{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 5000.0,
  "global_step": 741,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01349527665317139,
      "grad_norm": 7.016904524087463,
      "learning_rate": 8.695652173913043e-07,
      "loss": 1.1369,
      "step": 10
    },
    {
      "epoch": 0.02699055330634278,
      "grad_norm": 4.2020279077827905,
      "learning_rate": 1.7391304347826085e-06,
      "loss": 1.0452,
      "step": 20
    },
    {
      "epoch": 0.04048582995951417,
      "grad_norm": 3.441796090298099,
      "learning_rate": 1.999530989041473e-06,
      "loss": 0.9533,
      "step": 30
    },
    {
      "epoch": 0.05398110661268556,
      "grad_norm": 3.5191614427600753,
      "learning_rate": 1.9972348515341017e-06,
      "loss": 0.8914,
      "step": 40
    },
    {
      "epoch": 0.06747638326585695,
      "grad_norm": 2.9690875149374367,
      "learning_rate": 1.9930298323185945e-06,
      "loss": 0.8475,
      "step": 50
    },
    {
      "epoch": 0.08097165991902834,
      "grad_norm": 3.0556169559708475,
      "learning_rate": 1.986923980536286e-06,
      "loss": 0.8232,
      "step": 60
    },
    {
      "epoch": 0.09446693657219973,
      "grad_norm": 2.9704481548374653,
      "learning_rate": 1.9789289838540896e-06,
      "loss": 0.822,
      "step": 70
    },
    {
      "epoch": 0.10796221322537113,
      "grad_norm": 2.999043629121677,
      "learning_rate": 1.969060146092264e-06,
      "loss": 0.791,
      "step": 80
    },
    {
      "epoch": 0.1214574898785425,
      "grad_norm": 3.17575389006719,
      "learning_rate": 1.9573363579302263e-06,
      "loss": 0.806,
      "step": 90
    },
    {
      "epoch": 0.1349527665317139,
      "grad_norm": 2.9165449315999563,
      "learning_rate": 1.943780060746493e-06,
      "loss": 0.7961,
      "step": 100
    },
    {
      "epoch": 0.1484480431848853,
      "grad_norm": 2.952637325540401,
      "learning_rate": 1.928417203661959e-06,
      "loss": 0.7962,
      "step": 110
    },
    {
      "epoch": 0.16194331983805668,
      "grad_norm": 3.014781591451641,
      "learning_rate": 1.911277193868751e-06,
      "loss": 0.7781,
      "step": 120
    },
    {
      "epoch": 0.17543859649122806,
      "grad_norm": 2.8796052156819716,
      "learning_rate": 1.8923928403397207e-06,
      "loss": 0.776,
      "step": 130
    },
    {
      "epoch": 0.18893387314439947,
      "grad_norm": 2.8482523150497117,
      "learning_rate": 1.8718002910263424e-06,
      "loss": 0.7615,
      "step": 140
    },
    {
      "epoch": 0.20242914979757085,
      "grad_norm": 2.922903791793236,
      "learning_rate": 1.8495389636652184e-06,
      "loss": 0.7543,
      "step": 150
    },
    {
      "epoch": 0.21592442645074225,
      "grad_norm": 2.9536979340238547,
      "learning_rate": 1.8256514703256447e-06,
      "loss": 0.7598,
      "step": 160
    },
    {
      "epoch": 0.22941970310391363,
      "grad_norm": 3.1334920821882126,
      "learning_rate": 1.8001835358426684e-06,
      "loss": 0.7489,
      "step": 170
    },
    {
      "epoch": 0.242914979757085,
      "grad_norm": 3.2092630967068683,
      "learning_rate": 1.7731839102917642e-06,
      "loss": 0.7551,
      "step": 180
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 2.987735102823792,
      "learning_rate": 1.7447042756726754e-06,
      "loss": 0.7503,
      "step": 190
    },
    {
      "epoch": 0.2699055330634278,
      "grad_norm": 2.979147030983217,
      "learning_rate": 1.7147991469810365e-06,
      "loss": 0.7528,
      "step": 200
    },
    {
      "epoch": 0.2834008097165992,
      "grad_norm": 3.1413426729820904,
      "learning_rate": 1.6835257678571512e-06,
      "loss": 0.7387,
      "step": 210
    },
    {
      "epoch": 0.2968960863697706,
      "grad_norm": 3.1214265634728897,
      "learning_rate": 1.650944001011663e-06,
      "loss": 0.7281,
      "step": 220
    },
    {
      "epoch": 0.31039136302294196,
      "grad_norm": 2.978380133818548,
      "learning_rate": 1.6171162136378713e-06,
      "loss": 0.7514,
      "step": 230
    },
    {
      "epoch": 0.32388663967611336,
      "grad_norm": 2.85376146602686,
      "learning_rate": 1.5821071580300269e-06,
      "loss": 0.7403,
      "step": 240
    },
    {
      "epoch": 0.33738191632928477,
      "grad_norm": 3.1598761470719734,
