{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 574,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.034934497816593885,
      "grad_norm": 1.8211296796798706,
      "learning_rate": 9e-05,
      "loss": 3.1205413818359373,
      "step": 10
    },
    {
      "epoch": 0.06986899563318777,
      "grad_norm": 2.2983880043029785,
      "learning_rate": 0.00019,
      "loss": 1.7317464828491211,
      "step": 20
    },
    {
      "epoch": 0.10480349344978165,
      "grad_norm": 0.7729952335357666,
      "learning_rate": 0.00019986979101058972,
      "loss": 0.8218430519104004,
      "step": 30
    },
    {
      "epoch": 0.13973799126637554,
      "grad_norm": 0.7794175744056702,
      "learning_rate": 0.00019942012118204737,
      "loss": 0.6791059017181397,
      "step": 40
    },
    {
      "epoch": 0.17467248908296942,
      "grad_norm": 0.6147348880767822,
      "learning_rate": 0.0001986508282827419,
      "loss": 0.5647100448608399,
      "step": 50
    },
    {
      "epoch": 0.2096069868995633,
      "grad_norm": 0.5721135139465332,
      "learning_rate": 0.0001975643854917025,
      "loss": 0.4464299201965332,
      "step": 60
    },
    {
      "epoch": 0.2445414847161572,
      "grad_norm": 0.4910798668861389,
      "learning_rate": 0.00019616428558460634,
      "loss": 0.5486050605773926,
      "step": 70
    },
    {
      "epoch": 0.2794759825327511,
      "grad_norm": 0.4786812365055084,
      "learning_rate": 0.00019445502970494787,
      "loss": 0.6309103965759277,
      "step": 80
    },
    {
      "epoch": 0.314410480349345,
      "grad_norm": 0.3899824321269989,
      "learning_rate": 0.00019244211289343397,
      "loss": 0.47461185455322263,
      "step": 90
    },
    {
      "epoch": 0.34934497816593885,
      "grad_norm": 0.21079467236995697,
      "learning_rate": 0.00019013200642212545,
      "loss": 0.41464600563049314,
      "step": 100
    },
    {
      "epoch": 0.38427947598253276,
      "grad_norm": 0.42337626218795776,
      "learning_rate": 0.00018753213699011876,
      "loss": 0.4927196979522705,
      "step": 110
    },
    {
      "epoch": 0.4192139737991266,
      "grad_norm": 0.4860546588897705,
      "learning_rate": 0.00018465086284765093,
      "loss": 0.4953155040740967,
      "step": 120
    },
    {
      "epoch": 0.45414847161572053,
      "grad_norm": 0.5280138850212097,
      "learning_rate": 0.0001814974469253861,
      "loss": 0.3739574432373047,
      "step": 130
    },
    {
      "epoch": 0.4890829694323144,
      "grad_norm": 0.3762610852718353,
      "learning_rate": 0.000178082027055269,
      "loss": 0.5111323833465576,
      "step": 140
    },
    {
      "epoch": 0.5240174672489083,
      "grad_norm": 0.5376149415969849,
      "learning_rate": 0.00017441558337868198,
      "loss": 0.5593331813812256,
      "step": 150
    },
    {
      "epoch": 0.5589519650655022,
      "grad_norm": 0.472368448972702,
      "learning_rate": 0.00017050990304668423,
      "loss": 0.5056246757507324,
      "step": 160
    },
    {
      "epoch": 0.5938864628820961,
      "grad_norm": 0.44528254866600037,
      "learning_rate": 0.00016637754232581698,
      "loss": 0.4254063606262207,
      "step": 170
    },
    {
      "epoch": 0.62882096069869,
      "grad_norm": 0.38811150193214417,
      "learning_rate": 0.0001620317862313006,
      "loss": 0.5141812324523926,
      "step": 180
    },
    {
      "epoch": 0.6637554585152838,
      "grad_norm": 0.5775936841964722,
      "learning_rate": 0.00015748660581739655,
      "loss": 0.49105257987976075,
      "step": 190
    },
    {
