{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 4690,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.10660980810234541,
      "grad_norm": 1.512649655342102,
      "learning_rate": 7.021276595744681e-05,
      "loss": 0.8783621978759766,
      "step": 100
    },
    {
      "epoch": 0.21321961620469082,
      "grad_norm": 0.41342806816101074,
      "learning_rate": 9.872499450428666e-05,
      "loss": 0.3635389709472656,
      "step": 200
    },
    {
      "epoch": 0.31982942430703626,
      "grad_norm": 0.2897585332393646,
      "learning_rate": 9.652670916684985e-05,
      "loss": 0.18652456283569335,
      "step": 300
    },
    {
      "epoch": 0.42643923240938164,
      "grad_norm": 0.39718756079673767,
      "learning_rate": 9.432842382941306e-05,
      "loss": 0.13982501983642578,
      "step": 400
    },
    {
      "epoch": 0.5330490405117271,
      "grad_norm": 0.22674299776554108,
      "learning_rate": 9.213013849197626e-05,
      "loss": 0.12051151275634765,
      "step": 500
    },
    {
      "epoch": 0.6396588486140725,
      "grad_norm": 0.27016663551330566,
      "learning_rate": 8.993185315453946e-05,
      "loss": 0.10687240600585937,
      "step": 600
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 0.27923911809921265,
      "learning_rate": 8.773356781710267e-05,
      "loss": 0.0931793212890625,
      "step": 700
    },
    {
      "epoch": 0.8528784648187633,
      "grad_norm": 0.48017603158950806,
      "learning_rate": 8.553528247966587e-05,
      "loss": 0.08681591987609863,
      "step": 800
    },
    {
      "epoch": 0.9594882729211087,
      "grad_norm": 0.25462451577186584,
      "learning_rate": 8.333699714222907e-05,
      "loss": 0.08227352142333984,
      "step": 900
    },
    {
      "epoch": 1.0660980810234542,
      "grad_norm": 0.25555577874183655,
      "learning_rate": 8.113871180479227e-05,
      "loss": 0.07781341552734375,
      "step": 1000
    },
    {
      "epoch": 1.1727078891257996,
      "grad_norm": 0.2868955433368683,
      "learning_rate": 7.894042646735546e-05,
      "loss": 0.07137668609619141,
      "step": 1100
    },
    {
      "epoch": 1.279317697228145,
      "grad_norm": 0.7258135080337524,
      "learning_rate": 7.674214112991867e-05,
      "loss": 0.06982158660888672,
      "step": 1200
    },
    {
      "epoch": 1.3859275053304905,
      "grad_norm": 0.21467193961143494,
      "learning_rate": 7.454385579248186e-05,
      "loss": 0.06995021343231202,
      "step": 1300
    },
    {
      "epoch": 1.4925373134328357,
      "grad_norm": 0.2582932412624359,
      "learning_rate": 7.234557045504506e-05,
      "loss": 0.06500450611114501,
      "step": 1400
    },
    {
      "epoch": 1.5991471215351813,
      "grad_norm": 0.6736129522323608,
      "learning_rate": 7.014728511760827e-05,
      "loss": 0.06558525085449218,
      "step": 1500
    },
    {
      "epoch": 1.7057569296375266,
      "grad_norm": 0.347025603055954,
      "learning_rate": 6.794899978017147e-05,
      "loss": 0.06201983451843262,
      "step": 1600
    },
    {
      "epoch": 1.8123667377398722,
      "grad_norm": 0.14061450958251953,
      "learning_rate": 6.575071444273467e-05,
      "loss": 0.06188218116760254,
      "step": 1700
    },
    {
      "epoch": 1.9189765458422174,
      "grad_norm": 0.671807587146759,
      "learning_rate": 6.355242910529788e-05,
      "loss": 0.06162861347198487,
      "step": 1800
    },
    {
      "epoch": 2.025586353944563,
      "grad_norm": 0.23481066524982452,
      "learning_rate": 6.135414376786107e-05,
      "loss": 0.059541940689086914,
      "step": 1900
    },
    {
      "epoch": 2.1321961620469083,
      "grad_norm": 0.37396782636642456,
      "learning_rate": 5.915585843042427e-05,
      "loss": 0.05958046913146973,
      "step": 2000
    },
    {
      "epoch": 2.2388059701492535,
      "grad_norm": 0.3006986975669861,
      "learning_rate": 5.695757309298747e-05,
      "loss": 0.058162903785705565,
      "step": 2100
    },
    {
      "epoch": 2.345415778251599,
      "grad_norm": 0.512683629989624,
      "learning_rate": 5.475928775555067e-05,
      "loss": 0.05590470790863037,
      "step": 2200
    },
    {
      "epoch": 2.4520255863539444,
      "grad_norm": 0.6538902521133423,
      "learning_rate": 5.2561002418113866e-05,
      "loss": 0.056855697631835934,
      "step": 2300
    },
    {
      "epoch": 2.55863539445629,
