{
  "best_metric": 2.145188093185425,
  "best_model_checkpoint": "/content/working/models/checkpoint-3750",
  "epoch": 4.8475055544334475,
  "eval_steps": 750,
  "global_step": 3750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06463340739244597,
      "grad_norm": 0.06091862916946411,
      "learning_rate": 5e-05,
      "loss": 2.5923,
      "step": 50
    },
    {
      "epoch": 0.12926681478489194,
      "grad_norm": 0.08663396537303925,
      "learning_rate": 0.0001,
      "loss": 2.51,
      "step": 100
    },
    {
      "epoch": 0.1939002221773379,
      "grad_norm": 0.12191956490278244,
      "learning_rate": 9.867197875166003e-05,
      "loss": 2.4241,
      "step": 150
    },
    {
      "epoch": 0.2585336295697839,
      "grad_norm": 0.1454772800207138,
      "learning_rate": 9.734395750332006e-05,
      "loss": 2.3631,
      "step": 200
    },
    {
      "epoch": 0.32316703696222987,
      "grad_norm": 0.15225572884082794,
      "learning_rate": 9.601593625498009e-05,
      "loss": 2.3231,
      "step": 250
    },
    {
      "epoch": 0.3878004443546758,
      "grad_norm": 0.20414011180400848,
      "learning_rate": 9.468791500664011e-05,
      "loss": 2.3052,
      "step": 300
    },
    {
      "epoch": 0.4524338517471218,
      "grad_norm": 0.14269402623176575,
      "learning_rate": 9.335989375830013e-05,
      "loss": 2.3173,
      "step": 350
    },
    {
      "epoch": 0.5170672591395677,
      "grad_norm": 0.1620974987745285,
      "learning_rate": 9.203187250996016e-05,
      "loss": 2.3082,
      "step": 400
    },
    {
      "epoch": 0.5817006665320137,
      "grad_norm": 0.17254067957401276,
      "learning_rate": 9.070385126162018e-05,
      "loss": 2.2901,
      "step": 450
    },
    {
      "epoch": 0.6463340739244597,
      "grad_norm": 0.17900939285755157,
      "learning_rate": 8.937583001328021e-05,
      "loss": 2.2697,
      "step": 500
    },
    {
      "epoch": 0.7109674813169057,
      "grad_norm": 0.18225091695785522,
      "learning_rate": 8.804780876494024e-05,
      "loss": 2.2775,
      "step": 550
    },
    {
      "epoch": 0.7756008887093516,
      "grad_norm": 0.19103792309761047,
      "learning_rate": 8.671978751660027e-05,
      "loss": 2.285,
      "step": 600
    },
    {
      "epoch": 0.8402342961017976,
      "grad_norm": 0.18991926312446594,
      "learning_rate": 8.539176626826029e-05,
      "loss": 2.2732,
      "step": 650
    },
    {
      "epoch": 0.9048677034942436,
      "grad_norm": 0.19260592758655548,
      "learning_rate": 8.406374501992032e-05,
      "loss": 2.2706,
      "step": 700
    },
    {
      "epoch": 0.9695011108866896,
      "grad_norm": 0.2015322744846344,
      "learning_rate": 8.273572377158035e-05,
      "loss": 2.2757,
      "step": 750
    },
    {
      "epoch": 0.9695011108866896,
      "eval_loss": 2.1990480422973633,
      "eval_runtime": 668.7494,
      "eval_samples_per_second": 12.329,
      "eval_steps_per_second": 12.329,
      "step": 750
    },
    {
      "epoch": 1.0341345182791355,
      "grad_norm": 0.2102416753768921,
      "learning_rate": 8.140770252324038e-05,
      "loss": 2.2683,
      "step": 800
    },
    {
      "epoch": 1.0987679256715814,
      "grad_norm": 0.2448854297399521,
      "learning_rate": 8.00796812749004e-05,
      "loss": 2.2509,
      "step": 850
    },
    {
      "epoch": 1.1634013330640274,
      "grad_norm": 0.19221533834934235,
      "learning_rate": 7.875166002656043e-05,
      "loss": 2.2675,
      "step": 900
    },
    {
      "epoch": 1.2280347404564735,
      "grad_norm": 0.20851700007915497,
      "learning_rate": 7.742363877822046e-05,
      "loss": 2.2595,
      "step": 950
    },
    {
      "epoch": 1.2926681478489195,
