{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.971724787935909,
  "eval_steps": 500,
  "global_step": 792,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03770028275212064,
      "grad_norm": 3.988708734512329,
      "learning_rate": 4.9995083170283816e-05,
      "loss": 4.6192,
      "num_input_tokens_seen": 50400,
      "step": 5
    },
    {
      "epoch": 0.07540056550424128,
      "grad_norm": 2.142688512802124,
      "learning_rate": 4.998033461515242e-05,
      "loss": 3.9149,
      "num_input_tokens_seen": 104016,
      "step": 10
    },
    {
      "epoch": 0.11310084825636192,
      "grad_norm": 1.5928359031677246,
      "learning_rate": 4.9955760135896534e-05,
      "loss": 3.6912,
      "num_input_tokens_seen": 155584,
      "step": 15
    },
    {
      "epoch": 0.15080113100848255,
      "grad_norm": 1.5493167638778687,
      "learning_rate": 4.992136939879856e-05,
      "loss": 3.5556,
      "num_input_tokens_seen": 202672,
      "step": 20
    },
    {
      "epoch": 0.1885014137606032,
      "grad_norm": 1.7764347791671753,
      "learning_rate": 4.9877175931330346e-05,
      "loss": 3.4256,
      "num_input_tokens_seen": 254800,
      "step": 25
    },
    {
      "epoch": 0.22620169651272384,
      "grad_norm": 1.2482728958129883,
      "learning_rate": 4.982319711683221e-05,
      "loss": 3.3128,
      "num_input_tokens_seen": 306352,
      "step": 30
    },
    {
      "epoch": 0.2639019792648445,
      "grad_norm": 1.2829065322875977,
      "learning_rate": 4.975945418767529e-05,
      "loss": 3.2688,
      "num_input_tokens_seen": 356352,
      "step": 35
    },
    {
      "epoch": 0.3016022620169651,
      "grad_norm": 1.513293743133545,
      "learning_rate": 4.968597221690986e-05,
      "loss": 3.297,
      "num_input_tokens_seen": 406672,
      "step": 40
    },
    {
      "epoch": 0.3393025447690858,
      "grad_norm": 1.883090853691101,
      "learning_rate": 4.96027801084029e-05,
      "loss": 3.232,
      "num_input_tokens_seen": 456160,
      "step": 45
    },
    {
      "epoch": 0.3770028275212064,
      "grad_norm": 1.402272343635559,
      "learning_rate": 4.950991058546893e-05,
      "loss": 3.267,
      "num_input_tokens_seen": 509680,
      "step": 50
    },
    {
      "epoch": 0.41470311027332707,
      "grad_norm": 1.5488755702972412,
      "learning_rate": 4.940740017799833e-05,
      "loss": 3.2148,
      "num_input_tokens_seen": 559968,
      "step": 55
    },
    {
      "epoch": 0.4524033930254477,
      "grad_norm": 1.507287859916687,
      "learning_rate": 4.929528920808854e-05,
      "loss": 3.1403,
      "num_input_tokens_seen": 610000,
      "step": 60
    },
    {
      "epoch": 0.49010367577756836,
      "grad_norm": 1.9119170904159546,
      "learning_rate": 4.917362177418342e-05,
      "loss": 3.1515,
      "num_input_tokens_seen": 661280,
      "step": 65
    },
    {
      "epoch": 0.527803958529689,
      "grad_norm": 1.7253235578536987,
      "learning_rate": 4.904244573372733e-05,
      "loss": 3.1468,
      "num_input_tokens_seen": 713264,
      "step": 70
    },
    {
      "epoch": 0.5655042412818096,
      "grad_norm": 1.7201606035232544,
      "learning_rate": 4.8901812684340564e-05,
      "loss": 3.196,
      "num_input_tokens_seen": 762576,
      "step": 75
    },
    {
      "epoch": 0.6032045240339302,
      "grad_norm": 1.6135213375091553,
      "learning_rate": 4.8751777943523634e-05,
      "loss": 3.0593,
      "num_input_tokens_seen": 813392,
      "step": 80
    },
    {
      "epoch": 0.6409048067860509,
      "grad_norm": 1.7381868362426758,
      "learning_rate": 4.8592400526898314e-05,
      "loss": 3.0676,
      "num_input_tokens_seen": 860608,
      "step": 85
    },
    {
      "epoch": 0.6786050895381716,
      "grad_norm": 1.6142843961715698,
      "learning_rate": 4.842374312499405e-05,
      "loss": 3.1061,
      "num_input_tokens_seen": 909104,
      "step": 90
    },
    {
      "epoch": 0.7163053722902922,
      "grad_norm": 2.0389633178710938,
      "learning_rate": 4.824587207858888e-05,
      "loss": 2.9847,
      "num_input_tokens_seen": 959600,
      "step": 95
    },
    {
      "epoch": 0.7540056550424128,
      "grad_norm": 1.923561692237854,
      "learning_rate": 4.805885735261454e-05,
