{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0030714102892244,
  "eval_steps": 500,
  "global_step": 3907,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.012797542871768621,
      "grad_norm": 0.13088035583496094,
      "learning_rate": 4.9000000000000005e-06,
      "loss": 0.3135,
      "step": 50
    },
    {
      "epoch": 0.025595085743537242,
      "grad_norm": 0.19547288119792938,
      "learning_rate": 9.900000000000002e-06,
      "loss": 0.3061,
      "step": 100
    },
    {
      "epoch": 0.03839262861530586,
      "grad_norm": 0.4533034563064575,
      "learning_rate": 1.49e-05,
      "loss": 0.2686,
      "step": 150
    },
    {
      "epoch": 0.051190171487074485,
      "grad_norm": 0.19370593130588531,
      "learning_rate": 1.9900000000000003e-05,
      "loss": 0.1249,
      "step": 200
    },
    {
      "epoch": 0.0639877143588431,
      "grad_norm": 0.07303176075220108,
      "learning_rate": 2.4900000000000002e-05,
      "loss": 0.0414,
      "step": 250
    },
    {
      "epoch": 0.07678525723061172,
      "grad_norm": 0.07712763547897339,
      "learning_rate": 2.9900000000000002e-05,
      "loss": 0.0367,
      "step": 300
    },
    {
      "epoch": 0.08958280010238034,
      "grad_norm": 0.059200357645750046,
      "learning_rate": 3.49e-05,
      "loss": 0.0345,
      "step": 350
    },
    {
      "epoch": 0.10238034297414897,
      "grad_norm": 0.05315428972244263,
      "learning_rate": 3.99e-05,
      "loss": 0.0301,
      "step": 400
    },
    {
      "epoch": 0.11517788584591758,
      "grad_norm": 0.04727872833609581,
      "learning_rate": 4.49e-05,
      "loss": 0.0261,
      "step": 450
    },
    {
      "epoch": 0.1279754287176862,
      "grad_norm": 0.0576280876994133,
      "learning_rate": 4.99e-05,
      "loss": 0.0229,
      "step": 500
    },
    {
      "epoch": 0.14077297158945482,
      "grad_norm": 0.056870535016059875,
      "learning_rate": 5.4900000000000006e-05,
      "loss": 0.0205,
      "step": 550
    },
    {
      "epoch": 0.15357051446122344,
      "grad_norm": 0.04455719515681267,
      "learning_rate": 5.99e-05,
      "loss": 0.0187,
      "step": 600
    },
    {
      "epoch": 0.16636805733299206,
      "grad_norm": 0.04446660727262497,
      "learning_rate": 6.49e-05,
      "loss": 0.0167,
      "step": 650
    },
    {
      "epoch": 0.1791656002047607,
      "grad_norm": 0.03929851949214935,
      "learning_rate": 6.99e-05,
      "loss": 0.0153,
      "step": 700
    },
    {
      "epoch": 0.1919631430765293,
      "grad_norm": 0.04089954122900963,
      "learning_rate": 7.49e-05,
      "loss": 0.0139,
      "step": 750
    },
    {
      "epoch": 0.20476068594829794,
      "grad_norm": 0.03866012394428253,
      "learning_rate": 7.99e-05,
      "loss": 0.0142,
      "step": 800
    },
    {
      "epoch": 0.21755822882006653,
      "grad_norm": 0.03981732204556465,
      "learning_rate": 8.49e-05,
      "loss": 0.0129,
      "step": 850
    },
    {
      "epoch": 0.23035577169183516,
      "grad_norm": 0.04276875779032707,
      "learning_rate": 8.99e-05,
      "loss": 0.0122,
      "step": 900
    },
    {
      "epoch": 0.24315331456360378,
      "grad_norm": 0.05385587736964226,
      "learning_rate": 9.49e-05,
      "loss": 0.0119,
      "step": 950
    },
    {
      "epoch": 0.2559508574353724,
      "grad_norm": 0.04468897357583046,
      "learning_rate": 9.99e-05,
      "loss": 0.013,
