "loss": 3.3297,
      "num_input_tokens_seen": 136552,
      "step": 215
    },
    {
      "epoch": 1.4965986394557822,
      "grad_norm": 2.221858263015747,
      "learning_rate": 2.5089047222523838e-05,
      "loss": 3.2559,
      "num_input_tokens_seen": 139832,
      "step": 220
    },
    {
      "epoch": 1.5306122448979593,
      "grad_norm": 2.864755153656006,
      "learning_rate": 2.419871056070862e-05,
      "loss": 3.1332,
      "num_input_tokens_seen": 142840,
      "step": 225
    },
    {
      "epoch": 1.564625850340136,
      "grad_norm": 2.6603639125823975,
      "learning_rate": 2.3309390395837633e-05,
      "loss": 3.4912,
      "num_input_tokens_seen": 145704,
      "step": 230
    },
    {
      "epoch": 1.598639455782313,
      "grad_norm": 1.888742446899414,
      "learning_rate": 2.2422214898563916e-05,
      "loss": 3.4511,
      "num_input_tokens_seen": 148632,
      "step": 235
    },
    {
      "epoch": 1.6326530612244898,
      "grad_norm": 2.04915714263916,
      "learning_rate": 2.1538309518865646e-05,
      "loss": 3.4876,
      "num_input_tokens_seen": 151608,
      "step": 240
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 2.1959643363952637,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 3.474,
      "num_input_tokens_seen": 154936,
      "step": 245
    },
    {
      "epoch": 1.7006802721088436,
      "grad_norm": 2.2664616107940674,
      "learning_rate": 1.9784788747679982e-05,
      "loss": 3.2019,
      "num_input_tokens_seen": 157912,
      "step": 250
    },
    {
      "epoch": 1.7346938775510203,
      "grad_norm": 2.486283540725708,
      "learning_rate": 1.8917397831417286e-05,
      "loss": 3.2353,
      "num_input_tokens_seen": 160536,
      "step": 255
    },
    {
      "epoch": 1.7687074829931972,
      "grad_norm": 2.9121577739715576,
      "learning_rate": 1.80577231612625e-05,
      "loss": 3.3723,
      "num_input_tokens_seen": 163976,
      "step": 260
    },
    {
      "epoch": 1.8027210884353742,
      "grad_norm": 3.1636898517608643,
      "learning_rate": 1.720685530029105e-05,
      "loss": 3.3386,
      "num_input_tokens_seen": 167144,
      "step": 265
    },
    {
      "epoch": 1.836734693877551,
      "grad_norm": 3.5455474853515625,
      "learning_rate": 1.6365873639467315e-05,
      "loss": 3.4695,
      "num_input_tokens_seen": 169752,
      "step": 270
    },
    {
      "epoch": 1.870748299319728,
      "grad_norm": 2.9391326904296875,
      "learning_rate": 1.553584502835456e-05,
      "loss": 3.0469,
      "num_input_tokens_seen": 173416,
      "step": 275
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 2.9568731784820557,
      "learning_rate": 1.4717822421734718e-05,
      "loss": 3.3184,
      "num_input_tokens_seen": 176392,
      "step": 280
    },
    {
      "epoch": 1.9387755102040818,
      "grad_norm": 3.0478389263153076,
      "learning_rate": 1.3912843543854664e-05,
      "loss": 3.3918,
      "num_input_tokens_seen": 179272,
      "step": 285
    },
    {
      "epoch": 1.9727891156462585,
      "grad_norm": 2.8810529708862305,
      "learning_rate": 1.3121929571993685e-05,
      "loss": 3.5476,
      "num_input_tokens_seen": 182616,
      "step": 290
    },
    {
      "epoch": 2.006802721088435,
      "grad_norm": 2.8993630409240723,
      "learning_rate": 1.2346083841021928e-05,
      "loss": 3.3684,
      "num_input_tokens_seen": 185424,
      "step": 295
    },
    {
      "epoch": 2.0408163265306123,
      "grad_norm": 1.4063067436218262,
      "learning_rate": 1.158629057059343e-05,
      "loss": 3.2909,
      "num_input_tokens_seen": 189040,
      "step": 300
    },
    {
      "epoch": 2.074829931972789,
      "grad_norm": 4.071662425994873,
      "learning_rate": 1.084351361658816e-05,
      "loss": 3.2623,
      "num_input_tokens_seen": 191856,
      "step": 305
    },
    {
      "epoch": 2.108843537414966,
      "grad_norm": 3.5538320541381836,
      "learning_rate": 1.0118695248387141e-05,
      "loss": 3.3487,
      "num_input_tokens_seen": 194720,
      "step": 310
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 2.685102939605713,
      "learning_rate": 9.412754953531663e-06,
      "loss": 3.2409,
      "num_input_tokens_seen": 197808,
      "step": 315
    },
    {
      "epoch": 2.17687074829932,
      "grad_norm": 3.332947015762329,
      "learning_rate": 8.726588271282978e-06,
      "loss": 3.2031,
      "num_input_tokens_seen": 201040,
      "step": 320
    },
    {
      "epoch": 2.2108843537414966,
      "grad_norm": 3.082350492477417,
      "learning_rate": 8.061065656562269e-06,
      "loss": 2.9128,
      "num_input_tokens_seen": 204944,
      "step": 325
    },
    {
      "epoch": 2.2448979591836733,
      "grad_norm": 4.072040557861328,
      "learning_rate": 7.417031375712008e-06,
      "loss": 3.4445,
      "num_input_tokens_seen": 207712,
      "step": 330
    },
    {
      "epoch": 2.2789115646258504,
      "grad_norm": 3.686593770980835,