      "loss": 3.0289,
      "num_input_tokens_seen": 1013648,
      "step": 100
    },
    {
      "epoch": 0.7917059377945335,
      "grad_norm": 2.0325896739959717,
      "learning_rate": 4.786277250863599e-05,
      "loss": 2.9474,
      "num_input_tokens_seen": 1065120,
      "step": 105
    },
    {
      "epoch": 0.8294062205466541,
      "grad_norm": 1.6685590744018555,
      "learning_rate": 4.765769467591625e-05,
      "loss": 2.9713,
      "num_input_tokens_seen": 1119424,
      "step": 110
    },
    {
      "epoch": 0.8671065032987747,
      "grad_norm": 2.0325937271118164,
      "learning_rate": 4.744370452107789e-05,
      "loss": 3.0012,
      "num_input_tokens_seen": 1169888,
      "step": 115
    },
    {
      "epoch": 0.9048067860508954,
      "grad_norm": 1.7548010349273682,
      "learning_rate": 4.722088621637309e-05,
      "loss": 3.0399,
      "num_input_tokens_seen": 1218944,
      "step": 120
    },
    {
      "epoch": 0.942507068803016,
      "grad_norm": 1.6709191799163818,
      "learning_rate": 4.698932740657479e-05,
      "loss": 2.9156,
      "num_input_tokens_seen": 1269920,
      "step": 125
    },
    {
      "epoch": 0.9802073515551367,
      "grad_norm": 1.8369653224945068,
      "learning_rate": 4.6749119174501975e-05,
      "loss": 3.0288,
      "num_input_tokens_seen": 1315536,
      "step": 130
    },
    {
      "epoch": 1.0179076343072573,
      "grad_norm": 1.800703525543213,
      "learning_rate": 4.6500356005192514e-05,
      "loss": 2.8911,
      "num_input_tokens_seen": 1360736,
      "step": 135
    },
    {
      "epoch": 1.055607917059378,
      "grad_norm": 1.7134617567062378,
      "learning_rate": 4.6243135748737864e-05,
      "loss": 2.9148,
      "num_input_tokens_seen": 1409808,
      "step": 140
    },
    {
      "epoch": 1.0933081998114986,
      "grad_norm": 1.9385241270065308,
      "learning_rate": 4.597755958179406e-05,
      "loss": 2.868,
      "num_input_tokens_seen": 1460864,
      "step": 145
    },
    {
      "epoch": 1.1310084825636193,
      "grad_norm": 2.1658332347869873,
      "learning_rate": 4.570373196778427e-05,
      "loss": 2.7477,
      "num_input_tokens_seen": 1512640,
      "step": 150
    },
    {
      "epoch": 1.1687087653157398,
      "grad_norm": 2.239896774291992,
      "learning_rate": 4.5421760615808474e-05,
      "loss": 2.932,
      "num_input_tokens_seen": 1556048,
      "step": 155
    },
    {
      "epoch": 1.2064090480678604,
      "grad_norm": 2.0555717945098877,
      "learning_rate": 4.513175643827647e-05,
      "loss": 2.8219,
      "num_input_tokens_seen": 1607232,
      "step": 160
    },
    {
      "epoch": 1.244109330819981,
      "grad_norm": 2.0288779735565186,
      "learning_rate": 4.4833833507280884e-05,
      "loss": 2.8453,
      "num_input_tokens_seen": 1653520,
      "step": 165
    },
    {
      "epoch": 1.2818096135721018,
      "grad_norm": 1.9268651008605957,
      "learning_rate": 4.4528109009727336e-05,
      "loss": 2.7362,
      "num_input_tokens_seen": 1703568,
      "step": 170
    },
    {
      "epoch": 1.3195098963242224,
      "grad_norm": 2.413874387741089,
      "learning_rate": 4.42147032012394e-05,
      "loss": 2.9197,
      "num_input_tokens_seen": 1752944,
      "step": 175
    },
    {
      "epoch": 1.3572101790763431,
      "grad_norm": 2.2018630504608154,
      "learning_rate": 4.389373935885646e-05,
      "loss": 2.8897,
      "num_input_tokens_seen": 1805600,
      "step": 180
    },
    {
      "epoch": 1.3949104618284638,
      "grad_norm": 2.1807219982147217,
      "learning_rate": 4.356534373254316e-05,
      "loss": 2.7946,
      "num_input_tokens_seen": 1860688,
      "step": 185
    },
    {
      "epoch": 1.4326107445805842,
      "grad_norm": 2.2928526401519775,
      "learning_rate": 4.322964549552943e-05,
      "loss": 2.8149,
      "num_input_tokens_seen": 1913056,
      "step": 190
    },
    {
      "epoch": 1.4703110273327051,
      "grad_norm": 2.204533576965332,
      "learning_rate": 4.288677669350066e-05,
      "loss": 2.7811,
      "num_input_tokens_seen": 1961744,
      "step": 195
    },
    {
      "epoch": 1.5080113100848256,
      "grad_norm": 2.925762414932251,
      "learning_rate": 4.2536872192658036e-05,