      "epoch": 0.6986899563318777,
      "grad_norm": 0.47975367307662964,
      "learning_rate": 0.0001527566132622413,
      "loss": 0.5170726299285888,
      "step": 200
    },
    {
      "epoch": 0.7336244541484717,
      "grad_norm": 0.3569624125957489,
      "learning_rate": 0.0001478570148915483,
      "loss": 0.42121267318725586,
      "step": 210
    },
    {
      "epoch": 0.7685589519650655,
      "grad_norm": 0.5059508085250854,
      "learning_rate": 0.0001428035622922009,
      "loss": 0.41593084335327146,
      "step": 220
    },
    {
      "epoch": 0.8034934497816594,
      "grad_norm": 0.45586642622947693,
      "learning_rate": 0.0001376125016728996,
      "loss": 0.38859803676605226,
      "step": 230
    },
    {
      "epoch": 0.8384279475982532,
      "grad_norm": 0.41792041063308716,
      "learning_rate": 0.00013230052163466335,
      "loss": 0.4688732147216797,
      "step": 240
    },
    {
      "epoch": 0.8733624454148472,
      "grad_norm": 0.46951380372047424,
      "learning_rate": 0.0001268846995190953,
      "loss": 0.4584070682525635,
      "step": 250
    },
    {
      "epoch": 0.9082969432314411,
      "grad_norm": 0.44923996925354004,
      "learning_rate": 0.00012138244650689714,
      "loss": 0.4507625102996826,
      "step": 260
    },
    {
      "epoch": 0.9432314410480349,
      "grad_norm": 0.4775308072566986,
      "learning_rate": 0.00011581145164313307,
      "loss": 0.4381150722503662,
      "step": 270
    },
    {
      "epoch": 0.9781659388646288,
      "grad_norm": 0.3662133812904358,
      "learning_rate": 0.000110189624969195,
      "loss": 0.4980125427246094,
      "step": 280
    },
    {
      "epoch": 1.010480349344978,
      "grad_norm": 0.1824927031993866,
      "learning_rate": 0.00010453503994429279,
      "loss": 0.3719043254852295,
      "step": 290
    },
    {
      "epoch": 1.045414847161572,
      "grad_norm": 0.3003326654434204,
      "learning_rate": 9.886587534157678e-05,
      "loss": 0.39989519119262695,
      "step": 300
    },
    {
      "epoch": 1.080349344978166,
      "grad_norm": 0.531202495098114,
      "learning_rate": 9.32003568056896e-05,
      "loss": 0.32967467308044435,
      "step": 310
    },
    {
      "epoch": 1.1152838427947598,
      "grad_norm": 0.4517218768596649,
      "learning_rate": 8.755669825963159e-05,
      "loss": 0.3558018445968628,
      "step": 320
    },
    {
      "epoch": 1.1502183406113538,
      "grad_norm": 0.5482302308082581,
      "learning_rate": 8.19530433493105e-05,
      "loss": 0.38756818771362306,
      "step": 330
    },
    {
      "epoch": 1.1851528384279475,
      "grad_norm": 0.5365656614303589,
      "learning_rate": 7.640740711402266e-05,
      "loss": 0.33413424491882326,
      "step": 340
    },
    {
      "epoch": 1.2200873362445415,
      "grad_norm": 0.5340099930763245,
      "learning_rate": 7.093761807038802e-05,
      "loss": 0.43075904846191404,
      "step": 350
    },
    {
      "epoch": 1.2550218340611354,
      "grad_norm": 0.4649604558944702,
      "learning_rate": 6.556126089593226e-05,
      "loss": 0.42152748107910154,
      "step": 360
    },
    {
      "epoch": 1.2899563318777292,
      "grad_norm": 0.5258662104606628,
      "learning_rate": 6.029561989658058e-05,
      "loss": 0.3724403381347656,
      "step": 370
    },
    {
      "epoch": 1.3248908296943231,
      "grad_norm": 0.48639678955078125,
      "learning_rate": 5.515762343980757e-05,
      "loss": 0.37346906661987306,
      "step": 380
    },
    {
      "epoch": 1.359825327510917,
      "grad_norm": 0.505720853805542,