      "step": 1000
    },
    {
      "epoch": 0.26874840030714103,
      "grad_norm": 0.05959586054086685,
      "learning_rate": 9.831441348469213e-05,
      "loss": 0.0124,
      "step": 1050
    },
    {
      "epoch": 0.28154594317890963,
      "grad_norm": 0.04764668643474579,
      "learning_rate": 9.659442724458206e-05,
      "loss": 0.0124,
      "step": 1100
    },
    {
      "epoch": 0.2943434860506783,
      "grad_norm": 0.03957217559218407,
      "learning_rate": 9.487444100447197e-05,
      "loss": 0.0116,
      "step": 1150
    },
    {
      "epoch": 0.3071410289224469,
      "grad_norm": 0.03710690885782242,
      "learning_rate": 9.315445476436189e-05,
      "loss": 0.0109,
      "step": 1200
    },
    {
      "epoch": 0.31993857179421553,
      "grad_norm": 0.02536761574447155,
      "learning_rate": 9.143446852425182e-05,
      "loss": 0.0106,
      "step": 1250
    },
    {
      "epoch": 0.33273611466598413,
      "grad_norm": 0.03855664283037186,
      "learning_rate": 8.971448228414173e-05,
      "loss": 0.0109,
      "step": 1300
    },
    {
      "epoch": 0.3455336575377527,
      "grad_norm": 0.03235240280628204,
      "learning_rate": 8.799449604403165e-05,
      "loss": 0.0101,
      "step": 1350
    },
    {
      "epoch": 0.3583312004095214,
      "grad_norm": 0.03756868839263916,
      "learning_rate": 8.627450980392158e-05,
      "loss": 0.0098,
      "step": 1400
    },
    {
      "epoch": 0.37112874328129,
      "grad_norm": 0.05165262520313263,
      "learning_rate": 8.455452356381149e-05,
      "loss": 0.0104,
      "step": 1450
    },
    {
      "epoch": 0.3839262861530586,
      "grad_norm": 0.049087073653936386,
      "learning_rate": 8.283453732370142e-05,
      "loss": 0.0129,
      "step": 1500
    },
    {
      "epoch": 0.3967238290248272,
      "grad_norm": 0.037772029638290405,
      "learning_rate": 8.111455108359134e-05,
      "loss": 0.0134,
      "step": 1550
    },
    {
      "epoch": 0.4095213718965959,
      "grad_norm": 0.04680902883410454,
      "learning_rate": 7.939456484348125e-05,
      "loss": 0.0123,
      "step": 1600
    },
    {
      "epoch": 0.4223189147683645,
      "grad_norm": 0.033195000141859055,
      "learning_rate": 7.767457860337118e-05,
      "loss": 0.0117,
      "step": 1650
    },
    {
      "epoch": 0.43511645764013307,
      "grad_norm": 0.041804239153862,
      "learning_rate": 7.59545923632611e-05,
      "loss": 0.0116,
      "step": 1700
    },
    {
      "epoch": 0.4479140005119017,
      "grad_norm": 0.03666084632277489,
      "learning_rate": 7.423460612315101e-05,
      "loss": 0.0109,
      "step": 1750
    },
    {
      "epoch": 0.4607115433836703,
      "grad_norm": 0.03571762517094612,
      "learning_rate": 7.251461988304094e-05,
      "loss": 0.0106,
      "step": 1800
    },
    {
      "epoch": 0.47350908625543897,
      "grad_norm": 0.04815353825688362,
      "learning_rate": 7.079463364293086e-05,
      "loss": 0.0114,
      "step": 1850
    },
    {
      "epoch": 0.48630662912720757,
      "grad_norm": 0.04004329442977905,
      "learning_rate": 6.907464740282077e-05,
      "loss": 0.0121,
      "step": 1900
    },
    {
      "epoch": 0.4991041719989762,
      "grad_norm": 0.042084284126758575,
      "learning_rate": 6.73546611627107e-05,
      "loss": 0.0112,
      "step": 1950
    },
    {
      "epoch": 0.5119017148707448,
      "grad_norm": 0.03757471218705177,