      "loss": 2.8564,
      "num_input_tokens_seen": 2011248,
      "step": 200
    },
    {
      "epoch": 1.5457115928369463,
      "grad_norm": 2.398651599884033,
      "learning_rate": 4.218006962666934e-05,
      "loss": 2.7966,
      "num_input_tokens_seen": 2060640,
      "step": 205
    },
    {
      "epoch": 1.583411875589067,
      "grad_norm": 2.452263355255127,
      "learning_rate": 4.181650934253132e-05,
      "loss": 2.7674,
      "num_input_tokens_seen": 2113904,
      "step": 210
    },
    {
      "epoch": 1.6211121583411876,
      "grad_norm": 2.5911788940429688,
      "learning_rate": 4.144633434536467e-05,
      "loss": 2.7607,
      "num_input_tokens_seen": 2162608,
      "step": 215
    },
    {
      "epoch": 1.6588124410933083,
      "grad_norm": 2.648517608642578,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 2.8402,
      "num_input_tokens_seen": 2211616,
      "step": 220
    },
    {
      "epoch": 1.6965127238454287,
      "grad_norm": 2.6860735416412354,
      "learning_rate": 4.06867251845213e-05,
      "loss": 2.8019,
      "num_input_tokens_seen": 2269440,
      "step": 225
    },
    {
      "epoch": 1.7342130065975496,
      "grad_norm": 2.5891222953796387,
      "learning_rate": 4.0297589810356165e-05,
      "loss": 2.8311,
      "num_input_tokens_seen": 2321936,
      "step": 230
    },
    {
      "epoch": 1.77191328934967,
      "grad_norm": 2.695114850997925,
      "learning_rate": 3.9902437184657784e-05,
      "loss": 2.7626,
      "num_input_tokens_seen": 2376720,
      "step": 235
    },
    {
      "epoch": 1.8096135721017907,
      "grad_norm": 2.588127374649048,
      "learning_rate": 3.9501422739279956e-05,
      "loss": 2.8052,
      "num_input_tokens_seen": 2429952,
      "step": 240
    },
    {
      "epoch": 1.8473138548539114,
      "grad_norm": 2.1829710006713867,
      "learning_rate": 3.909470421180201e-05,
      "loss": 2.767,
      "num_input_tokens_seen": 2481488,
      "step": 245
    },
    {
      "epoch": 1.885014137606032,
      "grad_norm": 2.606924295425415,
      "learning_rate": 3.8682441583483314e-05,
      "loss": 2.7651,
      "num_input_tokens_seen": 2530768,
      "step": 250
    },
    {
      "epoch": 1.9227144203581528,
      "grad_norm": 2.3635494709014893,
      "learning_rate": 3.8264797016335205e-05,
      "loss": 2.8097,
      "num_input_tokens_seen": 2583088,
      "step": 255
    },
    {
      "epoch": 1.9604147031102732,
      "grad_norm": 2.560624361038208,
      "learning_rate": 3.7841934789335164e-05,
      "loss": 2.7269,
      "num_input_tokens_seen": 2631456,
      "step": 260
    },
    {
      "epoch": 1.998114985862394,
      "grad_norm": 2.7099437713623047,
      "learning_rate": 3.741402123380828e-05,
      "loss": 2.8586,
      "num_input_tokens_seen": 2684848,
      "step": 265
    },
    {
      "epoch": 2.0358152686145146,
      "grad_norm": 2.552143096923828,
      "learning_rate": 3.6981224668001424e-05,
      "loss": 2.6131,
      "num_input_tokens_seen": 2733408,
      "step": 270
    },
    {
      "epoch": 2.0735155513666355,
      "grad_norm": 2.9233176708221436,
      "learning_rate": 3.654371533087586e-05,
      "loss": 2.4891,
      "num_input_tokens_seen": 2786832,
      "step": 275
    },
    {
      "epoch": 2.111215834118756,
      "grad_norm": 2.7649636268615723,
      "learning_rate": 3.610166531514436e-05,
      "loss": 2.5783,
      "num_input_tokens_seen": 2828464,
      "step": 280
    },
    {
      "epoch": 2.1489161168708764,
      "grad_norm": 3.076122522354126,
      "learning_rate": 3.565524849957921e-05,
      "loss": 2.59,
      "num_input_tokens_seen": 2878192,
      "step": 285
    },
    {
      "epoch": 2.1866163996229973,
      "grad_norm": 3.242678642272949,
      "learning_rate": 3.520464048061758e-05,
      "loss": 2.5839,
      "num_input_tokens_seen": 2928304,
      "step": 290
    },
    {
      "epoch": 2.2243166823751177,
      "grad_norm": 3.139089584350586,
      "learning_rate": 3.47500185032913e-05,
      "loss": 2.567,
      "num_input_tokens_seen": 2978144,
      "step": 295
    },
    {
      "epoch": 2.2620169651272386,
      "grad_norm": 3.1967153549194336,
      "learning_rate": 3.4291561391508185e-05,
      "loss": 2.5694,
