{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.016022620169651,
  "eval_steps": 500,
  "global_step": 400,
  "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
    }
  ],
  "logging_steps": 5,
  "max_steps": 792,
  "num_input_tokens_seen": 4052688,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.830006553533481e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}