{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100.0,
  "global_step": 484,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002067717756526234,
      "grad_norm": 4.46875,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.8509945869445801,
      "step": 1,
      "token_acc": 0.7853175561458585
    },
    {
      "epoch": 0.020677177565262342,
      "grad_norm": 1.828125,
      "learning_rate": 1.3333333333333333e-05,
      "loss": 0.8491229481167264,
      "step": 10,
      "token_acc": 0.78339043091193
    },
    {
      "epoch": 0.041354355130524684,
      "grad_norm": 1.4296875,
      "learning_rate": 1.9994391800229666e-05,
      "loss": 0.7549973011016846,
      "step": 20,
      "token_acc": 0.7997072436054726
    },
    {
      "epoch": 0.062031532695787026,
      "grad_norm": 1.25,
      "learning_rate": 1.9949563937297045e-05,
      "loss": 0.734230375289917,
      "step": 30,
      "token_acc": 0.8047420407633951
    },
    {
      "epoch": 0.08270871026104937,
      "grad_norm": 1.2421875,
      "learning_rate": 1.9860109277923417e-05,
      "loss": 0.7340453624725342,
      "step": 40,
      "token_acc": 0.8038525401200097
    },
    {
      "epoch": 0.10338588782631171,
      "grad_norm": 1.1953125,
      "learning_rate": 1.972642905324813e-05,
      "loss": 0.6950289249420166,
      "step": 50,
      "token_acc": 0.8114663162785941
    },
    {
      "epoch": 0.12406306539157405,
      "grad_norm": 1.0703125,
      "learning_rate": 1.9549122859415538e-05,
      "loss": 0.6816429138183594,
      "step": 60,
      "token_acc": 0.8157978734876097
    },
    {
      "epoch": 0.14474024295683638,
      "grad_norm": 1.1953125,
      "learning_rate": 1.932898596820536e-05,
      "loss": 0.6713860034942627,
      "step": 70,
      "token_acc": 0.8179179583556543
    },
    {
      "epoch": 0.16541742052209873,
      "grad_norm": 1.1796875,
      "learning_rate": 1.9067005759998797e-05,
      "loss": 0.6746496677398681,
      "step": 80,
      "token_acc": 0.8165457239789224
    },
    {
      "epoch": 0.18609459808736106,
      "grad_norm": 1.1953125,
      "learning_rate": 1.876435729507959e-05,
      "loss": 0.6496047496795654,
      "step": 90,
      "token_acc": 0.8231839497434082
    },
    {
      "epoch": 0.20677177565262342,
      "grad_norm": 1.0625,
      "learning_rate": 1.8422398043134068e-05,
      "loss": 0.6486006259918213,
      "step": 100,
      "token_acc": 0.822600955086533
    },
    {
      "epoch": 0.22744895321788575,
      "grad_norm": 1.1484375,
      "learning_rate": 1.8042661794590023e-05,
      "loss": 0.658829641342163,
      "step": 110,
      "token_acc": 0.8208090582207568
    },
    {
      "epoch": 0.2481261307831481,
      "grad_norm": 1.15625,
      "learning_rate": 1.762685178110382e-05,
      "loss": 0.6648715972900391,
      "step": 120,
      "token_acc": 0.8185997272110292
    },
    {
      "epoch": 0.26880330834841043,
      "grad_norm": 1.1640625,
      "learning_rate": 1.7176833036052495e-05,
      "loss": 0.665419340133667,
      "step": 130,
      "token_acc": 0.8191171753031502
    },
    {
      "epoch": 0.28948048591367276,
      "grad_norm": 1.234375,
      "learning_rate": 1.6694624029296288e-05,
      "loss": 0.661893653869629,
      "step": 140,
      "token_acc": 0.8190959299464042
    },
    {
      "epoch": 0.31015766347893514,
      "grad_norm": 1.1484375,
      "learning_rate": 1.6182387613732295e-05,
      "loss": 0.6551508903503418,
      "step": 150,
      "token_acc": 0.820616800353477
    },
    {
      "epoch": 0.33083484104419747,
