{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13461214874642435,
  "eval_steps": 500,
  "global_step": 800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016826518593303045,
      "grad_norm": 3.75418950341011,
      "learning_rate": 4.9999999999999996e-06,
      "loss": 0.9983,
      "step": 10
    },
    {
      "epoch": 0.003365303718660609,
      "grad_norm": 4.027030925274863,
      "learning_rate": 9.999999999999999e-06,
      "loss": 0.9697,
      "step": 20
    },
    {
      "epoch": 0.005047955577990914,
      "grad_norm": 4.048987349136423,
      "learning_rate": 1.5e-05,
      "loss": 0.9412,
      "step": 30
    },
    {
      "epoch": 0.006730607437321218,
      "grad_norm": 5.720158971431411,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.8783,
      "step": 40
    },
    {
      "epoch": 0.008413259296651522,
      "grad_norm": 4.718965032869529,
      "learning_rate": 2.5e-05,
      "loss": 0.8454,
      "step": 50
    },
    {
      "epoch": 0.010095911155981827,
      "grad_norm": 3.5785181087788835,
      "learning_rate": 3e-05,
      "loss": 0.809,
      "step": 60
    },
    {
      "epoch": 0.011778563015312132,
      "grad_norm": 4.11981684712826,
      "learning_rate": 2.9999786123888308e-05,
      "loss": 0.7556,
      "step": 70
    },
    {
      "epoch": 0.013461214874642436,
      "grad_norm": 6.082559649594005,
      "learning_rate": 2.9999144501652298e-05,
      "loss": 0.7613,
      "step": 80
    },
    {
      "epoch": 0.01514386673397274,
      "grad_norm": 1.957553999291205,
      "learning_rate": 2.9998075151588992e-05,
      "loss": 0.7784,
      "step": 90
    },
    {
      "epoch": 0.016826518593303044,
      "grad_norm": 1.6706087540201593,
      "learning_rate": 2.999657810419285e-05,
      "loss": 0.7658,
      "step": 100
    },
    {
      "epoch": 0.01850917045263335,
      "grad_norm": 2.909734954037323,
      "learning_rate": 2.999465340215489e-05,
      "loss": 0.7331,
      "step": 110
    },
    {
      "epoch": 0.020191822311963654,
      "grad_norm": 1.977272298268717,
      "learning_rate": 2.999230110036149e-05,
      "loss": 0.7507,
      "step": 120
    },
    {
      "epoch": 0.02187447417129396,
      "grad_norm": 1.8089524113272115,
      "learning_rate": 2.99895212658928e-05,
      "loss": 0.7309,
      "step": 130
    },
    {
      "epoch": 0.023557126030624265,
      "grad_norm": 2.134962179309057,
      "learning_rate": 2.9986313978020846e-05,
      "loss": 0.721,
      "step": 140
    },
    {
      "epoch": 0.02523977788995457,
      "grad_norm": 11.10353091330302,
      "learning_rate": 2.9982679328207262e-05,
      "loss": 0.7338,
      "step": 150
    },
    {
      "epoch": 0.02692242974928487,
      "grad_norm": 1.4444344817739057,
      "learning_rate": 2.9978617420100692e-05,
      "loss": 0.7227,
      "step": 160
    },
    {
      "epoch": 0.028605081608615177,
      "grad_norm": 1.453288161439029,
      "learning_rate": 2.9974128369533805e-05,
      "loss": 0.7107,
      "step": 170
    },
    {
      "epoch": 0.03028773346794548,
      "grad_norm": 3.475164856876678,
      "learning_rate": 2.9969212304520034e-05,
      "loss": 0.7303,
      "step": 180
    },
    {
      "epoch": 0.03197038532727579,
      "grad_norm": 1.1636824531496957,
      "learning_rate": 2.9963869365249895e-05,
      "loss": 0.6688,
      "step": 190
    },
    {
      "epoch": 0.03365303718660609,
      "grad_norm": 1.8518695174363622,
      "learning_rate": 2.995809970408699e-05,
      "loss": 0.7003,