      "num_input_tokens_seen": 3028240,
      "step": 300
    },
    {
      "epoch": 2.299717247879359,
      "grad_norm": 3.1987555027008057,
      "learning_rate": 3.3829449477712324e-05,
      "loss": 2.4965,
      "num_input_tokens_seen": 3083328,
      "step": 305
    },
    {
      "epoch": 2.3374175306314795,
      "grad_norm": 3.4724180698394775,
      "learning_rate": 3.336386453195088e-05,
      "loss": 2.599,
      "num_input_tokens_seen": 3137072,
      "step": 310
    },
    {
      "epoch": 2.3751178133836004,
      "grad_norm": 3.381075143814087,
      "learning_rate": 3.2894989690375626e-05,
      "loss": 2.524,
      "num_input_tokens_seen": 3191136,
      "step": 315
    },
    {
      "epoch": 2.412818096135721,
      "grad_norm": 3.650747537612915,
      "learning_rate": 3.2423009383206876e-05,
      "loss": 2.5338,
      "num_input_tokens_seen": 3239952,
      "step": 320
    },
    {
      "epoch": 2.4505183788878417,
      "grad_norm": 3.3886971473693848,
      "learning_rate": 3.194810926218861e-05,
      "loss": 2.5096,
      "num_input_tokens_seen": 3291104,
      "step": 325
    },
    {
      "epoch": 2.488218661639962,
      "grad_norm": 3.415850877761841,
      "learning_rate": 3.147047612756302e-05,
      "loss": 2.473,
      "num_input_tokens_seen": 3340592,
      "step": 330
    },
    {
      "epoch": 2.525918944392083,
      "grad_norm": 3.513828754425049,
      "learning_rate": 3.099029785459328e-05,
      "loss": 2.5778,
      "num_input_tokens_seen": 3388224,
      "step": 335
    },
    {
      "epoch": 2.5636192271442035,
      "grad_norm": 3.49721360206604,
      "learning_rate": 3.0507763319663517e-05,
      "loss": 2.5684,
      "num_input_tokens_seen": 3440512,
      "step": 340
    },
    {
      "epoch": 2.6013195098963244,
      "grad_norm": 3.5137672424316406,
      "learning_rate": 3.002306232598497e-05,
      "loss": 2.4923,
      "num_input_tokens_seen": 3491744,
      "step": 345
    },
    {
      "epoch": 2.639019792648445,
      "grad_norm": 3.7216403484344482,
      "learning_rate": 2.9536385528937567e-05,
      "loss": 2.4633,
      "num_input_tokens_seen": 3542368,
      "step": 350
    },
    {
      "epoch": 2.6767200754005653,
      "grad_norm": 3.48529052734375,
      "learning_rate": 2.9047924361076345e-05,
      "loss": 2.5703,
      "num_input_tokens_seen": 3595360,
      "step": 355
    },
    {
      "epoch": 2.7144203581526862,
      "grad_norm": 3.4676520824432373,
      "learning_rate": 2.8557870956832132e-05,
      "loss": 2.4087,
      "num_input_tokens_seen": 3640912,
      "step": 360
    },
    {
      "epoch": 2.7521206409048067,
      "grad_norm": 4.316717147827148,
      "learning_rate": 2.8066418076936167e-05,
      "loss": 2.5007,
      "num_input_tokens_seen": 3690048,
      "step": 365
    },
    {
      "epoch": 2.7898209236569276,
      "grad_norm": 4.2354736328125,
      "learning_rate": 2.7573759032598366e-05,
      "loss": 2.5312,
      "num_input_tokens_seen": 3745104,
      "step": 370
    },
    {
      "epoch": 2.827521206409048,
      "grad_norm": 3.457280397415161,
      "learning_rate": 2.7080087609469062e-05,
      "loss": 2.5333,
      "num_input_tokens_seen": 3794160,
      "step": 375
    },
    {
      "epoch": 2.8652214891611685,
      "grad_norm": 3.417656183242798,
      "learning_rate": 2.6585597991414114e-05,
      "loss": 2.4185,
      "num_input_tokens_seen": 3846576,
      "step": 380
    },
    {
      "epoch": 2.9029217719132894,
      "grad_norm": 3.7148749828338623,
      "learning_rate": 2.6090484684133404e-05,
      "loss": 2.4913,
      "num_input_tokens_seen": 3891744,
      "step": 385
    },
    {
      "epoch": 2.9406220546654103,
      "grad_norm": 3.562427520751953,
      "learning_rate": 2.5594942438652688e-05,
      "loss": 2.5319,
      "num_input_tokens_seen": 3949568,
      "step": 390
    },
    {
      "epoch": 2.9783223374175307,
      "grad_norm": 4.2560505867004395,
      "learning_rate": 2.509916617471903e-05,
      "loss": 2.6441,
      "num_input_tokens_seen": 4002384,
      "step": 395
    },
    {
      "epoch": 3.016022620169651,
      "grad_norm": 3.349701166152954,
      "learning_rate": 2.46033509041298e-05,
      "loss": 2.3576,