      "grad_norm": 1.1796875,
      "learning_rate": 1.564242132424657e-05,
      "loss": 0.6404322624206543,
      "step": 160,
      "token_acc": 0.8242824359501302
    },
    {
      "epoch": 0.3515120186094598,
      "grad_norm": 1.1953125,
      "learning_rate": 1.5077147072576932e-05,
      "loss": 0.6450911521911621,
      "step": 170,
      "token_acc": 0.8225531631897226
    },
    {
      "epoch": 0.3721891961747221,
      "grad_norm": 1.109375,
      "learning_rate": 1.4489100284308018e-05,
      "loss": 0.6588228225708008,
      "step": 180,
      "token_acc": 0.8192937625626946
    },
    {
      "epoch": 0.3928663737399845,
      "grad_norm": 1.1953125,
      "learning_rate": 1.3880918526722497e-05,
      "loss": 0.6636178016662597,
      "step": 190,
      "token_acc": 0.8182313404409566
    },
    {
      "epoch": 0.41354355130524684,
      "grad_norm": 1.0703125,
      "learning_rate": 1.3255329678515959e-05,
      "loss": 0.6327512264251709,
      "step": 200,
      "token_acc": 0.8255940851586625
    },
    {
      "epoch": 0.43422072887050917,
      "grad_norm": 1.15625,
      "learning_rate": 1.2615139694437835e-05,
      "loss": 0.6687861442565918,
      "step": 210,
      "token_acc": 0.8168444004461097
    },
    {
      "epoch": 0.4548979064357715,
      "grad_norm": 1.171875,
      "learning_rate": 1.1963220019737691e-05,
      "loss": 0.6480214595794678,
      "step": 220,
      "token_acc": 0.8209949912628607
    },
    {
      "epoch": 0.4755750840010339,
      "grad_norm": 1.1328125,
      "learning_rate": 1.1302494710866859e-05,
      "loss": 0.6437870502471924,
      "step": 230,
      "token_acc": 0.8233039990630567
    },
    {
      "epoch": 0.4962522615662962,
      "grad_norm": 1.2109375,
      "learning_rate": 1.0635927320202928e-05,
      "loss": 0.6444666385650635,
      "step": 240,
      "token_acc": 0.8233064313791084
    },
    {
      "epoch": 0.5169294391315585,
      "grad_norm": NaN,
      "learning_rate": 9.966507603623125e-06,
      "loss": 0.6417760372161865,
      "step": 250,
      "token_acc": 0.8239854735118844
    },
    {
      "epoch": 0.5376066166968209,
      "grad_norm": 1.140625,
      "learning_rate": 9.297238110547075e-06,
      "loss": 0.6363988876342773,
      "step": 260,
      "token_acc": 0.8253960322908611
    },
    {
      "epoch": 0.5582837942620832,
      "grad_norm": 1.0390625,
      "learning_rate": 8.631120716596642e-06,
      "loss": 0.6291430950164795,
      "step": 270,
      "token_acc": 0.8267635377992593
    },
    {
      "epoch": 0.5789609718273455,
      "grad_norm": NaN,
      "learning_rate": 7.971143159278025e-06,
      "loss": 0.6549222946166993,
      "step": 280,
      "token_acc": 0.8202583345423531
    },
    {
      "epoch": 0.599638149392608,
      "grad_norm": 1.171875,
      "learning_rate": 7.320265637077473e-06,
      "loss": 0.6288355827331543,
      "step": 290,
      "token_acc": 0.8272131756443049
    },
    {
      "epoch": 0.6203153269578703,
      "grad_norm": 1.09375,
      "learning_rate": 6.681407532077895e-06,
      "loss": 0.6366195678710938,
      "step": 300,
      "token_acc": 0.8246204996799724
    },
    {
      "epoch": 0.6409925045231326,
      "grad_norm": 1.2265625,
      "learning_rate": 6.057434315649304e-06,
      "loss": 0.6529150485992432,
      "step": 310,
      "token_acc": 0.8214805383775918
    },
    {
      "epoch": 0.6616696820883949,
      "grad_norm": 1.125,
      "learning_rate": 5.451144695945116e-06,
      "loss": 0.6422211170196533,
      "step": 320,
      "token_acc": 0.8234491309794939
    },
