{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.4926905132192845,
  "eval_steps": 500,
  "global_step": 1000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.024883359253499222,
      "grad_norm": 6.788532733917236,
      "learning_rate": 4.5e-06,
      "loss": 1.2189,
      "step": 10
    },
    {
      "epoch": 0.049766718506998445,
      "grad_norm": 1.3378803730010986,
      "learning_rate": 9.5e-06,
      "loss": 0.6193,
      "step": 20
    },
    {
      "epoch": 0.07465007776049767,
      "grad_norm": 0.7917852997779846,
      "learning_rate": 1.45e-05,
      "loss": 0.231,
      "step": 30
    },
    {
      "epoch": 0.09953343701399689,
      "grad_norm": 0.7099640965461731,
      "learning_rate": 1.9500000000000003e-05,
      "loss": 0.1463,
      "step": 40
    },
    {
      "epoch": 0.12441679626749612,
      "grad_norm": 0.686485230922699,
      "learning_rate": 2.45e-05,
      "loss": 0.108,
      "step": 50
    },
    {
      "epoch": 0.14930015552099535,
      "grad_norm": 0.4254772961139679,
      "learning_rate": 2.95e-05,
      "loss": 0.0878,
      "step": 60
    },
    {
      "epoch": 0.17418351477449456,
      "grad_norm": 0.41301316022872925,
      "learning_rate": 3.45e-05,
      "loss": 0.0733,
      "step": 70
    },
    {
      "epoch": 0.19906687402799378,
      "grad_norm": 0.5910139679908752,
      "learning_rate": 3.9500000000000005e-05,
      "loss": 0.0654,
      "step": 80
    },
    {
      "epoch": 0.223950233281493,
      "grad_norm": 0.4281249940395355,
      "learning_rate": 4.4500000000000004e-05,
      "loss": 0.0621,
      "step": 90
    },
    {
      "epoch": 0.24883359253499224,
      "grad_norm": 0.33288511633872986,
      "learning_rate": 4.9500000000000004e-05,
      "loss": 0.0528,
      "step": 100
    },
    {
      "epoch": 0.2737169517884914,
      "grad_norm": 0.3627478778362274,
      "learning_rate": 5.45e-05,
      "loss": 0.0511,
      "step": 110
    },
    {
      "epoch": 0.2986003110419907,
      "grad_norm": 0.3620380461215973,
      "learning_rate": 5.95e-05,
      "loss": 0.0467,
      "step": 120
    },
    {
      "epoch": 0.3234836702954899,
      "grad_norm": 0.37019455432891846,
      "learning_rate": 6.450000000000001e-05,
      "loss": 0.0444,
      "step": 130
    },
    {
      "epoch": 0.3483670295489891,
      "grad_norm": 0.44425082206726074,
      "learning_rate": 6.95e-05,
      "loss": 0.0413,
      "step": 140
    },
    {
      "epoch": 0.37325038880248834,
      "grad_norm": 0.3729994297027588,
      "learning_rate": 7.450000000000001e-05,
      "loss": 0.0395,
      "step": 150
    },
    {
      "epoch": 0.39813374805598756,
      "grad_norm": 0.25299033522605896,
      "learning_rate": 7.950000000000001e-05,
      "loss": 0.0375,
      "step": 160
    },
    {
      "epoch": 0.4230171073094868,
      "grad_norm": 0.24479390680789948,
      "learning_rate": 8.450000000000001e-05,
      "loss": 0.0336,
      "step": 170
    },
    {
      "epoch": 0.447900466562986,
      "grad_norm": 0.4071142375469208,
      "learning_rate": 8.950000000000001e-05,
      "loss": 0.0316,
      "step": 180
    },
    {
      "epoch": 0.4727838258164852,
      "grad_norm": 0.40290141105651855,
      "learning_rate": 9.449999999999999e-05,
      "loss": 0.0331,
      "step": 190
    },
    {
      "epoch": 0.4976671850699845,
      "grad_norm": 0.38158151507377625,
      "learning_rate": 9.95e-05,
      "loss": 0.0311,
      "step": 200
    },