      "num_input_tokens_seen": 4052688,
      "step": 400
    },
    {
      "epoch": 3.053722902921772,
      "grad_norm": 3.660886287689209,
      "learning_rate": 2.410769165402549e-05,
      "loss": 2.3032,
      "num_input_tokens_seen": 4107392,
      "step": 405
    },
    {
      "epoch": 3.0914231856738925,
      "grad_norm": 4.248249530792236,
      "learning_rate": 2.3612383390176503e-05,
      "loss": 2.2542,
      "num_input_tokens_seen": 4157984,
      "step": 410
    },
    {
      "epoch": 3.1291234684260134,
      "grad_norm": 4.340310096740723,
      "learning_rate": 2.3117620940294048e-05,
      "loss": 2.2882,
      "num_input_tokens_seen": 4213280,
      "step": 415
    },
    {
      "epoch": 3.166823751178134,
      "grad_norm": 4.137709617614746,
      "learning_rate": 2.2623598917395438e-05,
      "loss": 2.2314,
      "num_input_tokens_seen": 4265792,
      "step": 420
    },
    {
      "epoch": 3.2045240339302543,
      "grad_norm": 4.506406307220459,
      "learning_rate": 2.213051164325366e-05,
      "loss": 2.2679,
      "num_input_tokens_seen": 4310832,
      "step": 425
    },
    {
      "epoch": 3.242224316682375,
      "grad_norm": 4.44052791595459,
      "learning_rate": 2.1638553071961708e-05,
      "loss": 2.2521,
      "num_input_tokens_seen": 4353488,
      "step": 430
    },
    {
      "epoch": 3.2799245994344957,
      "grad_norm": 4.674520015716553,
      "learning_rate": 2.1147916713641367e-05,
      "loss": 2.2071,
      "num_input_tokens_seen": 4404384,
      "step": 435
    },
    {
      "epoch": 3.3176248821866166,
      "grad_norm": 4.979199409484863,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 2.2525,
      "num_input_tokens_seen": 4453232,
      "step": 440
    },
    {
      "epoch": 3.355325164938737,
      "grad_norm": 4.564790725708008,
      "learning_rate": 2.017138200005236e-05,
      "loss": 2.2431,
      "num_input_tokens_seen": 4508640,
      "step": 445
    },
    {
      "epoch": 3.3930254476908575,
      "grad_norm": 4.888641834259033,
      "learning_rate": 1.9685867761175584e-05,
      "loss": 2.3357,
      "num_input_tokens_seen": 4559360,
      "step": 450
    },
    {
      "epoch": 3.4307257304429783,
      "grad_norm": 4.425845623016357,
      "learning_rate": 1.9202443816963425e-05,
      "loss": 2.2875,
      "num_input_tokens_seen": 4609584,
      "step": 455
    },
    {
      "epoch": 3.468426013195099,
      "grad_norm": 5.38726282119751,
      "learning_rate": 1.872130032047302e-05,
      "loss": 2.2136,
      "num_input_tokens_seen": 4665472,
      "step": 460
    },
    {
      "epoch": 3.5061262959472197,
      "grad_norm": 4.473924160003662,
      "learning_rate": 1.824262652775568e-05,
      "loss": 2.294,
      "num_input_tokens_seen": 4719360,
      "step": 465
    },
    {
      "epoch": 3.54382657869934,
      "grad_norm": 5.171916484832764,
      "learning_rate": 1.7766610723413684e-05,
      "loss": 2.2146,
      "num_input_tokens_seen": 4771504,
      "step": 470
    },
    {
      "epoch": 3.581526861451461,
      "grad_norm": 5.492386817932129,
      "learning_rate": 1.7293440146539196e-05,
      "loss": 2.3166,
      "num_input_tokens_seen": 4820432,
      "step": 475
    },
    {
      "epoch": 3.6192271442035815,
      "grad_norm": 4.300539493560791,
      "learning_rate": 1.682330091706446e-05,
      "loss": 2.2775,
      "num_input_tokens_seen": 4877984,
      "step": 480
    },
    {
      "epoch": 3.6569274269557024,
      "grad_norm": 5.470084190368652,
      "learning_rate": 1.6356377962552238e-05,
      "loss": 2.2442,
      "num_input_tokens_seen": 4927712,
      "step": 485
    },
    {
      "epoch": 3.694627709707823,
      "grad_norm": 5.457830429077148,
      "learning_rate": 1.589285494545514e-05,
      "loss": 2.2499,
      "num_input_tokens_seen": 4979520,
      "step": 490
    },
    {
      "epoch": 3.7323279924599433,
      "grad_norm": 4.851473808288574,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 2.214,
      "num_input_tokens_seen": 5030720,
      "step": 495
    },
    {
      "epoch": 3.770028275212064,
      "grad_norm": 4.645096302032471,
      "learning_rate": 1.4976736614834664e-05,
      "loss": 2.1646,
      "num_input_tokens_seen": 5081376,
      "step": 500