      "grad_norm": 0.384748250246048,
      "learning_rate": 5.036271708067708e-05,
      "loss": 0.0553256368637085,
      "step": 2400
    },
    {
      "epoch": 2.6652452025586353,
      "grad_norm": 0.2743995785713196,
      "learning_rate": 4.8164431743240275e-05,
      "loss": 0.055201725959777834,
      "step": 2500
    },
    {
      "epoch": 2.771855010660981,
      "grad_norm": 0.3086058497428894,
      "learning_rate": 4.5966146405803476e-05,
      "loss": 0.05579360485076904,
      "step": 2600
    },
    {
      "epoch": 2.878464818763326,
      "grad_norm": 0.20562346279621124,
      "learning_rate": 4.376786106836668e-05,
      "loss": 0.053631467819213866,
      "step": 2700
    },
    {
      "epoch": 2.9850746268656714,
      "grad_norm": 0.17855797708034515,
      "learning_rate": 4.156957573092988e-05,
      "loss": 0.05369348526000976,
      "step": 2800
    },
    {
      "epoch": 3.091684434968017,
      "grad_norm": 0.21947342157363892,
      "learning_rate": 3.937129039349308e-05,
      "loss": 0.05297693252563476,
      "step": 2900
    },
    {
      "epoch": 3.1982942430703627,
      "grad_norm": 0.1905689537525177,
      "learning_rate": 3.717300505605627e-05,
      "loss": 0.05208170413970947,
      "step": 3000
    },
    {
      "epoch": 3.304904051172708,
      "grad_norm": 0.4524707496166229,
      "learning_rate": 3.497471971861948e-05,
      "loss": 0.053418731689453124,
      "step": 3100
    },
    {
      "epoch": 3.411513859275053,
      "grad_norm": 0.3877377510070801,
      "learning_rate": 3.277643438118268e-05,
      "loss": 0.05178478240966797,
      "step": 3200
    },
    {
      "epoch": 3.518123667377399,
      "grad_norm": 0.38067901134490967,
      "learning_rate": 3.057814904374588e-05,
      "loss": 0.05265708446502686,
      "step": 3300
    },
    {
      "epoch": 3.624733475479744,
      "grad_norm": 0.220926433801651,
      "learning_rate": 2.837986370630908e-05,
      "loss": 0.051145505905151364,
      "step": 3400
    },
    {
      "epoch": 3.7313432835820897,
      "grad_norm": 0.24693001806735992,
      "learning_rate": 2.6181578368872278e-05,
      "loss": 0.05244531154632568,
      "step": 3500
    },
    {
      "epoch": 3.837953091684435,
      "grad_norm": 0.16234378516674042,
      "learning_rate": 2.3983293031435482e-05,
      "loss": 0.05159466743469238,
      "step": 3600
    },
    {
      "epoch": 3.9445628997867805,
      "grad_norm": 0.25106945633888245,
      "learning_rate": 2.1785007693998683e-05,
      "loss": 0.050518522262573244,
      "step": 3700
    },
    {
      "epoch": 4.051172707889126,
      "grad_norm": 0.15427334606647491,
      "learning_rate": 1.958672235656188e-05,
      "loss": 0.05148844242095947,
      "step": 3800
    },
    {
      "epoch": 4.157782515991471,
      "grad_norm": 0.2565928101539612,
      "learning_rate": 1.7388437019125085e-05,
      "loss": 0.05278157234191894,
      "step": 3900
    },
    {
      "epoch": 4.264392324093817,
      "grad_norm": 0.23209957778453827,
      "learning_rate": 1.5190151681688284e-05,
      "loss": 0.05116010189056396,
      "step": 4000
    },
    {
      "epoch": 4.371002132196162,
      "grad_norm": 0.2657167613506317,
      "learning_rate": 1.2991866344251485e-05,
      "loss": 0.050900754928588865,
      "step": 4100
    },
    {
      "epoch": 4.477611940298507,
      "grad_norm": 0.1503467857837677,
      "learning_rate": 1.0793581006814684e-05,
      "loss": 0.05005928516387939,
      "step": 4200
    },
    {
      "epoch": 4.584221748400853,
      "grad_norm": 0.22385095059871674,
      "learning_rate": 8.595295669377885e-06,
      "loss": 0.04985287666320801,
      "step": 4300
    },
    {
      "epoch": 4.690831556503198,
      "grad_norm": 0.2489224523305893,
      "learning_rate": 6.397010331941086e-06,
      "loss": 0.05140969753265381,
      "step": 4400
    },
    {
      "epoch": 4.797441364605544,
      "grad_norm": 0.14599594473838806,
      "learning_rate": 4.198724994504287e-06,
      "loss": 0.05068167209625244,
      "step": 4500
    },
    {
      "epoch": 4.904051172707889,
      "grad_norm": 0.2004062831401825,
      "learning_rate": 2.0004396570674875e-06,
      "loss": 0.050402441024780274,
      "step": 4600
    }
  ],
  "logging_steps": 100,
  "max_steps": 4690,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 0.0,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}