    {
      "epoch": 0.5225505443234837,
      "grad_norm": 0.29570913314819336,
      "learning_rate": 9.999861593790126e-05,
      "loss": 0.0291,
      "step": 210
    },
    {
      "epoch": 0.5474339035769828,
      "grad_norm": 0.37690913677215576,
      "learning_rate": 9.999383162408304e-05,
      "loss": 0.0277,
      "step": 220
    },
    {
      "epoch": 0.5723172628304821,
      "grad_norm": 0.3893811106681824,
      "learning_rate": 9.998563029828259e-05,
      "loss": 0.028,
      "step": 230
    },
    {
      "epoch": 0.5972006220839814,
      "grad_norm": 0.3241683542728424,
      "learning_rate": 9.997401252104962e-05,
      "loss": 0.0267,
      "step": 240
    },
    {
      "epoch": 0.6220839813374806,
      "grad_norm": 0.31424349546432495,
      "learning_rate": 9.995897908644378e-05,
      "loss": 0.0268,
      "step": 250
    },
    {
      "epoch": 0.6469673405909798,
      "grad_norm": 0.2265535593032837,
      "learning_rate": 9.994053102198034e-05,
      "loss": 0.0257,
      "step": 260
    },
    {
      "epoch": 0.671850699844479,
      "grad_norm": 0.352764368057251,
      "learning_rate": 9.991866958856003e-05,
      "loss": 0.0244,
      "step": 270
    },
    {
      "epoch": 0.6967340590979783,
      "grad_norm": 0.29578715562820435,
      "learning_rate": 9.989339628038276e-05,
      "loss": 0.0224,
      "step": 280
    },
    {
      "epoch": 0.7216174183514774,
      "grad_norm": 0.36025872826576233,
      "learning_rate": 9.98647128248456e-05,
      "loss": 0.0231,
      "step": 290
    },
    {
      "epoch": 0.7465007776049767,
      "grad_norm": 0.31710195541381836,
      "learning_rate": 9.98326211824246e-05,
      "loss": 0.0247,
      "step": 300
    },
    {
      "epoch": 0.7713841368584758,
      "grad_norm": 0.28732505440711975,
      "learning_rate": 9.979712354654091e-05,
      "loss": 0.0224,
      "step": 310
    },
    {
      "epoch": 0.7962674961119751,
      "grad_norm": 0.21972423791885376,
      "learning_rate": 9.975822234341079e-05,
      "loss": 0.0211,
      "step": 320
    },
    {
      "epoch": 0.8211508553654744,
      "grad_norm": 0.22749976813793182,
      "learning_rate": 9.97159202318798e-05,
      "loss": 0.0201,
      "step": 330
    },
    {
      "epoch": 0.8460342146189735,
      "grad_norm": 0.3257753551006317,
      "learning_rate": 9.967022010324105e-05,
      "loss": 0.0218,
      "step": 340
    },
    {
      "epoch": 0.8709175738724728,
      "grad_norm": 0.2250833660364151,
      "learning_rate": 9.962112508103765e-05,
      "loss": 0.0192,
      "step": 350
    },
    {
      "epoch": 0.895800933125972,
      "grad_norm": 0.3466697335243225,
      "learning_rate": 9.956863852084914e-05,
      "loss": 0.0194,
      "step": 360
    },
    {
      "epoch": 0.9206842923794712,
      "grad_norm": 0.3127228319644928,
      "learning_rate": 9.951276401006221e-05,
      "loss": 0.0207,
      "step": 370
    },
    {
      "epoch": 0.9455676516329704,
      "grad_norm": 0.2664047181606293,
      "learning_rate": 9.945350536762543e-05,
      "loss": 0.0194,
      "step": 380
    },
    {
      "epoch": 0.9704510108864697,
      "grad_norm": 0.2534600794315338,
      "learning_rate": 9.939086664378829e-05,
      "loss": 0.0203,
      "step": 390
    },
    {
      "epoch": 0.995334370139969,
      "grad_norm": 0.2339852750301361,
      "learning_rate": 9.932485211982437e-05,
      "loss": 0.0193,
      "step": 400
    },
    {
      "epoch": 1.0223950233281494,