    },
    {
      "epoch": 3.8077285579641846,
      "grad_norm": 5.5402512550354,
      "learning_rate": 1.4524501653137787e-05,
      "loss": 2.3151,
      "num_input_tokens_seen": 5127888,
      "step": 505
    },
    {
      "epoch": 3.8454288407163055,
      "grad_norm": 4.753649711608887,
      "learning_rate": 1.4076387190766017e-05,
      "loss": 2.2602,
      "num_input_tokens_seen": 5178720,
      "step": 510
    },
    {
      "epoch": 3.883129123468426,
      "grad_norm": 5.488243579864502,
      "learning_rate": 1.363256949191972e-05,
      "loss": 2.1839,
      "num_input_tokens_seen": 5227120,
      "step": 515
    },
    {
      "epoch": 3.9208294062205464,
      "grad_norm": 5.427800178527832,
      "learning_rate": 1.3193223130682936e-05,
      "loss": 2.2833,
      "num_input_tokens_seen": 5275760,
      "step": 520
    },
    {
      "epoch": 3.9585296889726673,
      "grad_norm": 4.901040077209473,
      "learning_rate": 1.2758520922355226e-05,
      "loss": 2.1802,
      "num_input_tokens_seen": 5319632,
      "step": 525
    },
    {
      "epoch": 3.9962299717247878,
      "grad_norm": 4.977085590362549,
      "learning_rate": 1.2328633855475429e-05,
      "loss": 2.2383,
      "num_input_tokens_seen": 5369936,
      "step": 530
    },
    {
      "epoch": 4.033930254476909,
      "grad_norm": 4.724318027496338,
      "learning_rate": 1.1903731024563966e-05,
      "loss": 2.007,
      "num_input_tokens_seen": 5421440,
      "step": 535
    },
    {
      "epoch": 4.071630537229029,
      "grad_norm": 5.148896217346191,
      "learning_rate": 1.148397956361007e-05,
      "loss": 2.0286,
      "num_input_tokens_seen": 5476736,
      "step": 540
    },
    {
      "epoch": 4.10933081998115,
      "grad_norm": 5.690558433532715,
      "learning_rate": 1.106954458033026e-05,
      "loss": 2.0398,
      "num_input_tokens_seen": 5531328,
      "step": 545
    },
    {
      "epoch": 4.147031102733271,
      "grad_norm": 5.595386505126953,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 2.1157,
      "num_input_tokens_seen": 5579216,
      "step": 550
    },
    {
      "epoch": 4.184731385485391,
      "grad_norm": 6.112159252166748,
      "learning_rate": 1.025727395745095e-05,
      "loss": 2.094,
      "num_input_tokens_seen": 5626208,
      "step": 555
    },
    {
      "epoch": 4.222431668237512,
      "grad_norm": 5.86374568939209,
      "learning_rate": 9.859757821558337e-06,
      "loss": 2.0531,
      "num_input_tokens_seen": 5679360,
      "step": 560
    },
    {
      "epoch": 4.260131950989632,
      "grad_norm": 5.2934699058532715,
      "learning_rate": 9.468197045077976e-06,
      "loss": 1.9652,
      "num_input_tokens_seen": 5724608,
      "step": 565
    },
    {
      "epoch": 4.297832233741753,
      "grad_norm": 6.302525043487549,
      "learning_rate": 9.082745647022797e-06,
      "loss": 2.0592,
      "num_input_tokens_seen": 5779904,
      "step": 570
    },
    {
      "epoch": 4.335532516493874,
      "grad_norm": 6.2651143074035645,
      "learning_rate": 8.703555243303835e-06,
      "loss": 2.0418,
      "num_input_tokens_seen": 5826880,
      "step": 575
    },
    {
      "epoch": 4.3732327992459945,
      "grad_norm": 6.225465774536133,
      "learning_rate": 8.330774987092712e-06,
      "loss": 1.991,
      "num_input_tokens_seen": 5875440,
      "step": 580
    },
    {
      "epoch": 4.410933081998115,
      "grad_norm": 5.812168121337891,
      "learning_rate": 7.96455151015272e-06,
      "loss": 2.0726,
      "num_input_tokens_seen": 5924960,
      "step": 585
    },
    {
      "epoch": 4.448633364750235,
      "grad_norm": 5.528653621673584,
      "learning_rate": 7.605028865161809e-06,
      "loss": 2.069,
      "num_input_tokens_seen": 5976416,
      "step": 590
    },
    {
      "epoch": 4.486333647502356,
      "grad_norm": 5.838290691375732,
      "learning_rate": 7.25234846904993e-06,
      "loss": 2.052,
      "num_input_tokens_seen": 6027088,
      "step": 595
    },
    {
      "epoch": 4.524033930254477,
      "grad_norm": 6.014201641082764,
      "learning_rate": 6.906649047373246e-06,
      "loss": 2.0651,
      "num_input_tokens_seen": 6080528,
      "step": 600
    },
    {
      "epoch": 4.561734213006598,