      "learning_rate": 5.0163789532084785e-05,
      "loss": 0.3663132667541504,
      "step": 390
    },
    {
      "epoch": 1.3947598253275109,
      "grad_norm": 0.4511260688304901,
      "learning_rate": 4.533017271558631e-05,
      "loss": 0.4028172016143799,
      "step": 400
    },
    {
      "epoch": 1.4296943231441048,
      "grad_norm": 0.36770346760749817,
      "learning_rate": 4.067231245487331e-05,
      "loss": 0.28973219394683836,
      "step": 410
    },
    {
      "epoch": 1.4646288209606988,
      "grad_norm": 0.5649269819259644,
      "learning_rate": 3.6205183179488034e-05,
      "loss": 0.3343945503234863,
      "step": 420
    },
    {
      "epoch": 1.4995633187772925,
      "grad_norm": 0.5703375339508057,
      "learning_rate": 3.1943146143063175e-05,
      "loss": 0.3596197128295898,
      "step": 430
    },
    {
      "epoch": 1.5344978165938865,
      "grad_norm": 0.5321503281593323,
      "learning_rate": 2.7899903253714488e-05,
      "loss": 0.3965036392211914,
      "step": 440
    },
    {
      "epoch": 1.5694323144104803,
      "grad_norm": 0.5592755079269409,
      "learning_rate": 2.4088453024145074e-05,
      "loss": 0.3017162084579468,
      "step": 450
    },
    {
      "epoch": 1.6043668122270742,
      "grad_norm": 0.5473719835281372,
      "learning_rate": 2.052104878307709e-05,
      "loss": 0.36124472618103026,
      "step": 460
    },
    {
      "epoch": 1.6393013100436682,
      "grad_norm": 0.41305872797966003,
      "learning_rate": 1.7209159282355047e-05,
      "loss": 0.34646024703979494,
      "step": 470
    },
    {
      "epoch": 1.6742358078602622,
      "grad_norm": 0.24601048231124878,
      "learning_rate": 1.4163431826364138e-05,
      "loss": 0.37380959987640383,
      "step": 480
    },
    {
      "epoch": 1.709170305676856,
      "grad_norm": 0.5165665149688721,
      "learning_rate": 1.1393658042298361e-05,
      "loss": 0.34536712169647216,
      "step": 490
    },
    {
      "epoch": 1.7441048034934497,
      "grad_norm": 0.5911356806755066,
      "learning_rate": 8.908742401321701e-06,
      "loss": 0.28776962757110597,
      "step": 500
    },
    {
      "epoch": 1.7790393013100436,
      "grad_norm": 0.48452237248420715,
      "learning_rate": 6.7166735918234744e-06,
      "loss": 0.3274099349975586,
      "step": 510
    },
    {
      "epoch": 1.8139737991266376,
      "grad_norm": 0.5194221138954163,
      "learning_rate": 4.824498836799285e-06,
      "loss": 0.42140350341796873,
      "step": 520
    },
    {
      "epoch": 1.8489082969432316,
      "grad_norm": 0.4017932415008545,
      "learning_rate": 3.2383012379234024e-06,
      "loss": 0.32117505073547364,
      "step": 530
    },
    {
      "epoch": 1.8838427947598253,
      "grad_norm": 0.5720022916793823,
      "learning_rate": 1.9631802191490744e-06,
      "loss": 0.3702544212341309,
      "step": 540
    },
    {
      "epoch": 1.9187772925764193,
      "grad_norm": 0.42618224024772644,
      "learning_rate": 1.003235132707725e-06,
      "loss": 0.40667200088500977,
      "step": 550
    },
    {
      "epoch": 1.953711790393013,
      "grad_norm": 0.5558740496635437,
      "learning_rate": 3.615520802118244e-07,
      "loss": 0.3302525281906128,
      "step": 560
    },
    {
      "epoch": 1.988646288209607,
      "grad_norm": 0.5960554480552673,
      "learning_rate": 4.019399122991985e-08,
      "loss": 0.3490064859390259,
      "step": 570
    }
  ],
  "logging_steps": 10,
  "max_steps": 574,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 7489120523028480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}