      "grad_norm": 0.2680792212486267,
      "learning_rate": 9.92554663077387e-05,
      "loss": 0.0188,
      "step": 410
    },
    {
      "epoch": 1.0472783825816485,
      "grad_norm": 0.22340402007102966,
      "learning_rate": 9.918271394995935e-05,
      "loss": 0.0175,
      "step": 420
    },
    {
      "epoch": 1.0721617418351477,
      "grad_norm": 0.22573307156562805,
      "learning_rate": 9.910660001901335e-05,
      "loss": 0.0191,
      "step": 430
    },
    {
      "epoch": 1.097045101088647,
      "grad_norm": 0.16532698273658752,
      "learning_rate": 9.902712971718675e-05,
      "loss": 0.0189,
      "step": 440
    },
    {
      "epoch": 1.1219284603421462,
      "grad_norm": 0.26129794120788574,
      "learning_rate": 9.894430847616915e-05,
      "loss": 0.0191,
      "step": 450
    },
    {
      "epoch": 1.1468118195956454,
      "grad_norm": 0.2564263939857483,
      "learning_rate": 9.885814195668232e-05,
      "loss": 0.0184,
      "step": 460
    },
    {
      "epoch": 1.1716951788491445,
      "grad_norm": 0.269545316696167,
      "learning_rate": 9.876863604809344e-05,
      "loss": 0.0202,
      "step": 470
    },
    {
      "epoch": 1.196578538102644,
      "grad_norm": 0.25393763184547424,
      "learning_rate": 9.867579686801245e-05,
      "loss": 0.0193,
      "step": 480
    },
    {
      "epoch": 1.221461897356143,
      "grad_norm": 0.26436880230903625,
      "learning_rate": 9.8579630761874e-05,
      "loss": 0.0184,
      "step": 490
    },
    {
      "epoch": 1.2463452566096422,
      "grad_norm": 0.1819346696138382,
      "learning_rate": 9.848014430250367e-05,
      "loss": 0.0182,
      "step": 500
    },
    {
      "epoch": 1.2712286158631416,
      "grad_norm": 0.26912328600883484,
      "learning_rate": 9.837734428966885e-05,
      "loss": 0.0177,
      "step": 510
    },
    {
      "epoch": 1.2961119751166408,
      "grad_norm": 0.32153385877609253,
      "learning_rate": 9.827123774961383e-05,
      "loss": 0.0181,
      "step": 520
    },
    {
      "epoch": 1.32099533437014,
      "grad_norm": 0.32203471660614014,
      "learning_rate": 9.816183193457968e-05,
      "loss": 0.0182,
      "step": 530
    },
    {
      "epoch": 1.3458786936236393,
      "grad_norm": 0.34882357716560364,
      "learning_rate": 9.804913432230856e-05,
      "loss": 0.0182,
      "step": 540
    },
    {
      "epoch": 1.3707620528771385,
      "grad_norm": 0.3095707297325134,
      "learning_rate": 9.793315261553252e-05,
      "loss": 0.0178,
      "step": 550
    },
    {
      "epoch": 1.3956454121306376,
      "grad_norm": 0.31017982959747314,
      "learning_rate": 9.781389474144717e-05,
      "loss": 0.0182,
      "step": 560
    },
    {
      "epoch": 1.4205287713841368,
      "grad_norm": 0.24658547341823578,
      "learning_rate": 9.76913688511698e-05,
      "loss": 0.0174,
      "step": 570
    },
    {
      "epoch": 1.445412130637636,
      "grad_norm": 0.23288820683956146,
      "learning_rate": 9.756558331918227e-05,
      "loss": 0.0172,
      "step": 580
    },
    {
      "epoch": 1.4702954898911353,
      "grad_norm": 0.16752177476882935,
      "learning_rate": 9.743654674275855e-05,
      "loss": 0.0185,
      "step": 590
    },
    {
      "epoch": 1.4951788491446345,
      "grad_norm": 0.19120067358016968,
      "learning_rate": 9.730426794137727e-05,
      "loss": 0.0163,
      "step": 600
    },
    {
      "epoch": 1.5200622083981337,
