{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 406,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0024630541871921183,
      "grad_norm": 0.14675670862197876,
      "learning_rate": 4.8780487804878055e-06,
      "loss": 0.7979,
      "step": 1
    },
    {
      "epoch": 0.012315270935960592,
      "grad_norm": 0.16588939726352692,
      "learning_rate": 2.4390243902439026e-05,
      "loss": 0.8031,
      "step": 5
    },
    {
      "epoch": 0.024630541871921183,
      "grad_norm": 0.12261141091585159,
      "learning_rate": 4.878048780487805e-05,
      "loss": 0.7831,
      "step": 10
    },
    {
      "epoch": 0.03694581280788178,
      "grad_norm": 0.147330179810524,
      "learning_rate": 7.317073170731707e-05,
      "loss": 0.7869,
      "step": 15
    },
    {
      "epoch": 0.04926108374384237,
      "grad_norm": 0.12319152057170868,
      "learning_rate": 9.75609756097561e-05,
      "loss": 0.7846,
      "step": 20
    },
    {
      "epoch": 0.06157635467980296,
      "grad_norm": 0.1133740246295929,
      "learning_rate": 0.00012195121951219512,
      "loss": 0.7557,
      "step": 25
    },
    {
      "epoch": 0.07389162561576355,
      "grad_norm": 0.1037982627749443,
      "learning_rate": 0.00014634146341463414,
      "loss": 0.7589,
      "step": 30
    },
    {
      "epoch": 0.08620689655172414,
      "grad_norm": 0.09962955117225647,
      "learning_rate": 0.0001707317073170732,
      "loss": 0.7533,
      "step": 35
    },
    {
      "epoch": 0.09852216748768473,
      "grad_norm": 0.10443014651536942,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7685,
      "step": 40
    },
    {
      "epoch": 0.11083743842364532,
      "grad_norm": 0.11216488480567932,
      "learning_rate": 0.0001999407400739705,
      "loss": 0.7686,
      "step": 45
    },
    {
      "epoch": 0.12315270935960591,
      "grad_norm": 0.10660657286643982,
      "learning_rate": 0.00019970011699250152,
      "loss": 0.7612,
      "step": 50
    },
    {
      "epoch": 0.1354679802955665,
      "grad_norm": 0.10816114395856857,
      "learning_rate": 0.00019927487224577402,
      "loss": 0.7411,
      "step": 55
    },
    {
      "epoch": 0.1477832512315271,
      "grad_norm": 0.09839071333408356,
      "learning_rate": 0.0001986657932891657,
      "loss": 0.7602,
      "step": 60
    },
    {
      "epoch": 0.16009852216748768,
      "grad_norm": 0.1016278862953186,
      "learning_rate": 0.00019787400799669154,
      "loss": 0.7323,
      "step": 65
    },
    {
      "epoch": 0.1724137931034483,
      "grad_norm": 0.10624498128890991,
      "learning_rate": 0.00019690098257244064,
      "loss": 0.7466,
      "step": 70
    },
    {
      "epoch": 0.18472906403940886,
      "grad_norm": 0.10132507234811783,
      "learning_rate": 0.00019574851883550395,
      "loss": 0.7374,
      "step": 75
    },
    {
      "epoch": 0.19704433497536947,
      "grad_norm": 0.10639315843582153,
      "learning_rate": 0.00019441875088341997,
      "loss": 0.7481,
      "step": 80
    },
    {
      "epoch": 0.20935960591133004,
      "grad_norm": 0.09627559036016464,
      "learning_rate": 0.00019291414114031743,
      "loss": 0.7093,
      "step": 85
    },
    {
      "epoch": 0.22167487684729065,
      "grad_norm": 0.09796547144651413,
      "learning_rate": 0.00019123747579707275,
      "loss": 0.7428,
      "step": 90
    },
    {
      "epoch": 0.23399014778325122,
      "grad_norm": 0.11040158569812775,
      "learning_rate": 0.0001893918596519257,
      "loss": 0.7584,
      "step": 95
    },
    {
      "epoch": 0.24630541871921183,
      "grad_norm": 0.10157530009746552,
      "learning_rate": 0.00018738071036110808,
      "loss": 0.7441,
      "step": 100
    },