      "step": 200
    },
    {
      "epoch": 0.0353356890459364,
      "grad_norm": 4.09791760479377,
      "learning_rate": 2.9951903485563685e-05,
      "loss": 0.7442,
      "step": 210
    },
    {
      "epoch": 0.0370183409052667,
      "grad_norm": 2.4987929291159956,
      "learning_rate": 2.99452808863764e-05,
      "loss": 0.7517,
      "step": 220
    },
    {
      "epoch": 0.03870099276459701,
      "grad_norm": 3.4584802037194087,
      "learning_rate": 2.993823209538056e-05,
      "loss": 0.7537,
      "step": 230
    },
    {
      "epoch": 0.04038364462392731,
      "grad_norm": 2.511130636368107,
      "learning_rate": 2.9930757313585238e-05,
      "loss": 0.7599,
      "step": 240
    },
    {
      "epoch": 0.04206629648325761,
      "grad_norm": 1.7030446444812277,
      "learning_rate": 2.9922856754147406e-05,
      "loss": 0.7126,
      "step": 250
    },
    {
      "epoch": 0.04374894834258792,
      "grad_norm": 4.790377413030976,
      "learning_rate": 2.9914530642365852e-05,
      "loss": 0.72,
      "step": 260
    },
    {
      "epoch": 0.04543160020191822,
      "grad_norm": 2.0321244924961976,
      "learning_rate": 2.990577921567476e-05,
      "loss": 0.6733,
      "step": 270
    },
    {
      "epoch": 0.04711425206124853,
      "grad_norm": 2.310370624749643,
      "learning_rate": 2.989660272363696e-05,
      "loss": 0.7212,
      "step": 280
    },
    {
      "epoch": 0.04879690392057883,
      "grad_norm": 3.451763592410144,
      "learning_rate": 2.988700142793676e-05,
      "loss": 0.7237,
      "step": 290
    },
    {
      "epoch": 0.05047955577990914,
      "grad_norm": 5.317302731978485,
      "learning_rate": 2.9876975602372536e-05,
      "loss": 0.7558,
      "step": 300
    },
    {
      "epoch": 0.05216220763923944,
      "grad_norm": 2.3026448136142914,
      "learning_rate": 2.9866525532848906e-05,
      "loss": 0.6985,
      "step": 310
    },
    {
      "epoch": 0.05384485949856974,
      "grad_norm": 1.8320545447196381,
      "learning_rate": 2.9855651517368567e-05,
      "loss": 0.7227,
      "step": 320
    },
    {
      "epoch": 0.05552751135790005,
      "grad_norm": 1.9908218789466392,
      "learning_rate": 2.9844353866023802e-05,
      "loss": 0.7075,
      "step": 330
    },
    {
      "epoch": 0.05721016321723035,
      "grad_norm": 5.182840115712529,
      "learning_rate": 2.9832632900987642e-05,
      "loss": 0.7207,
      "step": 340
    },
    {
      "epoch": 0.05889281507656066,
      "grad_norm": 1.5483797249278837,
      "learning_rate": 2.982048895650468e-05,
      "loss": 0.7233,
      "step": 350
    },
    {
      "epoch": 0.06057546693589096,
      "grad_norm": 2.3382590504722693,
      "learning_rate": 2.9807922378881537e-05,
      "loss": 0.7002,
      "step": 360
    },
    {
      "epoch": 0.06225811879522127,
      "grad_norm": 3.1859655239636937,
      "learning_rate": 2.979493352647697e-05,
      "loss": 0.7201,
      "step": 370
    },
    {
      "epoch": 0.06394077065455157,
      "grad_norm": 0.9149159742557087,
      "learning_rate": 2.9781522769691686e-05,
      "loss": 0.7136,
      "step": 380
    },
    {
      "epoch": 0.06562342251388188,
      "grad_norm": 10.861566072795899,
      "learning_rate": 2.9767690490957758e-05,
      "loss": 0.7068,
      "step": 390
    },
    {
      "epoch": 0.06730607437321218,
      "grad_norm": 2.8618866775651006,
      "learning_rate": 2.9753437084727713e-05,
      "loss": 0.7239,
      "step": 400
    },
    {
      "epoch": 0.06898872623254249,