      "learning_rate": 6.563467492260062e-05,
      "loss": 0.0097,
      "step": 2000
    },
    {
      "epoch": 0.5246992577425135,
      "grad_norm": 0.03647317737340927,
      "learning_rate": 6.391468868249054e-05,
      "loss": 0.0091,
      "step": 2050
    },
    {
      "epoch": 0.5374968006142821,
      "grad_norm": 0.03781365975737572,
      "learning_rate": 6.219470244238046e-05,
      "loss": 0.0091,
      "step": 2100
    },
    {
      "epoch": 0.5502943434860507,
      "grad_norm": 0.03655465319752693,
      "learning_rate": 6.0474716202270386e-05,
      "loss": 0.0105,
      "step": 2150
    },
    {
      "epoch": 0.5630918863578193,
      "grad_norm": 0.04239595681428909,
      "learning_rate": 5.8754729962160305e-05,
      "loss": 0.0117,
      "step": 2200
    },
    {
      "epoch": 0.575889429229588,
      "grad_norm": 0.03313069045543671,
      "learning_rate": 5.703474372205022e-05,
      "loss": 0.0115,
      "step": 2250
    },
    {
      "epoch": 0.5886869721013566,
      "grad_norm": 0.04855331405997276,
      "learning_rate": 5.531475748194015e-05,
      "loss": 0.0115,
      "step": 2300
    },
    {
      "epoch": 0.6014845149731252,
      "grad_norm": 0.0456092394888401,
      "learning_rate": 5.3594771241830066e-05,
      "loss": 0.0115,
      "step": 2350
    },
    {
      "epoch": 0.6142820578448938,
      "grad_norm": 0.0333721786737442,
      "learning_rate": 5.1874785001719984e-05,
      "loss": 0.0111,
      "step": 2400
    },
    {
      "epoch": 0.6270796007166624,
      "grad_norm": 0.042097028344869614,
      "learning_rate": 5.015479876160991e-05,
      "loss": 0.0106,
      "step": 2450
    },
    {
      "epoch": 0.6398771435884311,
      "grad_norm": 0.034766409546136856,
      "learning_rate": 4.843481252149983e-05,
      "loss": 0.0102,
      "step": 2500
    },
    {
      "epoch": 0.6526746864601997,
      "grad_norm": 0.054405491799116135,
      "learning_rate": 4.671482628138975e-05,
      "loss": 0.0098,
      "step": 2550
    },
    {
      "epoch": 0.6654722293319683,
      "grad_norm": 0.03880583122372627,
      "learning_rate": 4.499484004127967e-05,
      "loss": 0.0095,
      "step": 2600
    },
    {
      "epoch": 0.6782697722037369,
      "grad_norm": 0.040803831070661545,
      "learning_rate": 4.327485380116959e-05,
      "loss": 0.0094,
      "step": 2650
    },
    {
      "epoch": 0.6910673150755055,
      "grad_norm": 0.03792567178606987,
      "learning_rate": 4.1554867561059514e-05,
      "loss": 0.0092,
      "step": 2700
    },
    {
      "epoch": 0.7038648579472742,
      "grad_norm": 0.03281814232468605,
      "learning_rate": 3.983488132094943e-05,
      "loss": 0.0091,
      "step": 2750
    },
    {
      "epoch": 0.7166624008190428,
      "grad_norm": 0.030551088973879814,
      "learning_rate": 3.811489508083935e-05,
      "loss": 0.01,
      "step": 2800
    },
    {
      "epoch": 0.7294599436908114,
      "grad_norm": 0.03448718041181564,
      "learning_rate": 3.6394908840729275e-05,
      "loss": 0.0094,
      "step": 2850
    },
    {
      "epoch": 0.74225748656258,
      "grad_norm": 0.02883707545697689,
      "learning_rate": 3.46749226006192e-05,
      "loss": 0.0096,
      "step": 2900
    },
    {
      "epoch": 0.7550550294343487,
      "grad_norm": 0.03563438728451729,
      "learning_rate": 3.295493636050912e-05,
      "loss": 0.0096,
      "step": 2950
    },
    {
      "epoch": 0.7678525723061173,