      "grad_norm": 0.2136230617761612,
      "learning_rate": 9.716875595611879e-05,
      "loss": 0.0171,
      "step": 610
    },
    {
      "epoch": 1.544945567651633,
      "grad_norm": 0.18993347883224487,
      "learning_rate": 9.703002004904729e-05,
      "loss": 0.0164,
      "step": 620
    },
    {
      "epoch": 1.5698289269051322,
      "grad_norm": 0.22324898838996887,
      "learning_rate": 9.688806970257773e-05,
      "loss": 0.0169,
      "step": 630
    },
    {
      "epoch": 1.5947122861586314,
      "grad_norm": 0.18617911636829376,
      "learning_rate": 9.674291461882774e-05,
      "loss": 0.0153,
      "step": 640
    },
    {
      "epoch": 1.6195956454121307,
      "grad_norm": 0.1991218626499176,
      "learning_rate": 9.659456471895445e-05,
      "loss": 0.0158,
      "step": 650
    },
    {
      "epoch": 1.64447900466563,
      "grad_norm": 0.27028852701187134,
      "learning_rate": 9.644303014247648e-05,
      "loss": 0.0164,
      "step": 660
    },
    {
      "epoch": 1.669362363919129,
      "grad_norm": 0.21468698978424072,
      "learning_rate": 9.628832124658085e-05,
      "loss": 0.0159,
      "step": 670
    },
    {
      "epoch": 1.6942457231726284,
      "grad_norm": 0.25870266556739807,
      "learning_rate": 9.613044860541507e-05,
      "loss": 0.0159,
      "step": 680
    },
    {
      "epoch": 1.7191290824261274,
      "grad_norm": 0.2562198042869568,
      "learning_rate": 9.596942300936445e-05,
      "loss": 0.0149,
      "step": 690
    },
    {
      "epoch": 1.7440124416796268,
      "grad_norm": 0.22703538835048676,
      "learning_rate": 9.580525546431459e-05,
      "loss": 0.0165,
      "step": 700
    },
    {
      "epoch": 1.768895800933126,
      "grad_norm": 0.27203115820884705,
      "learning_rate": 9.563795719089911e-05,
      "loss": 0.0153,
      "step": 710
    },
    {
      "epoch": 1.793779160186625,
      "grad_norm": 0.337146133184433,
      "learning_rate": 9.546753962373281e-05,
      "loss": 0.0175,
      "step": 720
    },
    {
      "epoch": 1.8186625194401245,
      "grad_norm": 0.3714126944541931,
      "learning_rate": 9.529401441062997e-05,
      "loss": 0.0162,
      "step": 730
    },
    {
      "epoch": 1.8435458786936236,
      "grad_norm": 0.23839302361011505,
      "learning_rate": 9.511739341180842e-05,
      "loss": 0.0169,
      "step": 740
    },
    {
      "epoch": 1.8684292379471228,
      "grad_norm": 0.2162984013557434,
      "learning_rate": 9.493768869907886e-05,
      "loss": 0.0153,
      "step": 750
    },
    {
      "epoch": 1.8933125972006222,
      "grad_norm": 0.25327548384666443,
      "learning_rate": 9.475491255501968e-05,
      "loss": 0.0149,
      "step": 760
    },
    {
      "epoch": 1.9181959564541213,
      "grad_norm": 0.17730680108070374,
      "learning_rate": 9.456907747213748e-05,
      "loss": 0.0147,
      "step": 770
    },
    {
      "epoch": 1.9430793157076205,
      "grad_norm": 0.2287522703409195,
      "learning_rate": 9.438019615201336e-05,
      "loss": 0.0154,
      "step": 780
    },
    {
      "epoch": 1.9679626749611199,
      "grad_norm": 0.2877958118915558,
      "learning_rate": 9.418828150443469e-05,
      "loss": 0.0157,
      "step": 790
    },
    {
      "epoch": 1.9928460342146188,
      "grad_norm": 0.272636741399765,
      "learning_rate": 9.399334664651262e-05,
      "loss": 0.0153,
      "step": 800
    },
    {
      "epoch": 2.0199066874027993,
      "grad_norm": 0.3082719147205353,