    {
      "epoch": 0.25862068965517243,
      "grad_norm": 0.1049741879105568,
      "learning_rate": 0.00018520775211013093,
      "loss": 0.7404,
      "step": 105
    },
    {
      "epoch": 0.270935960591133,
      "grad_norm": 0.10510259866714478,
      "learning_rate": 0.00018287700871745036,
      "loss": 0.7262,
      "step": 110
    },
    {
      "epoch": 0.2832512315270936,
      "grad_norm": 0.09340078383684158,
      "learning_rate": 0.00018039279618328212,
      "loss": 0.7488,
      "step": 115
    },
    {
      "epoch": 0.2955665024630542,
      "grad_norm": 0.1036185547709465,
      "learning_rate": 0.0001777597146973627,
      "loss": 0.7427,
      "step": 120
    },
    {
      "epoch": 0.3078817733990148,
      "grad_norm": 0.0969434604048729,
      "learning_rate": 0.00017498264012045687,
      "loss": 0.7383,
      "step": 125
    },
    {
      "epoch": 0.32019704433497537,
      "grad_norm": 0.090766541659832,
      "learning_rate": 0.00017206671495538612,
      "loss": 0.7427,
      "step": 130
    },
    {
      "epoch": 0.33251231527093594,
      "grad_norm": 0.10108979046344757,
      "learning_rate": 0.0001690173388242972,
      "loss": 0.7326,
      "step": 135
    },
    {
      "epoch": 0.3448275862068966,
      "grad_norm": 0.1024017408490181,
      "learning_rate": 0.0001658401584698049,
      "loss": 0.7459,
      "step": 140
    },
    {
      "epoch": 0.35714285714285715,
      "grad_norm": 0.09906227886676788,
      "learning_rate": 0.00016254105729852464,
      "loss": 0.7576,
      "step": 145
    },
    {
      "epoch": 0.3694581280788177,
      "grad_norm": 0.09525298327207565,
      "learning_rate": 0.00015912614448635782,
      "loss": 0.7659,
      "step": 150
    },
    {
      "epoch": 0.3817733990147783,
      "grad_norm": 0.09237983077764511,
      "learning_rate": 0.00015560174366570446,
      "loss": 0.7308,
      "step": 155
    },
    {
      "epoch": 0.39408866995073893,
      "grad_norm": 0.09774871915578842,
      "learning_rate": 0.0001519743812155516,
      "loss": 0.7585,
      "step": 160
    },
    {
      "epoch": 0.4064039408866995,
      "grad_norm": 0.09578228741884232,
      "learning_rate": 0.00014825077417612186,
      "loss": 0.7393,
      "step": 165
    },
    {
      "epoch": 0.4187192118226601,
      "grad_norm": 0.09492405503988266,
      "learning_rate": 0.00014443781781046136,
      "loss": 0.7286,
      "step": 170
    },
    {
      "epoch": 0.43103448275862066,
      "grad_norm": 0.09465403109788895,
      "learning_rate": 0.00014054257283599973,
      "loss": 0.7272,
      "step": 175
    },
    {
      "epoch": 0.4433497536945813,
      "grad_norm": 0.09246574342250824,
      "learning_rate": 0.00013657225234972695,
      "loss": 0.7332,
      "step": 180
    },
    {
      "epoch": 0.45566502463054187,
      "grad_norm": 0.09713710844516754,
      "learning_rate": 0.00013253420847119803,
      "loss": 0.7454,
      "step": 185
    },
    {
      "epoch": 0.46798029556650245,
      "grad_norm": 0.10003787279129028,
      "learning_rate": 0.0001284359187281004,
      "loss": 0.7378,
      "step": 190
    },
    {
      "epoch": 0.4802955665024631,
      "grad_norm": 0.1029965803027153,
      "learning_rate": 0.0001242849722095936,
      "loss": 0.7423,
      "step": 195
    },
    {
      "epoch": 0.49261083743842365,
      "grad_norm": 0.09402066469192505,
      "learning_rate": 0.00012008905551306356,
      "loss": 0.7243,
      "step": 200
    },
    {
      "epoch": 0.5049261083743842,
      "grad_norm": 0.09957736730575562,
      "learning_rate": 0.00011585593851031347,
      "loss": 0.7415,
      "step": 205
    },
    {
      "epoch": 0.5172413793103449,
      "grad_norm": 0.09485721588134766,