      "learning_rate": 1.5459838476361322e-06,
      "loss": 0.7435,
      "step": 250
    },
    {
      "epoch": 0.3508771929824561,
      "grad_norm": 2.821356522721463,
      "learning_rate": 1.5088154287824932e-06,
      "loss": 0.7209,
      "step": 260
    },
    {
      "epoch": 0.3643724696356275,
      "grad_norm": 2.98057980294587,
      "learning_rate": 1.4706730483155736e-06,
      "loss": 0.7311,
      "step": 270
    },
    {
      "epoch": 0.37786774628879893,
      "grad_norm": 3.0364233244848364,
      "learning_rate": 1.4316297174145016e-06,
      "loss": 0.7282,
      "step": 280
    },
    {
      "epoch": 0.3913630229419703,
      "grad_norm": 2.949886690990857,
      "learning_rate": 1.391760171834918e-06,
      "loss": 0.7078,
      "step": 290
    },
    {
      "epoch": 0.4048582995951417,
      "grad_norm": 2.9507364249680053,
      "learning_rate": 1.3511407288516878e-06,
      "loss": 0.7201,
      "step": 300
    },
    {
      "epoch": 0.4183535762483131,
      "grad_norm": 2.827650772154331,
      "learning_rate": 1.3098491411743014e-06,
      "loss": 0.7147,
      "step": 310
    },
    {
      "epoch": 0.4318488529014845,
      "grad_norm": 2.8781557252440635,
      "learning_rate": 1.267964448114608e-06,
      "loss": 0.7295,
      "step": 320
    },
    {
      "epoch": 0.44534412955465585,
      "grad_norm": 2.952298995368144,
      "learning_rate": 1.2255668242917648e-06,
      "loss": 0.724,
      "step": 330
    },
    {
      "epoch": 0.45883940620782726,
      "grad_norm": 3.121925726144687,
      "learning_rate": 1.1827374261640126e-06,
      "loss": 0.697,
      "step": 340
    },
    {
      "epoch": 0.47233468286099867,
      "grad_norm": 2.852801476396792,
      "learning_rate": 1.1395582366810346e-06,
      "loss": 0.718,
      "step": 350
    },
    {
      "epoch": 0.48582995951417,
      "grad_norm": 3.0303857364861955,
      "learning_rate": 1.0961119083542726e-06,
      "loss": 0.7197,
      "step": 360
    },
    {
      "epoch": 0.4993252361673414,
      "grad_norm": 3.166667043296761,
      "learning_rate": 1.05248160504558e-06,
      "loss": 0.7091,
      "step": 370
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 2.906467539598673,
      "learning_rate": 1.0087508427770638e-06,
      "loss": 0.6934,
      "step": 380
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 3.02782546633098,
      "learning_rate": 9.650033298668279e-07,
      "loss": 0.7025,
      "step": 390
    },
    {
      "epoch": 0.5398110661268556,
      "grad_norm": 2.8912523592077637,
      "learning_rate": 9.213228066966326e-07,
      "loss": 0.7033,
      "step": 400
    },
    {
      "epoch": 0.553306342780027,
      "grad_norm": 2.82347772754047,
      "learning_rate": 8.777928854181709e-07,
      "loss": 0.7,
      "step": 410
    },
    {
      "epoch": 0.5668016194331984,
      "grad_norm": 2.9229669660658293,
      "learning_rate": 8.344968899048091e-07,
      "loss": 0.7022,
      "step": 420
    },
    {
      "epoch": 0.5802968960863698,
      "grad_norm": 3.1576009691196707,
      "learning_rate": 7.915176962551347e-07,
      "loss": 0.7037,
      "step": 430
    },
    {
      "epoch": 0.5937921727395412,
      "grad_norm": 3.1084612640931173,
      "learning_rate": 7.489375741536281e-07,
      "loss": 0.7073,
      "step": 440
    },
    {
      "epoch": 0.6072874493927125,
      "grad_norm": 2.9866909336253595,
      "learning_rate": 7.068380293921141e-07,
      "loss": 0.6877,
      "step": 450
    },
    {
      "epoch": 0.6207827260458839,
      "grad_norm": 2.8444556383038053,
      "learning_rate": 6.652996478534394e-07,
      "loss": 0.6996,
      "step": 460
    },
    {
      "epoch": 0.6342780026990553,
      "grad_norm": 3.073223609545424,
      "learning_rate": 6.244019412560143e-07,
      "loss": 0.6941,
      "step": 470
    },
    {
      "epoch": 0.6477732793522267,
      "grad_norm": 2.8831703732503753,
      "learning_rate": 5.842231949544962e-07,
      "loss": 0.7049,
      "step": 480
    },
    {
      "epoch": 0.6612685560053981,
      "grad_norm": 3.060533732204664,
      "learning_rate": 5.448403180879439e-07,
      "loss": 0.679,
      "step": 490
    },
    {
      "epoch": 0.6747638326585695,
      "grad_norm": 2.9803982323010585,
      "learning_rate": 5.063286963622902e-07,
      "loss": 0.6972,
      "step": 500
    },
