{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 401,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012484394506866416,
      "grad_norm": 1.0609335899353027,
      "learning_rate": 1.1881188118811881e-06,
      "loss": 1.2283,
      "step": 5
    },
    {
      "epoch": 0.024968789013732832,
      "grad_norm": 0.8323203921318054,
      "learning_rate": 2.673267326732673e-06,
      "loss": 1.2561,
      "step": 10
    },
    {
      "epoch": 0.03745318352059925,
      "grad_norm": 0.8071620464324951,
      "learning_rate": 4.158415841584159e-06,
      "loss": 1.2571,
      "step": 15
    },
    {
      "epoch": 0.049937578027465665,
      "grad_norm": 0.6458085775375366,
      "learning_rate": 5.643564356435644e-06,
      "loss": 1.2301,
      "step": 20
    },
    {
      "epoch": 0.062421972534332085,
      "grad_norm": 0.6387593746185303,
      "learning_rate": 7.128712871287129e-06,
      "loss": 1.1905,
      "step": 25
    },
    {
      "epoch": 0.0749063670411985,
      "grad_norm": 0.5484127402305603,
      "learning_rate": 8.613861386138613e-06,
      "loss": 1.2693,
      "step": 30
    },
    {
      "epoch": 0.08739076154806492,
      "grad_norm": 0.6438347101211548,
      "learning_rate": 1.00990099009901e-05,
      "loss": 1.1677,
      "step": 35
    },
    {
      "epoch": 0.09987515605493133,
      "grad_norm": 0.503511905670166,
      "learning_rate": 1.1584158415841584e-05,
      "loss": 1.1914,
      "step": 40
    },
    {
      "epoch": 0.11235955056179775,
      "grad_norm": 0.5014557242393494,
      "learning_rate": 1.306930693069307e-05,
      "loss": 1.2152,
      "step": 45
    },
    {
      "epoch": 0.12484394506866417,
      "grad_norm": 0.49721699953079224,
      "learning_rate": 1.4554455445544554e-05,
      "loss": 1.1607,
      "step": 50
    },
    {
      "epoch": 0.1373283395755306,
      "grad_norm": 0.5247049927711487,
      "learning_rate": 1.6039603960396042e-05,
      "loss": 1.1722,
      "step": 55
    },
    {
      "epoch": 0.149812734082397,
      "grad_norm": 0.4929521083831787,
      "learning_rate": 1.7524752475247524e-05,
      "loss": 1.1115,
      "step": 60
    },
    {
      "epoch": 0.16229712858926343,
      "grad_norm": 0.4400411546230316,
      "learning_rate": 1.900990099009901e-05,
      "loss": 1.1327,
      "step": 65
    },
    {
      "epoch": 0.17478152309612985,
      "grad_norm": 0.5146467089653015,
      "learning_rate": 2.0495049504950496e-05,
      "loss": 1.0995,
      "step": 70
    },
    {
      "epoch": 0.18726591760299627,
      "grad_norm": 0.4721396565437317,
      "learning_rate": 2.198019801980198e-05,
      "loss": 1.0986,
      "step": 75
    },
    {
      "epoch": 0.19975031210986266,
      "grad_norm": 0.5145531296730042,
      "learning_rate": 2.3465346534653467e-05,
      "loss": 1.052,
      "step": 80
    },
    {
      "epoch": 0.21223470661672908,
      "grad_norm": 0.4975873827934265,
      "learning_rate": 2.495049504950495e-05,
      "loss": 1.1328,
      "step": 85
    },
    {
      "epoch": 0.2247191011235955,
      "grad_norm": 0.5143810510635376,
      "learning_rate": 2.6435643564356436e-05,
      "loss": 1.1032,
      "step": 90
    },
    {
      "epoch": 0.23720349563046192,
      "grad_norm": 0.5382490754127502,
      "learning_rate": 2.792079207920792e-05,
      "loss": 1.1121,
      "step": 95
    },
    {
      "epoch": 0.24968789013732834,
      "grad_norm": 0.5149545073509216,
      "learning_rate": 2.9405940594059407e-05,
      "loss": 1.0955,