      "grad_norm": 0.2272697389125824,
      "learning_rate": 7.609561752988048e-05,
      "loss": 2.2552,
      "step": 1000
    },
    {
      "epoch": 1.3573015552413654,
      "grad_norm": 0.24437403678894043,
      "learning_rate": 7.476759628154051e-05,
      "loss": 2.2545,
      "step": 1050
    },
    {
      "epoch": 1.4219349626338114,
      "grad_norm": 0.18688540160655975,
      "learning_rate": 7.343957503320054e-05,
      "loss": 2.2611,
      "step": 1100
    },
    {
      "epoch": 1.4865683700262573,
      "grad_norm": 0.25209754705429077,
      "learning_rate": 7.211155378486057e-05,
      "loss": 2.2444,
      "step": 1150
    },
    {
      "epoch": 1.5512017774187032,
      "grad_norm": 0.26226118206977844,
      "learning_rate": 7.07835325365206e-05,
      "loss": 2.2491,
      "step": 1200
    },
    {
      "epoch": 1.6158351848111492,
      "grad_norm": 0.19100286066532135,
      "learning_rate": 6.945551128818062e-05,
      "loss": 2.2401,
      "step": 1250
    },
    {
      "epoch": 1.6804685922035953,
      "grad_norm": 0.24590526521205902,
      "learning_rate": 6.812749003984064e-05,
      "loss": 2.238,
      "step": 1300
    },
    {
      "epoch": 1.745101999596041,
      "grad_norm": 0.20657116174697876,
      "learning_rate": 6.679946879150066e-05,
      "loss": 2.2481,
      "step": 1350
    },
    {
      "epoch": 1.8097354069884872,
      "grad_norm": 0.2326170951128006,
      "learning_rate": 6.547144754316069e-05,
      "loss": 2.2503,
      "step": 1400
    },
    {
      "epoch": 1.8743688143809332,
      "grad_norm": 0.192840114235878,
      "learning_rate": 6.414342629482072e-05,
      "loss": 2.2438,
      "step": 1450
    },
    {
      "epoch": 1.939002221773379,
      "grad_norm": 0.2151508778333664,
      "learning_rate": 6.281540504648075e-05,
      "loss": 2.2364,
      "step": 1500
    },
    {
      "epoch": 1.939002221773379,
      "eval_loss": 2.171081304550171,
      "eval_runtime": 669.7809,
      "eval_samples_per_second": 12.31,
      "eval_steps_per_second": 12.31,
      "step": 1500
    },
    {
      "epoch": 2.0036356291658253,
      "grad_norm": 0.23874713480472565,
      "learning_rate": 6.148738379814077e-05,
      "loss": 2.2375,
      "step": 1550
    },
    {
      "epoch": 2.068269036558271,
      "grad_norm": 0.23924137651920319,
      "learning_rate": 6.01593625498008e-05,
      "loss": 2.234,
      "step": 1600
    },
    {
      "epoch": 2.132902443950717,
      "grad_norm": 0.24824275076389313,
      "learning_rate": 5.883134130146083e-05,
      "loss": 2.2261,
      "step": 1650
    },
    {
      "epoch": 2.197535851343163,
      "grad_norm": 0.26141875982284546,
      "learning_rate": 5.7503320053120855e-05,
      "loss": 2.2319,
      "step": 1700
    },
    {
      "epoch": 2.262169258735609,
      "grad_norm": 0.23786722123622894,
      "learning_rate": 5.6175298804780876e-05,
      "loss": 2.2351,
      "step": 1750
    },
    {
      "epoch": 2.3268026661280548,
      "grad_norm": 0.22672909498214722,
      "learning_rate": 5.48472775564409e-05,
      "loss": 2.2194,
      "step": 1800
    },
    {
      "epoch": 2.391436073520501,
      "grad_norm": 0.2062198519706726,
      "learning_rate": 5.351925630810093e-05,
      "loss": 2.2284,
      "step": 1850
    },
    {
      "epoch": 2.456069480912947,
      "grad_norm": 0.2124897688627243,
      "learning_rate": 5.219123505976096e-05,
      "loss": 2.2472,
      "step": 1900
    },
    {
      "epoch": 2.520702888305393,
      "grad_norm": 0.24128706753253937,
      "learning_rate": 5.0863213811420985e-05,
      "loss": 2.2264,
      "step": 1950
    },
    {
      "epoch": 2.585336295697839,
      "grad_norm": 0.22971104085445404,