    {
      "epoch": 0.6882591093117408,
      "grad_norm": 2.8648873659535794,
      "learning_rate": 4.687620477489337e-07,
      "loss": 0.6894,
      "step": 510
    },
    {
      "epoch": 0.7017543859649122,
      "grad_norm": 2.8594131054352054,
      "learning_rate": 4.3221228137566223e-07,
      "loss": 0.6984,
      "step": 520
    },
    {
      "epoch": 0.7152496626180836,
      "grad_norm": 2.826483265916211,
      "learning_rate": 3.9674935988002325e-07,
      "loss": 0.6806,
      "step": 530
    },
    {
      "epoch": 0.728744939271255,
      "grad_norm": 3.0466631136136875,
      "learning_rate": 3.624411654886108e-07,
      "loss": 0.7028,
      "step": 540
    },
    {
      "epoch": 0.7422402159244265,
      "grad_norm": 2.8395840111896806,
      "learning_rate": 3.293533700786286e-07,
      "loss": 0.6966,
      "step": 550
    },
    {
      "epoch": 0.7557354925775979,
      "grad_norm": 2.9054816392819154,
      "learning_rate": 2.975493094704435e-07,
      "loss": 0.6908,
      "step": 560
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 2.9460246471571345,
      "learning_rate": 2.670898621917629e-07,
      "loss": 0.6947,
      "step": 570
    },
    {
      "epoch": 0.7827260458839406,
      "grad_norm": 2.941971675288718,
      "learning_rate": 2.3803333294549644e-07,
      "loss": 0.6795,
      "step": 580
    },
    {
      "epoch": 0.796221322537112,
      "grad_norm": 3.0680540747802527,
      "learning_rate": 2.104353410043712e-07,
      "loss": 0.6743,
      "step": 590
    },
    {
      "epoch": 0.8097165991902834,
      "grad_norm": 3.1007189679330374,
      "learning_rate": 1.843487137459261e-07,
      "loss": 0.6941,
      "step": 600
    },
    {
      "epoch": 0.8232118758434548,
      "grad_norm": 2.8712948349597625,
      "learning_rate": 1.598233855316856e-07,
      "loss": 0.6827,
      "step": 610
    },
    {
      "epoch": 0.8367071524966262,
      "grad_norm": 3.028709196939323,
      "learning_rate": 1.369063021240665e-07,
      "loss": 0.7058,
      "step": 620
    },
    {
      "epoch": 0.8502024291497976,
      "grad_norm": 2.8663884949478655,
      "learning_rate": 1.1564133082398942e-07,
      "loss": 0.6926,
      "step": 630
    },
    {
      "epoch": 0.863697705802969,
      "grad_norm": 2.7965685313183983,
      "learning_rate": 9.606917650120083e-08,
      "loss": 0.6902,
      "step": 640
    },
    {
      "epoch": 0.8771929824561403,
      "grad_norm": 2.9702187500416426,
      "learning_rate": 7.822730367804331e-08,
      "loss": 0.6809,
      "step": 650
    },
    {
      "epoch": 0.8906882591093117,
      "grad_norm": 2.9740711603347534,
      "learning_rate": 6.214986481581364e-08,
      "loss": 0.6846,
      "step": 660
    },
    {
      "epoch": 0.9041835357624831,
      "grad_norm": 3.108653359820244,
      "learning_rate": 4.786763494098689e-08,
      "loss": 0.6845,
      "step": 670
    },
    {
      "epoch": 0.9176788124156545,
      "grad_norm": 3.0730509775220005,
      "learning_rate": 3.540795273643926e-08,
      "loss": 0.6942,
      "step": 680
    },
    {
      "epoch": 0.9311740890688259,
      "grad_norm": 2.8851954067191885,
      "learning_rate": 2.479466821043419e-08,
      "loss": 0.6858,
      "step": 690
    },
    {
      "epoch": 0.9446693657219973,
      "grad_norm": 2.7753430457192816,
      "learning_rate": 1.604809704353949e-08,
      "loss": 0.6911,
      "step": 700
    },
    {
      "epoch": 0.9581646423751687,
      "grad_norm": 2.894348481910036,
      "learning_rate": 9.184981700866346e-09,
      "loss": 0.6892,
      "step": 710
    },
    {
      "epoch": 0.97165991902834,
      "grad_norm": 2.9242281390477505,
      "learning_rate": 4.218459384065953e-09,
      "loss": 0.6878,
      "step": 720
    },
    {
      "epoch": 0.9851551956815114,
      "grad_norm": 3.0382180715715568,
      "learning_rate": 1.1580368844316125e-09,
      "loss": 0.6897,
      "step": 730
    },
    {
      "epoch": 0.9986504723346828,
      "grad_norm": 3.0414366034886235,
      "learning_rate": 9.572385238243441e-12,
      "loss": 0.6865,
      "step": 740
    }
  ],
  "logging_steps": 10,
  "max_steps": 741,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 350,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.306076234857578e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}