      "learning_rate": 0.00011159345995955006,
      "loss": 0.7449,
      "step": 210
    },
    {
      "epoch": 0.5295566502463054,
      "grad_norm": 0.09737714380025864,
      "learning_rate": 0.00010730951298980776,
      "loss": 0.7518,
      "step": 215
    },
    {
      "epoch": 0.541871921182266,
      "grad_norm": 0.09507936239242554,
      "learning_rate": 0.00010301203048469083,
      "loss": 0.7474,
      "step": 220
    },
    {
      "epoch": 0.5541871921182266,
      "grad_norm": 0.09971079975366592,
      "learning_rate": 9.870897039249911e-05,
      "loss": 0.7495,
      "step": 225
    },
    {
      "epoch": 0.5665024630541872,
      "grad_norm": 0.09943493455648422,
      "learning_rate": 9.440830098993969e-05,
      "loss": 0.7314,
      "step": 230
    },
    {
      "epoch": 0.5788177339901478,
      "grad_norm": 0.09579654783010483,
      "learning_rate": 9.011798612671286e-05,
      "loss": 0.742,
      "step": 235
    },
    {
      "epoch": 0.5911330049261084,
      "grad_norm": 0.09293965250253677,
      "learning_rate": 8.58459704782957e-05,
      "loss": 0.7445,
      "step": 240
    },
    {
      "epoch": 0.603448275862069,
      "grad_norm": 0.09880805015563965,
      "learning_rate": 8.160016483423199e-05,
      "loss": 0.7366,
      "step": 245
    },
    {
      "epoch": 0.6157635467980296,
      "grad_norm": 0.09536171704530716,
      "learning_rate": 7.738843144917119e-05,
      "loss": 0.7426,
      "step": 250
    },
    {
      "epoch": 0.6280788177339901,
      "grad_norm": 0.09729348868131638,
      "learning_rate": 7.321856948378259e-05,
      "loss": 0.7347,
      "step": 255
    },
    {
      "epoch": 0.6403940886699507,
      "grad_norm": 0.09990367293357849,
      "learning_rate": 6.909830056250527e-05,
      "loss": 0.7499,
      "step": 260
    },
    {
      "epoch": 0.6527093596059114,
      "grad_norm": 0.09805148094892502,
      "learning_rate": 6.503525447487715e-05,
      "loss": 0.7459,
      "step": 265
    },
    {
      "epoch": 0.6650246305418719,
      "grad_norm": 0.10217900574207306,
      "learning_rate": 6.103695504692122e-05,
      "loss": 0.7494,
      "step": 270
    },
    {
      "epoch": 0.6773399014778325,
      "grad_norm": 0.09525923430919647,
      "learning_rate": 5.7110806208751655e-05,
      "loss": 0.7563,
      "step": 275
    },
    {
      "epoch": 0.6896551724137931,
      "grad_norm": 0.10066010057926178,
      "learning_rate": 5.326407828419979e-05,
      "loss": 0.7265,
      "step": 280
    },
    {
      "epoch": 0.7019704433497537,
      "grad_norm": 0.10397505015134811,
      "learning_rate": 4.9503894527847964e-05,
      "loss": 0.7309,
      "step": 285
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.09594658017158508,
      "learning_rate": 4.583721793440188e-05,
      "loss": 0.738,
      "step": 290
    },
    {
      "epoch": 0.7266009852216748,
      "grad_norm": 0.09076676517724991,
      "learning_rate": 4.227083834482728e-05,
      "loss": 0.7395,
      "step": 295
    },
    {
      "epoch": 0.7389162561576355,
      "grad_norm": 0.09753654897212982,
      "learning_rate": 3.881135987312757e-05,
      "loss": 0.7475,
      "step": 300
    },
    {
      "epoch": 0.7512315270935961,
      "grad_norm": 0.09329697489738464,
      "learning_rate": 3.546518867704499e-05,
      "loss": 0.7401,
      "step": 305
    },
    {
      "epoch": 0.7635467980295566,
      "grad_norm": 0.09275539964437485,
      "learning_rate": 3.223852109533112e-05,
      "loss": 0.7201,
      "step": 310
    },
    {
      "epoch": 0.7758620689655172,
      "grad_norm": 0.09541057795286179,
      "learning_rate": 2.9137332173554043e-05,
      "loss": 0.7325,
      "step": 315
    },