      "grad_norm": 2.8726068570785097,
      "learning_rate": 2.9738762957463292e-05,
      "loss": 0.7245,
      "step": 410
    },
    {
      "epoch": 0.0706713780918728,
      "grad_norm": 2.4481298042739112,
      "learning_rate": 2.9723668527623877e-05,
      "loss": 0.7752,
      "step": 420
    },
    {
      "epoch": 0.0723540299512031,
      "grad_norm": 1.8599931346602536,
      "learning_rate": 2.9708154225654526e-05,
      "loss": 0.7323,
      "step": 430
    },
    {
      "epoch": 0.0740366818105334,
      "grad_norm": 1.2855737813743626,
      "learning_rate": 2.9692220493973712e-05,
      "loss": 0.7037,
      "step": 440
    },
    {
      "epoch": 0.0757193336698637,
      "grad_norm": 4.629091463528233,
      "learning_rate": 2.9675867786960718e-05,
      "loss": 0.6867,
      "step": 450
    },
    {
      "epoch": 0.07740198552919401,
      "grad_norm": 6.294427059845777,
      "learning_rate": 2.9659096570942654e-05,
      "loss": 0.7272,
      "step": 460
    },
    {
      "epoch": 0.07908463738852431,
      "grad_norm": 2.4758348810051345,
      "learning_rate": 2.9641907324181194e-05,
      "loss": 0.6779,
      "step": 470
    },
    {
      "epoch": 0.08076728924785462,
      "grad_norm": 1.3455245255212915,
      "learning_rate": 2.96243005368589e-05,
      "loss": 0.7051,
      "step": 480
    },
    {
      "epoch": 0.08244994110718493,
      "grad_norm": 4.796150475871981,
      "learning_rate": 2.960627671106527e-05,
      "loss": 0.7547,
      "step": 490
    },
    {
      "epoch": 0.08413259296651522,
      "grad_norm": 2.684441445075641,
      "learning_rate": 2.9587836360782405e-05,
      "loss": 0.709,
      "step": 500
    },
    {
      "epoch": 0.08581524482584553,
      "grad_norm": 1.3869329152815553,
      "learning_rate": 2.9568980011870357e-05,
      "loss": 0.7073,
      "step": 510
    },
    {
      "epoch": 0.08749789668517584,
      "grad_norm": 2.5576974478207197,
      "learning_rate": 2.954970820205214e-05,
      "loss": 0.6918,
      "step": 520
    },
    {
      "epoch": 0.08918054854450615,
      "grad_norm": 1.1525450967004647,
      "learning_rate": 2.9530021480898393e-05,
      "loss": 0.6698,
      "step": 530
    },
    {
      "epoch": 0.09086320040383644,
      "grad_norm": 2.847083851829901,
      "learning_rate": 2.9509920409811696e-05,
      "loss": 0.671,
      "step": 540
    },
    {
      "epoch": 0.09254585226316675,
      "grad_norm": 2.561042091789346,
      "learning_rate": 2.9489405562010565e-05,
      "loss": 0.75,
      "step": 550
    },
    {
      "epoch": 0.09422850412249706,
      "grad_norm": 4.458337350053255,
      "learning_rate": 2.9468477522513132e-05,
      "loss": 0.7277,
      "step": 560
    },
    {
      "epoch": 0.09591115598182735,
      "grad_norm": 3.114622509219852,
      "learning_rate": 2.9447136888120408e-05,
      "loss": 0.6967,
      "step": 570
    },
    {
      "epoch": 0.09759380784115766,
      "grad_norm": 1.6295210229360877,
      "learning_rate": 2.9425384267399327e-05,
      "loss": 0.6867,
      "step": 580
    },
    {
      "epoch": 0.09927645970048797,
      "grad_norm": 1.7579117810504754,
      "learning_rate": 2.940322028066534e-05,
      "loss": 0.7236,
      "step": 590
    },
    {
      "epoch": 0.10095911155981828,
      "grad_norm": 1.788183804411441,
      "learning_rate": 2.938064555996476e-05,
      "loss": 0.6864,
      "step": 600
    },
    {
      "epoch": 0.10264176341914857,
      "grad_norm": 2.8340511721646373,