      "grad_norm": 6.840231895446777,
      "learning_rate": 6.568066579746901e-06,
      "loss": 2.0546,
      "num_input_tokens_seen": 6125904,
      "step": 605
    },
    {
      "epoch": 4.599434495758718,
      "grad_norm": 6.350096702575684,
      "learning_rate": 6.2367342463579475e-06,
      "loss": 2.081,
      "num_input_tokens_seen": 6173744,
      "step": 610
    },
    {
      "epoch": 4.6371347785108386,
      "grad_norm": 6.259740352630615,
      "learning_rate": 5.912782375579412e-06,
      "loss": 2.0395,
      "num_input_tokens_seen": 6222560,
      "step": 615
    },
    {
      "epoch": 4.674835061262959,
      "grad_norm": 6.564173221588135,
      "learning_rate": 5.596338392706077e-06,
      "loss": 2.0659,
      "num_input_tokens_seen": 6272544,
      "step": 620
    },
    {
      "epoch": 4.71253534401508,
      "grad_norm": 5.375278949737549,
      "learning_rate": 5.2875267698322325e-06,
      "loss": 2.0247,
      "num_input_tokens_seen": 6323024,
      "step": 625
    },
    {
      "epoch": 4.750235626767201,
      "grad_norm": 5.922281265258789,
      "learning_rate": 4.986468976890993e-06,
      "loss": 2.0485,
      "num_input_tokens_seen": 6374608,
      "step": 630
    },
    {
      "epoch": 4.787935909519321,
      "grad_norm": 5.62613582611084,
      "learning_rate": 4.693283433874565e-06,
      "loss": 2.0561,
      "num_input_tokens_seen": 6422208,
      "step": 635
    },
    {
      "epoch": 4.825636192271442,
      "grad_norm": 6.259154796600342,
      "learning_rate": 4.408085464254183e-06,
      "loss": 2.1047,
      "num_input_tokens_seen": 6468912,
      "step": 640
    },
    {
      "epoch": 4.863336475023563,
      "grad_norm": 5.757895469665527,
      "learning_rate": 4.130987249617993e-06,
      "loss": 2.0481,
      "num_input_tokens_seen": 6522848,
      "step": 645
    },
    {
      "epoch": 4.9010367577756835,
      "grad_norm": 5.949391841888428,
      "learning_rate": 3.8620977855448935e-06,
      "loss": 2.0637,
      "num_input_tokens_seen": 6578768,
      "step": 650
    },
    {
      "epoch": 4.938737040527804,
      "grad_norm": 6.397491931915283,
      "learning_rate": 3.601522838731461e-06,
      "loss": 2.0429,
      "num_input_tokens_seen": 6631936,
      "step": 655
    },
    {
      "epoch": 4.976437323279924,
      "grad_norm": 6.2142157554626465,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 2.1212,
      "num_input_tokens_seen": 6682992,
      "step": 660
    },
    {
      "epoch": 5.014137606032045,
      "grad_norm": 5.99893856048584,
      "learning_rate": 3.1057231709272077e-06,
      "loss": 2.0205,
      "num_input_tokens_seen": 6735056,
      "step": 665
    },
    {
      "epoch": 5.051837888784166,
      "grad_norm": 6.014187335968018,
      "learning_rate": 2.8706934709395892e-06,
      "loss": 1.9942,
      "num_input_tokens_seen": 6784224,
      "step": 670
    },
    {
      "epoch": 5.089538171536287,
      "grad_norm": 6.134748935699463,
      "learning_rate": 2.6443682535072177e-06,
      "loss": 1.868,
      "num_input_tokens_seen": 6831040,
      "step": 675
    },
    {
      "epoch": 5.127238454288407,
      "grad_norm": 5.91867733001709,
      "learning_rate": 2.4268365428344736e-06,
      "loss": 1.9132,
      "num_input_tokens_seen": 6883552,
      "step": 680
    },
    {
      "epoch": 5.1649387370405275,
      "grad_norm": 7.725922584533691,
      "learning_rate": 2.21818390423168e-06,
      "loss": 1.8698,
      "num_input_tokens_seen": 6928272,
      "step": 685
    },
    {
      "epoch": 5.202639019792649,
      "grad_norm": 5.97230863571167,
      "learning_rate": 2.0184924104583613e-06,
      "loss": 1.8974,
      "num_input_tokens_seen": 6972496,
      "step": 690
    },
    {
      "epoch": 5.240339302544769,
      "grad_norm": 6.879273414611816,
      "learning_rate": 1.8278406094401623e-06,
      "loss": 1.9096,
      "num_input_tokens_seen": 7018496,
      "step": 695
    },
    {
      "epoch": 5.27803958529689,
      "grad_norm": 6.802375793457031,
      "learning_rate": 1.6463034933723337e-06,
      "loss": 2.0098,
      "num_input_tokens_seen": 7066400,
      "step": 700
    },
    {
      "epoch": 5.31573986804901,
      "grad_norm": 6.246311187744141,