      "learning_rate": 6.795302435479523e-06,
      "loss": 3.0001,
      "num_input_tokens_seen": 210576,
      "step": 335
    },
    {
      "epoch": 2.312925170068027,
      "grad_norm": 2.2774229049682617,
      "learning_rate": 6.196667546581405e-06,
      "loss": 3.3204,
      "num_input_tokens_seen": 213712,
      "step": 340
    },
    {
      "epoch": 2.3469387755102042,
      "grad_norm": 3.1405270099639893,
      "learning_rate": 5.621886123163708e-06,
      "loss": 3.1907,
      "num_input_tokens_seen": 216464,
      "step": 345
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 2.792036771774292,
      "learning_rate": 5.071687319426946e-06,
      "loss": 3.298,
      "num_input_tokens_seen": 219616,
      "step": 350
    },
    {
      "epoch": 2.4149659863945576,
      "grad_norm": 3.187742233276367,
      "learning_rate": 4.5467691046382435e-06,
      "loss": 3.2584,
      "num_input_tokens_seen": 222848,
      "step": 355
    },
    {
      "epoch": 2.4489795918367347,
      "grad_norm": 3.170606851577759,
      "learning_rate": 4.047797377703985e-06,
      "loss": 3.3844,
      "num_input_tokens_seen": 225568,
      "step": 360
    },
    {
      "epoch": 2.4829931972789114,
      "grad_norm": 3.8285155296325684,
      "learning_rate": 3.5754051224260176e-06,
      "loss": 3.3962,
      "num_input_tokens_seen": 228832,
      "step": 365
    },
    {
      "epoch": 2.5170068027210886,
      "grad_norm": 3.4845287799835205,
      "learning_rate": 3.130191604513352e-06,
      "loss": 3.1933,
      "num_input_tokens_seen": 231968,
      "step": 370
    },
    {
      "epoch": 2.5510204081632653,
      "grad_norm": 3.385293960571289,
      "learning_rate": 2.7127216113677635e-06,
      "loss": 3.1452,
      "num_input_tokens_seen": 235840,
      "step": 375
    },
    {
      "epoch": 2.5850340136054424,
      "grad_norm": 4.231153964996338,
      "learning_rate": 2.323524735607749e-06,
      "loss": 3.3513,
      "num_input_tokens_seen": 238768,
      "step": 380
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 2.916943311691284,
      "learning_rate": 1.9630947032398067e-06,
      "loss": 2.9965,
      "num_input_tokens_seen": 242240,
      "step": 385
    },
    {
      "epoch": 2.6530612244897958,
      "grad_norm": 2.958503484725952,
      "learning_rate": 1.6318887473292243e-06,
      "loss": 3.1061,
      "num_input_tokens_seen": 245248,
      "step": 390
    },
    {
      "epoch": 2.687074829931973,
      "grad_norm": 2.5356791019439697,
      "learning_rate": 1.3303270279649477e-06,
      "loss": 3.0728,
      "num_input_tokens_seen": 248416,
      "step": 395
    },
    {
      "epoch": 2.7210884353741496,
      "grad_norm": 3.929884672164917,
      "learning_rate": 1.0587920992543853e-06,
      "loss": 3.1985,
      "num_input_tokens_seen": 251712,
      "step": 400
    },
    {
      "epoch": 2.7551020408163263,
      "grad_norm": 3.698723077774048,
      "learning_rate": 8.176284240242638e-07,
      "loss": 3.3142,
      "num_input_tokens_seen": 254496,
      "step": 405
    },
    {
      "epoch": 2.7891156462585034,
      "grad_norm": 3.604297637939453,
      "learning_rate": 6.071419368431779e-07,
      "loss": 3.4238,
      "num_input_tokens_seen": 257760,
      "step": 410
    },
    {
      "epoch": 2.8231292517006805,
      "grad_norm": 4.10955810546875,
      "learning_rate": 4.2759965592018283e-07,
      "loss": 3.3226,
      "num_input_tokens_seen": 260784,
      "step": 415
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 3.1334779262542725,
      "learning_rate": 2.7922934437178695e-07,
      "loss": 3.2627,
      "num_input_tokens_seen": 263792,
      "step": 420
    },
    {
      "epoch": 2.891156462585034,
      "grad_norm": 3.3782756328582764,
      "learning_rate": 1.6221922128700217e-07,
      "loss": 3.2338,
      "num_input_tokens_seen": 266784,
      "step": 425
    },
    {
      "epoch": 2.925170068027211,
      "grad_norm": 2.9588587284088135,
      "learning_rate": 7.671772295704815e-08,
      "loss": 3.1991,
      "num_input_tokens_seen": 269936,
      "step": 430
    },
    {
      "epoch": 2.9591836734693877,
      "grad_norm": 3.1428213119506836,
      "learning_rate": 2.2833314572542895e-08,
      "loss": 3.3015,
      "num_input_tokens_seen": 272704,
      "step": 435
    },
    {
      "epoch": 2.9931972789115644,
      "grad_norm": 4.047586917877197,
      "learning_rate": 6.343526271379574e-10,
      "loss": 3.4811,
      "num_input_tokens_seen": 276208,
      "step": 440
    },
    {
      "epoch": 3.0,
      "num_input_tokens_seen": 276856,
      "step": 441,
      "total_flos": 2191990201638912.0,
      "train_loss": 3.4709230188339477,
      "train_runtime": 2415.5729,
      "train_samples_per_second": 2.92,
      "train_steps_per_second": 0.183
    }
  ],
  "logging_steps": 5,
  "max_steps": 441,
  "num_input_tokens_seen": 276856,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2191990201638912.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}