      "learning_rate": 2.9357660749056713e-05,
      "loss": 0.6847,
      "step": 610
    },
    {
      "epoch": 0.10432441527847888,
      "grad_norm": 2.5230840193297985,
      "learning_rate": 2.9334266503394803e-05,
      "loss": 0.6889,
      "step": 620
    },
    {
      "epoch": 0.10600706713780919,
      "grad_norm": 7.346086885083334,
      "learning_rate": 2.9310463490108397e-05,
      "loss": 0.7419,
      "step": 630
    },
    {
      "epoch": 0.10768971899713949,
      "grad_norm": 2.356832890545339,
      "learning_rate": 2.928625238798362e-05,
      "loss": 0.7369,
      "step": 640
    },
    {
      "epoch": 0.1093723708564698,
      "grad_norm": 2.4978380391841095,
      "learning_rate": 2.9261633887443993e-05,
      "loss": 0.6948,
      "step": 650
    },
    {
      "epoch": 0.1110550227158001,
      "grad_norm": 3.535487375505793,
      "learning_rate": 2.9236608690530738e-05,
      "loss": 0.7081,
      "step": 660
    },
    {
      "epoch": 0.11273767457513041,
      "grad_norm": 2.522638625540884,
      "learning_rate": 2.921117751088276e-05,
      "loss": 0.7191,
      "step": 670
    },
    {
      "epoch": 0.1144203264344607,
      "grad_norm": 3.055823541699581,
      "learning_rate": 2.91853410737163e-05,
      "loss": 0.74,
      "step": 680
    },
    {
      "epoch": 0.11610297829379101,
      "grad_norm": 3.270117047516123,
      "learning_rate": 2.915910011580426e-05,
      "loss": 0.6829,
      "step": 690
    },
    {
      "epoch": 0.11778563015312132,
      "grad_norm": 2.3219806056695367,
      "learning_rate": 2.9132455385455176e-05,
      "loss": 0.7062,
      "step": 700
    },
    {
      "epoch": 0.11946828201245162,
      "grad_norm": 1.541921603113568,
      "learning_rate": 2.9105407642491895e-05,
      "loss": 0.7217,
      "step": 710
    },
    {
      "epoch": 0.12115093387178193,
      "grad_norm": 1.557595298876376,
      "learning_rate": 2.907795765822989e-05,
      "loss": 0.7083,
      "step": 720
    },
    {
      "epoch": 0.12283358573111224,
      "grad_norm": 2.3829156571868753,
      "learning_rate": 2.9050106215455283e-05,
      "loss": 0.6992,
      "step": 730
    },
    {
      "epoch": 0.12451623759044254,
      "grad_norm": 7.536777098548366,
      "learning_rate": 2.9021854108402516e-05,
      "loss": 0.7248,
      "step": 740
    },
    {
      "epoch": 0.12619888944977284,
      "grad_norm": 1.3408030642895519,
      "learning_rate": 2.8993202142731693e-05,
      "loss": 0.6375,
      "step": 750
    },
    {
      "epoch": 0.12788154130910315,
      "grad_norm": 2.4880776314537254,
      "learning_rate": 2.8964151135505616e-05,
      "loss": 0.7063,
      "step": 760
    },
    {
      "epoch": 0.12956419316843346,
      "grad_norm": 1.5507053769862247,
      "learning_rate": 2.8934701915166477e-05,
      "loss": 0.73,
      "step": 770
    },
    {
      "epoch": 0.13124684502776376,
      "grad_norm": 3.5622930633942564,
      "learning_rate": 2.890485532151225e-05,
      "loss": 0.7521,
      "step": 780
    },
    {
      "epoch": 0.13292949688709407,
      "grad_norm": 4.188153799459233,
      "learning_rate": 2.887461220567271e-05,
      "loss": 0.6841,
      "step": 790
    },
    {
      "epoch": 0.13461214874642435,
      "grad_norm": 2.702901312773331,
      "learning_rate": 2.8843973430085204e-05,
      "loss": 0.694,
      "step": 800
    }
  ],
  "logging_steps": 10,
  "max_steps": 5943,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.644760786993152e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}