      "learning_rate": 1.4739524692218314e-06,
      "loss": 1.9554,
      "num_input_tokens_seen": 7113744,
      "step": 705
    },
    {
      "epoch": 5.353440150801131,
      "grad_norm": 6.855324745178223,
      "learning_rate": 1.3108553306396265e-06,
      "loss": 2.0233,
      "num_input_tokens_seen": 7166848,
      "step": 710
    },
    {
      "epoch": 5.391140433553252,
      "grad_norm": 7.124240398406982,
      "learning_rate": 1.1570762312943295e-06,
      "loss": 1.9629,
      "num_input_tokens_seen": 7220048,
      "step": 715
    },
    {
      "epoch": 5.4288407163053725,
      "grad_norm": 6.546064853668213,
      "learning_rate": 1.0126756596375686e-06,
      "loss": 1.9036,
      "num_input_tokens_seen": 7268064,
      "step": 720
    },
    {
      "epoch": 5.466540999057493,
      "grad_norm": 6.543118953704834,
      "learning_rate": 8.777104151110826e-07,
      "loss": 1.988,
      "num_input_tokens_seen": 7326512,
      "step": 725
    },
    {
      "epoch": 5.504241281809613,
      "grad_norm": 6.955906391143799,
      "learning_rate": 7.522335858048707e-07,
      "loss": 1.9844,
      "num_input_tokens_seen": 7382288,
      "step": 730
    },
    {
      "epoch": 5.541941564561734,
      "grad_norm": 6.836036682128906,
      "learning_rate": 6.362945275751736e-07,
      "loss": 1.9743,
      "num_input_tokens_seen": 7430544,
      "step": 735
    },
    {
      "epoch": 5.579641847313855,
      "grad_norm": 6.253538608551025,
      "learning_rate": 5.299388446305343e-07,
      "loss": 2.007,
      "num_input_tokens_seen": 7479488,
      "step": 740
    },
    {
      "epoch": 5.617342130065976,
      "grad_norm": 5.982280731201172,
      "learning_rate": 4.3320837159353813e-07,
      "loss": 1.9413,
      "num_input_tokens_seen": 7533536,
      "step": 745
    },
    {
      "epoch": 5.655042412818096,
      "grad_norm": 5.737644195556641,
      "learning_rate": 3.4614115704533767e-07,
      "loss": 1.902,
      "num_input_tokens_seen": 7589200,
      "step": 750
    },
    {
      "epoch": 5.6927426955702165,
      "grad_norm": 6.928066730499268,
      "learning_rate": 2.687714485593462e-07,
      "loss": 2.0091,
      "num_input_tokens_seen": 7638928,
      "step": 755
    },
    {
      "epoch": 5.730442978322337,
      "grad_norm": 6.864605903625488,
      "learning_rate": 2.011296792301165e-07,
      "loss": 2.0389,
      "num_input_tokens_seen": 7693680,
      "step": 760
    },
    {
      "epoch": 5.768143261074458,
      "grad_norm": 6.230181694030762,
      "learning_rate": 1.4324245570256633e-07,
      "loss": 2.0012,
      "num_input_tokens_seen": 7743904,
      "step": 765
    },
    {
      "epoch": 5.805843543826579,
      "grad_norm": 6.436938285827637,
      "learning_rate": 9.513254770636137e-08,
      "loss": 2.0127,
      "num_input_tokens_seen": 7790992,
      "step": 770
    },
    {
      "epoch": 5.843543826578699,
      "grad_norm": 6.2262349128723145,
      "learning_rate": 5.681887909952388e-08,
      "loss": 2.0237,
      "num_input_tokens_seen": 7843600,
      "step": 775
    },
    {
      "epoch": 5.88124410933082,
      "grad_norm": 6.8672027587890625,
      "learning_rate": 2.831652042480093e-08,
      "loss": 1.9273,
      "num_input_tokens_seen": 7893968,
      "step": 780
    },
    {
      "epoch": 5.918944392082941,
      "grad_norm": 6.41185188293457,
      "learning_rate": 9.636682981720158e-09,
      "loss": 1.9827,
      "num_input_tokens_seen": 7945856,
      "step": 785
    },
    {
      "epoch": 5.956644674835061,
      "grad_norm": 6.624245643615723,
      "learning_rate": 7.867144166728846e-10,
      "loss": 1.9642,
      "num_input_tokens_seen": 7998560,
      "step": 790
    },
    {
      "epoch": 5.971724787935909,
      "num_input_tokens_seen": 8017392,
      "step": 792,
      "total_flos": 3.6202835979167334e+17,
      "train_loss": 2.4793783682163317,
      "train_runtime": 5283.1732,
      "train_samples_per_second": 4.82,
      "train_steps_per_second": 0.15
    }
  ],
  "logging_steps": 5,
  "max_steps": 792,
  "num_input_tokens_seen": 8017392,
  "num_train_epochs": 6,
  "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": 3.6202835979167334e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}