    {
      "epoch": 0.6823468596536573,
      "grad_norm": 1.109375,
      "learning_rate": 4.865258064851579e-06,
      "loss": 0.6308234691619873,
      "step": 330,
      "token_acc": 0.8257183171934186
    },
    {
      "epoch": 0.7030240372189196,
      "grad_norm": 1.1953125,
      "learning_rate": 4.302402300694636e-06,
      "loss": 0.6352657794952392,
      "step": 340,
      "token_acc": 0.8245651251591005
    },
    {
      "epoch": 0.7237012147841819,
      "grad_norm": 1.1484375,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.6413043022155762,
      "step": 350,
      "token_acc": 0.8234804751669123
    },
    {
      "epoch": 0.7443783923494443,
      "grad_norm": 1.15625,
      "learning_rate": 3.2557670610626924e-06,
      "loss": 0.6614915370941162,
      "step": 360,
      "token_acc": 0.8185413597228922
    },
    {
      "epoch": 0.7650555699147067,
      "grad_norm": 1.1875,
      "learning_rate": 2.7766820604492474e-06,
      "loss": 0.6162252426147461,
      "step": 370,
      "token_acc": 0.8291887765179509
    },
    {
      "epoch": 0.785732747479969,
      "grad_norm": 1.21875,
      "learning_rate": 2.32999582035923e-06,
      "loss": 0.6416737556457519,
      "step": 380,
      "token_acc": 0.8251579582098943
    },
    {
      "epoch": 0.8064099250452313,
      "grad_norm": 1.0625,
      "learning_rate": 1.917711863362581e-06,
      "loss": 0.6319101333618165,
      "step": 390,
      "token_acc": 0.8257550774349528
    },
    {
      "epoch": 0.8270871026104937,
      "grad_norm": 1.1796875,
      "learning_rate": 1.5416794074090258e-06,
      "loss": 0.6236296653747558,
      "step": 400,
      "token_acc": 0.8279304274286109
    },
    {
      "epoch": 0.847764280175756,
      "grad_norm": 1.109375,
      "learning_rate": 1.2035850715275865e-06,
      "loss": 0.6315475940704346,
      "step": 410,
      "token_acc": 0.8259817088278696
    },
    {
      "epoch": 0.8684414577410183,
      "grad_norm": 1.15625,
      "learning_rate": 9.049453108312967e-07,
      "loss": 0.64545578956604,
      "step": 420,
      "token_acc": 0.8220505314986443
    },
    {
      "epoch": 0.8891186353062807,
      "grad_norm": 1.2265625,
      "learning_rate": 6.470996147584684e-07,
      "loss": 0.6390243530273437,
      "step": 430,
      "token_acc": 0.8245470650344368
    },
    {
      "epoch": 0.909795812871543,
      "grad_norm": 1.078125,
      "learning_rate": 4.3120449905836746e-07,
      "loss": 0.6486499309539795,
      "step": 440,
      "token_acc": 0.8215761843927472
    },
    {
      "epoch": 0.9304729904368054,
      "grad_norm": 1.1171875,
      "learning_rate": 2.5822831846912035e-07,
      "loss": 0.6450016021728515,
      "step": 450,
      "token_acc": 0.8231799966516982
    },
    {
      "epoch": 0.9511501680020678,
      "grad_norm": 1.1015625,
      "learning_rate": 1.2894692335451376e-07,
      "loss": 0.6580901145935059,
      "step": 460,
      "token_acc": 0.8195172223593108
    },
    {
      "epoch": 0.9718273455673301,
      "grad_norm": 1.1171875,
      "learning_rate": 4.394017978101905e-08,
      "loss": 0.6284302234649658,
      "step": 470,
      "token_acc": 0.8261059191431867
    },
    {
      "epoch": 0.9925045231325924,
      "grad_norm": 1.09375,
      "learning_rate": 3.5893686435028995e-09,
      "loss": 0.637957763671875,
      "step": 480,
      "token_acc": 0.8241242127369184
    }
  ],
  "logging_steps": 10,
  "max_steps": 484,
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.135171100255191e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}