      "step": 100
    },
    {
      "epoch": 0.26217228464419473,
      "grad_norm": 0.5805860757827759,
      "learning_rate": 2.999981623248469e-05,
      "loss": 1.0344,
      "step": 105
    },
    {
      "epoch": 0.2746566791510612,
      "grad_norm": 0.524933934211731,
      "learning_rate": 2.9998693225086163e-05,
      "loss": 1.0875,
      "step": 110
    },
    {
      "epoch": 0.28714107365792757,
      "grad_norm": 0.5526661276817322,
      "learning_rate": 2.9996549379694418e-05,
      "loss": 1.1151,
      "step": 115
    },
    {
      "epoch": 0.299625468164794,
      "grad_norm": 0.5277731418609619,
      "learning_rate": 2.9993384842223426e-05,
      "loss": 1.04,
      "step": 120
    },
    {
      "epoch": 0.3121098626716604,
      "grad_norm": 0.5590221285820007,
      "learning_rate": 2.998919982805729e-05,
      "loss": 1.0067,
      "step": 125
    },
    {
      "epoch": 0.32459425717852686,
      "grad_norm": 0.596834659576416,
      "learning_rate": 2.998399462203559e-05,
      "loss": 0.9961,
      "step": 130
    },
    {
      "epoch": 0.33707865168539325,
      "grad_norm": 0.5012202262878418,
      "learning_rate": 2.9977769578433987e-05,
      "loss": 1.0435,
      "step": 135
    },
    {
      "epoch": 0.3495630461922597,
      "grad_norm": 0.6139566898345947,
      "learning_rate": 2.9970525120940132e-05,
      "loss": 0.9714,
      "step": 140
    },
    {
      "epoch": 0.3620474406991261,
      "grad_norm": 0.5993323922157288,
      "learning_rate": 2.9962261742624813e-05,
      "loss": 1.0804,
      "step": 145
    },
    {
      "epoch": 0.37453183520599254,
      "grad_norm": 0.6254947185516357,
      "learning_rate": 2.995298000590839e-05,
      "loss": 0.9821,
      "step": 150
    },
    {
      "epoch": 0.38701622971285893,
      "grad_norm": 0.6110448241233826,
      "learning_rate": 2.9942680542522535e-05,
      "loss": 0.9785,
      "step": 155
    },
    {
      "epoch": 0.3995006242197253,
      "grad_norm": 0.5888521075248718,
      "learning_rate": 2.993136405346722e-05,
      "loss": 0.9882,
      "step": 160
    },
    {
      "epoch": 0.41198501872659177,
      "grad_norm": 0.6749442219734192,
      "learning_rate": 2.991903130896301e-05,
      "loss": 1.0322,
      "step": 165
    },
    {
      "epoch": 0.42446941323345816,
      "grad_norm": 0.7961056232452393,
      "learning_rate": 2.9905683148398642e-05,
      "loss": 0.9149,
      "step": 170
    },
    {
      "epoch": 0.4369538077403246,
      "grad_norm": 0.6190369129180908,
      "learning_rate": 2.9891320480273886e-05,
      "loss": 0.9756,
      "step": 175
    },
    {
      "epoch": 0.449438202247191,
      "grad_norm": 0.6471540927886963,
      "learning_rate": 2.9875944282137734e-05,
      "loss": 0.9204,
      "step": 180
    },
    {
      "epoch": 0.46192259675405745,
      "grad_norm": 0.6503486037254333,
      "learning_rate": 2.9859555600521838e-05,
      "loss": 0.8895,
      "step": 185
    },
    {
      "epoch": 0.47440699126092384,
      "grad_norm": 0.6892472505569458,
      "learning_rate": 2.9842155550869294e-05,
      "loss": 0.9435,
      "step": 190
    },
    {
      "epoch": 0.4868913857677903,
      "grad_norm": 0.7145974636077881,
      "learning_rate": 2.982374531745873e-05,
      "loss": 0.9135,
      "step": 195
    },
    {
      "epoch": 0.4993757802746567,
      "grad_norm": 0.7395890951156616,
      "learning_rate": 2.9804326153323683e-05,
      "loss": 0.8777,
      "step": 200
    },
    {
      "epoch": 0.5118601747815231,