    {
      "epoch": 0.7881773399014779,
      "grad_norm": 0.09886154532432556,
      "learning_rate": 2.616736459968936e-05,
      "loss": 0.726,
      "step": 320
    },
    {
      "epoch": 0.8004926108374384,
      "grad_norm": 0.09287051111459732,
      "learning_rate": 2.33341180699841e-05,
      "loss": 0.7259,
      "step": 325
    },
    {
      "epoch": 0.812807881773399,
      "grad_norm": 0.09618936479091644,
      "learning_rate": 2.0642839104785272e-05,
      "loss": 0.7339,
      "step": 330
    },
    {
      "epoch": 0.8251231527093597,
      "grad_norm": 0.09387245029211044,
      "learning_rate": 1.8098511333192024e-05,
      "loss": 0.7401,
      "step": 335
    },
    {
      "epoch": 0.8374384236453202,
      "grad_norm": 0.09571622312068939,
      "learning_rate": 1.570584626452173e-05,
      "loss": 0.72,
      "step": 340
    },
    {
      "epoch": 0.8497536945812808,
      "grad_norm": 0.09303436428308487,
      "learning_rate": 1.3469274563679402e-05,
      "loss": 0.7239,
      "step": 345
    },
    {
      "epoch": 0.8620689655172413,
      "grad_norm": 0.0941215455532074,
      "learning_rate": 1.1392937846586215e-05,
      "loss": 0.7436,
      "step": 350
    },
    {
      "epoch": 0.874384236453202,
      "grad_norm": 0.09552398324012756,
      "learning_rate": 9.48068101086026e-06,
      "loss": 0.7304,
      "step": 355
    },
    {
      "epoch": 0.8866995073891626,
      "grad_norm": 0.09602542966604233,
      "learning_rate": 7.736045115951251e-06,
      "loss": 0.7355,
      "step": 360
    },
    {
      "epoch": 0.8990147783251231,
      "grad_norm": 0.1008099839091301,
      "learning_rate": 6.16226082591359e-06,
      "loss": 0.726,
      "step": 365
    },
    {
      "epoch": 0.9113300492610837,
      "grad_norm": 0.0940895676612854,
      "learning_rate": 4.762242426960262e-06,
      "loss": 0.7417,
      "step": 370
    },
    {
      "epoch": 0.9236453201970444,
      "grad_norm": 0.09120815247297287,
      "learning_rate": 3.5385824308756587e-06,
      "loss": 0.7361,
      "step": 375
    },
    {
      "epoch": 0.9359605911330049,
      "grad_norm": 0.0950731709599495,
      "learning_rate": 2.493546774280531e-06,
      "loss": 0.7362,
      "step": 380
    },
    {
      "epoch": 0.9482758620689655,
      "grad_norm": 0.09295763075351715,
      "learning_rate": 1.6290706226390285e-06,
      "loss": 0.7237,
      "step": 385
    },
    {
      "epoch": 0.9605911330049262,
      "grad_norm": 0.09224182367324829,
      "learning_rate": 9.46754786777726e-07,
      "loss": 0.7286,
      "step": 390
    },
    {
      "epoch": 0.9729064039408867,
      "grad_norm": 0.0961490347981453,
      "learning_rate": 4.4786275855247527e-07,
      "loss": 0.7221,
      "step": 395
    },
    {
      "epoch": 0.9852216748768473,
      "grad_norm": 0.09469573199748993,
      "learning_rate": 1.333183711524133e-07,
      "loss": 0.7498,
      "step": 400
    },
    {
      "epoch": 0.9975369458128078,
      "grad_norm": 0.09686147421598434,
      "learning_rate": 3.7040883734462683e-09,
      "loss": 0.7407,
      "step": 405
    },
    {
      "epoch": 1.0,
      "eval_loss": NaN,
      "eval_runtime": 938.2112,
      "eval_samples_per_second": 1.231,
      "eval_steps_per_second": 0.308,
      "step": 406
    },
    {
      "epoch": 1.0,
      "step": 406,
      "total_flos": 2.1311021010303058e+18,
      "train_loss": 0.011041376391067882,
      "train_runtime": 1933.8682,
      "train_samples_per_second": 53.743,
      "train_steps_per_second": 0.21
    }
  ],
  "logging_steps": 5,
  "max_steps": 406,
  "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": 2.1311021010303058e+18,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}