      "learning_rate": 9.379540490178581e-05,
      "loss": 0.0151,
      "step": 810
    },
    {
      "epoch": 2.0447900466562987,
      "grad_norm": 0.3081252872943878,
      "learning_rate": 9.359446979930955e-05,
      "loss": 0.0156,
      "step": 820
    },
    {
      "epoch": 2.0696734059097976,
      "grad_norm": 0.25696584582328796,
      "learning_rate": 9.33905550727312e-05,
      "loss": 0.0157,
      "step": 830
    },
    {
      "epoch": 2.094556765163297,
      "grad_norm": 0.2680334150791168,
      "learning_rate": 9.318367465935142e-05,
      "loss": 0.0151,
      "step": 840
    },
    {
      "epoch": 2.1194401244167964,
      "grad_norm": 0.20804259181022644,
      "learning_rate": 9.29738426991717e-05,
      "loss": 0.0144,
      "step": 850
    },
    {
      "epoch": 2.1443234836702953,
      "grad_norm": 0.2176770567893982,
      "learning_rate": 9.276107353392774e-05,
      "loss": 0.0144,
      "step": 860
    },
    {
      "epoch": 2.1692068429237947,
      "grad_norm": 0.21425634622573853,
      "learning_rate": 9.254538170610938e-05,
      "loss": 0.0145,
      "step": 870
    },
    {
      "epoch": 2.194090202177294,
      "grad_norm": 0.20511746406555176,
      "learning_rate": 9.232678195796654e-05,
      "loss": 0.0146,
      "step": 880
    },
    {
      "epoch": 2.218973561430793,
      "grad_norm": 0.2533751130104065,
      "learning_rate": 9.210528923050164e-05,
      "loss": 0.0134,
      "step": 890
    },
    {
      "epoch": 2.2438569206842924,
      "grad_norm": 0.2530650794506073,
      "learning_rate": 9.188091866244834e-05,
      "loss": 0.0143,
      "step": 900
    },
    {
      "epoch": 2.2687402799377914,
      "grad_norm": 0.25711414217948914,
      "learning_rate": 9.165368558923695e-05,
      "loss": 0.0139,
      "step": 910
    },
    {
      "epoch": 2.2936236391912908,
      "grad_norm": 0.226607546210289,
      "learning_rate": 9.142360554194618e-05,
      "loss": 0.0146,
      "step": 920
    },
    {
      "epoch": 2.31850699844479,
      "grad_norm": 0.15505652129650116,
      "learning_rate": 9.119069424624163e-05,
      "loss": 0.014,
      "step": 930
    },
    {
      "epoch": 2.343390357698289,
      "grad_norm": 0.20164167881011963,
      "learning_rate": 9.0954967621301e-05,
      "loss": 0.0142,
      "step": 940
    },
    {
      "epoch": 2.3682737169517885,
      "grad_norm": 0.2123536318540573,
      "learning_rate": 9.071644177872594e-05,
      "loss": 0.0136,
      "step": 950
    },
    {
      "epoch": 2.393157076205288,
      "grad_norm": 0.218880295753479,
      "learning_rate": 9.047513302144095e-05,
      "loss": 0.0133,
      "step": 960
    },
    {
      "epoch": 2.4180404354587868,
      "grad_norm": 0.20033881068229675,
      "learning_rate": 9.023105784257906e-05,
      "loss": 0.013,
      "step": 970
    },
    {
      "epoch": 2.442923794712286,
      "grad_norm": 0.20657172799110413,
      "learning_rate": 8.998423292435454e-05,
      "loss": 0.0146,
      "step": 980
    },
    {
      "epoch": 2.4678071539657855,
      "grad_norm": 0.14253973960876465,
      "learning_rate": 8.973467513692265e-05,
      "loss": 0.0133,
      "step": 990
    },
    {
      "epoch": 2.4926905132192845,
      "grad_norm": 0.20540325343608856,
      "learning_rate": 8.94824015372267e-05,
      "loss": 0.0155,
      "step": 1000
    }
  ],
  "logging_steps": 10,
  "max_steps": 4000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}