      "grad_norm": 0.8736094832420349,
      "learning_rate": 2.9783899380167345e-05,
      "loss": 0.8953,
      "step": 205
    },
    {
      "epoch": 0.5243445692883895,
      "grad_norm": 0.7746868133544922,
      "learning_rate": 2.976246638827257e-05,
      "loss": 0.8839,
      "step": 210
    },
    {
      "epoch": 0.5368289637952559,
      "grad_norm": 0.7751911878585815,
      "learning_rate": 2.974002863640727e-05,
      "loss": 0.8941,
      "step": 215
    },
    {
      "epoch": 0.5493133583021224,
      "grad_norm": 0.8329525589942932,
      "learning_rate": 2.9716587651725134e-05,
      "loss": 0.8562,
      "step": 220
    },
    {
      "epoch": 0.5617977528089888,
      "grad_norm": 0.8044184446334839,
      "learning_rate": 2.9692145029661664e-05,
      "loss": 0.8543,
      "step": 225
    },
    {
      "epoch": 0.5742821473158551,
      "grad_norm": 0.7520190477371216,
      "learning_rate": 2.9666702433825614e-05,
      "loss": 0.839,
      "step": 230
    },
    {
      "epoch": 0.5867665418227216,
      "grad_norm": 0.7825169563293457,
      "learning_rate": 2.9640261595885735e-05,
      "loss": 0.8368,
      "step": 235
    },
    {
      "epoch": 0.599250936329588,
      "grad_norm": 0.7438607215881348,
      "learning_rate": 2.9612824315452943e-05,
      "loss": 0.8619,
      "step": 240
    },
    {
      "epoch": 0.6117353308364545,
      "grad_norm": 0.7354984283447266,
      "learning_rate": 2.958439245995781e-05,
      "loss": 0.8337,
      "step": 245
    },
    {
      "epoch": 0.6242197253433208,
      "grad_norm": 0.7580518126487732,
      "learning_rate": 2.955496796452347e-05,
      "loss": 0.7538,
      "step": 250
    },
    {
      "epoch": 0.6367041198501873,
      "grad_norm": 0.7653853893280029,
      "learning_rate": 2.9524552831833924e-05,
      "loss": 0.8178,
      "step": 255
    },
    {
      "epoch": 0.6491885143570537,
      "grad_norm": 0.7680398225784302,
      "learning_rate": 2.9493149131997713e-05,
      "loss": 0.795,
      "step": 260
    },
    {
      "epoch": 0.66167290886392,
      "grad_norm": 0.7689065337181091,
      "learning_rate": 2.946075900240704e-05,
      "loss": 0.849,
      "step": 265
    },
    {
      "epoch": 0.6741573033707865,
      "grad_norm": 0.8538303971290588,
      "learning_rate": 2.942738464759229e-05,
      "loss": 0.7875,
      "step": 270
    },
    {
      "epoch": 0.686641697877653,
      "grad_norm": 0.9141761064529419,
      "learning_rate": 2.939302833907197e-05,
      "loss": 0.7989,
      "step": 275
    },
    {
      "epoch": 0.6991260923845194,
      "grad_norm": 0.9288301467895508,
      "learning_rate": 2.9357692415198136e-05,
      "loss": 0.7606,
      "step": 280
    },
    {
      "epoch": 0.7116104868913857,
      "grad_norm": 0.8967108130455017,
      "learning_rate": 2.932137928099722e-05,
      "loss": 0.782,
      "step": 285
    },
    {
      "epoch": 0.7240948813982522,
      "grad_norm": 0.7744588851928711,
      "learning_rate": 2.928409140800634e-05,
      "loss": 0.7793,
      "step": 290
    },
    {
      "epoch": 0.7365792759051186,
      "grad_norm": 0.9789696335792542,
      "learning_rate": 2.9245831334105084e-05,
      "loss": 0.78,
      "step": 295
    },
    {
      "epoch": 0.7490636704119851,
      "grad_norm": 0.853340744972229,
      "learning_rate": 2.9206601663342786e-05,
      "loss": 0.7659,
      "step": 300
    },
    {
      "epoch": 0.7615480649188514,
      "grad_norm": 0.9357976317405701,