      "grad_norm": 0.02967008203268051,
      "learning_rate": 3.123495012039904e-05,
      "loss": 0.0091,
      "step": 3000
    },
    {
      "epoch": 0.7806501151778859,
      "grad_norm": 0.043325092643499374,
      "learning_rate": 2.9514963880288958e-05,
      "loss": 0.0093,
      "step": 3050
    },
    {
      "epoch": 0.7934476580496544,
      "grad_norm": 0.06209968030452728,
      "learning_rate": 2.7794977640178883e-05,
      "loss": 0.0095,
      "step": 3100
    },
    {
      "epoch": 0.806245200921423,
      "grad_norm": 0.051814526319503784,
      "learning_rate": 2.6074991400068798e-05,
      "loss": 0.0101,
      "step": 3150
    },
    {
      "epoch": 0.8190427437931918,
      "grad_norm": 0.041128940880298615,
      "learning_rate": 2.4355005159958723e-05,
      "loss": 0.0097,
      "step": 3200
    },
    {
      "epoch": 0.8318402866649603,
      "grad_norm": 0.03410228341817856,
      "learning_rate": 2.263501891984864e-05,
      "loss": 0.0092,
      "step": 3250
    },
    {
      "epoch": 0.844637829536729,
      "grad_norm": 0.05371547117829323,
      "learning_rate": 2.0915032679738563e-05,
      "loss": 0.0095,
      "step": 3300
    },
    {
      "epoch": 0.8574353724084975,
      "grad_norm": 0.03577767685055733,
      "learning_rate": 1.9195046439628485e-05,
      "loss": 0.0091,
      "step": 3350
    },
    {
      "epoch": 0.8702329152802661,
      "grad_norm": 0.031514376401901245,
      "learning_rate": 1.7475060199518406e-05,
      "loss": 0.0091,
      "step": 3400
    },
    {
      "epoch": 0.8830304581520348,
      "grad_norm": 0.0212860070168972,
      "learning_rate": 1.5755073959408324e-05,
      "loss": 0.0089,
      "step": 3450
    },
    {
      "epoch": 0.8958280010238034,
      "grad_norm": 0.04357130452990532,
      "learning_rate": 1.4035087719298246e-05,
      "loss": 0.009,
      "step": 3500
    },
    {
      "epoch": 0.908625543895572,
      "grad_norm": 0.03506151959300041,
      "learning_rate": 1.2315101479188166e-05,
      "loss": 0.0102,
      "step": 3550
    },
    {
      "epoch": 0.9214230867673406,
      "grad_norm": 0.03501707315444946,
      "learning_rate": 1.0595115239078087e-05,
      "loss": 0.0102,
      "step": 3600
    },
    {
      "epoch": 0.9342206296391093,
      "grad_norm": 0.02822631224989891,
      "learning_rate": 8.875128998968009e-06,
      "loss": 0.0099,
      "step": 3650
    },
    {
      "epoch": 0.9470181725108779,
      "grad_norm": 0.035826027393341064,
      "learning_rate": 7.15514275885793e-06,
      "loss": 0.0099,
      "step": 3700
    },
    {
      "epoch": 0.9598157153826465,
      "grad_norm": 0.03122458979487419,
      "learning_rate": 5.4351565187478506e-06,
      "loss": 0.0092,
      "step": 3750
    },
    {
      "epoch": 0.9726132582544151,
      "grad_norm": 0.050926536321640015,
      "learning_rate": 3.715170278637771e-06,
      "loss": 0.0097,
      "step": 3800
    },
    {
      "epoch": 0.9854108011261837,
      "grad_norm": 0.04788774251937866,
      "learning_rate": 1.9951840385276917e-06,
      "loss": 0.0094,
      "step": 3850
    },
    {
      "epoch": 1.001279754287177,
      "grad_norm": 0.04952634498476982,
      "learning_rate": 2.751977984176127e-07,
      "loss": 0.009,
      "step": 3900
    }
  ],
  "logging_steps": 50,
  "max_steps": 3907,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 512,
  "trial_name": null,
  "trial_params": null
}