      "learning_rate": 2.916640506576128e-05,
      "loss": 0.7468,
      "step": 305
    },
    {
      "epoch": 0.7740324594257179,
      "grad_norm": 0.8526910543441772,
      "learning_rate": 2.9125244277213176e-05,
      "loss": 0.7384,
      "step": 310
    },
    {
      "epoch": 0.7865168539325843,
      "grad_norm": 0.8397050499916077,
      "learning_rate": 2.908312209917565e-05,
      "loss": 0.7512,
      "step": 315
    },
    {
      "epoch": 0.7990012484394506,
      "grad_norm": 0.8564719557762146,
      "learning_rate": 2.904004139855978e-05,
      "loss": 0.7304,
      "step": 320
    },
    {
      "epoch": 0.8114856429463171,
      "grad_norm": 1.0210206508636475,
      "learning_rate": 2.8996005107515405e-05,
      "loss": 0.6818,
      "step": 325
    },
    {
      "epoch": 0.8239700374531835,
      "grad_norm": 0.9247426986694336,
      "learning_rate": 2.8951016223231567e-05,
      "loss": 0.7076,
      "step": 330
    },
    {
      "epoch": 0.83645443196005,
      "grad_norm": 1.1422244310379028,
      "learning_rate": 2.890507780773252e-05,
      "loss": 0.659,
      "step": 335
    },
    {
      "epoch": 0.8489388264669163,
      "grad_norm": 0.8729642629623413,
      "learning_rate": 2.8858192987669303e-05,
      "loss": 0.7419,
      "step": 340
    },
    {
      "epoch": 0.8614232209737828,
      "grad_norm": 0.9443491101264954,
      "learning_rate": 2.881036495410696e-05,
      "loss": 0.6977,
      "step": 345
    },
    {
      "epoch": 0.8739076154806492,
      "grad_norm": 0.9886714816093445,
      "learning_rate": 2.8761596962307343e-05,
      "loss": 0.6996,
      "step": 350
    },
    {
      "epoch": 0.8863920099875156,
      "grad_norm": 0.9167611002922058,
      "learning_rate": 2.871189233150754e-05,
      "loss": 0.6976,
      "step": 355
    },
    {
      "epoch": 0.898876404494382,
      "grad_norm": 0.9194567799568176,
      "learning_rate": 2.8661254444693975e-05,
      "loss": 0.6719,
      "step": 360
    },
    {
      "epoch": 0.9113607990012484,
      "grad_norm": 0.9292520880699158,
      "learning_rate": 2.8609686748372155e-05,
      "loss": 0.6539,
      "step": 365
    },
    {
      "epoch": 0.9238451935081149,
      "grad_norm": 0.8527399301528931,
      "learning_rate": 2.8557192752332082e-05,
      "loss": 0.6709,
      "step": 370
    },
    {
      "epoch": 0.9363295880149812,
      "grad_norm": 1.0521934032440186,
      "learning_rate": 2.8503776029409398e-05,
      "loss": 0.6857,
      "step": 375
    },
    {
      "epoch": 0.9488139825218477,
      "grad_norm": 0.9660723209381104,
      "learning_rate": 2.844944021524217e-05,
      "loss": 0.6418,
      "step": 380
    },
    {
      "epoch": 0.9612983770287141,
      "grad_norm": 0.9831718802452087,
      "learning_rate": 2.8394189008023482e-05,
      "loss": 0.6334,
      "step": 385
    },
    {
      "epoch": 0.9737827715355806,
      "grad_norm": 0.9556214809417725,
      "learning_rate": 2.833802616824972e-05,
      "loss": 0.6385,
      "step": 390
    },
    {
      "epoch": 0.9862671660424469,
      "grad_norm": 0.9405916929244995,
      "learning_rate": 2.8280955518464587e-05,
      "loss": 0.6673,
      "step": 395
    },
    {
      "epoch": 0.9987515605493134,
      "grad_norm": 0.9383732676506042,
      "learning_rate": 2.8222980942999005e-05,
      "loss": 0.618,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 2005,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.842838055865549e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}