      "learning_rate": 4.953519256308101e-05,
      "loss": 2.2134,
      "step": 2000
    },
    {
      "epoch": 2.6499697030902847,
      "grad_norm": 0.22065037488937378,
      "learning_rate": 4.820717131474104e-05,
      "loss": 2.2328,
      "step": 2050
    },
    {
      "epoch": 2.714603110482731,
      "grad_norm": 0.2271411418914795,
      "learning_rate": 4.687915006640107e-05,
      "loss": 2.2252,
      "step": 2100
    },
    {
      "epoch": 2.7792365178751766,
      "grad_norm": 0.2558536231517792,
      "learning_rate": 4.555112881806109e-05,
      "loss": 2.2324,
      "step": 2150
    },
    {
      "epoch": 2.8438699252676227,
      "grad_norm": 0.23957061767578125,
      "learning_rate": 4.4223107569721116e-05,
      "loss": 2.2209,
      "step": 2200
    },
    {
      "epoch": 2.908503332660069,
      "grad_norm": 0.26163169741630554,
      "learning_rate": 4.289508632138114e-05,
      "loss": 2.2172,
      "step": 2250
    },
    {
      "epoch": 2.908503332660069,
      "eval_loss": 2.156771183013916,
      "eval_runtime": 668.1763,
      "eval_samples_per_second": 12.34,
      "eval_steps_per_second": 12.34,
      "step": 2250
    },
    {
      "epoch": 2.9731367400525146,
      "grad_norm": 0.26465606689453125,
      "learning_rate": 4.156706507304117e-05,
      "loss": 2.2313,
      "step": 2300
    },
    {
      "epoch": 3.0377701474449608,
      "grad_norm": 0.22578325867652893,
      "learning_rate": 4.02390438247012e-05,
      "loss": 2.2253,
      "step": 2350
    },
    {
      "epoch": 3.1024035548374065,
      "grad_norm": 0.23404210805892944,
      "learning_rate": 3.8911022576361225e-05,
      "loss": 2.2121,
      "step": 2400
    },
    {
      "epoch": 3.1670369622298526,
      "grad_norm": 0.2838682532310486,
      "learning_rate": 3.758300132802125e-05,
      "loss": 2.2218,
      "step": 2450
    },
    {
      "epoch": 3.2316703696222984,
      "grad_norm": 0.310476690530777,
      "learning_rate": 3.625498007968128e-05,
      "loss": 2.2159,
      "step": 2500
    },
    {
      "epoch": 3.2963037770147445,
      "grad_norm": 0.22608056664466858,
      "learning_rate": 3.492695883134131e-05,
      "loss": 2.2157,
      "step": 2550
    },
    {
      "epoch": 3.3609371844071907,
      "grad_norm": 0.23135437071323395,
      "learning_rate": 3.359893758300133e-05,
      "loss": 2.2255,
      "step": 2600
    },
    {
      "epoch": 3.4255705917996364,
      "grad_norm": 0.23839163780212402,
      "learning_rate": 3.2270916334661356e-05,
      "loss": 2.2223,
      "step": 2650
    },
    {
      "epoch": 3.4902039991920826,
      "grad_norm": 0.24394294619560242,
      "learning_rate": 3.094289508632138e-05,
      "loss": 2.2199,
      "step": 2700
    },
    {
      "epoch": 3.5548374065845283,
      "grad_norm": 0.2429606020450592,
      "learning_rate": 2.961487383798141e-05,
      "loss": 2.2015,
      "step": 2750
    },
    {
      "epoch": 3.6194708139769745,
      "grad_norm": 0.25373005867004395,
      "learning_rate": 2.8286852589641438e-05,
      "loss": 2.2152,
      "step": 2800
    },
    {
      "epoch": 3.68410422136942,
      "grad_norm": 0.2572405934333801,
      "learning_rate": 2.6958831341301462e-05,
      "loss": 2.2133,
      "step": 2850
    },
    {
      "epoch": 3.7487376287618663,
      "grad_norm": 0.2735884189605713,
      "learning_rate": 2.563081009296149e-05,
      "loss": 2.2171,
      "step": 2900
    },
    {
      "epoch": 3.8133710361543125,
      "grad_norm": 0.24303478002548218,
      "learning_rate": 2.4302788844621517e-05,
      "loss": 2.206,
      "step": 2950
    },
    {
      "epoch": 3.878004443546758,
      "grad_norm": 0.27165114879608154,
      "learning_rate": 2.297476759628154e-05,
      "loss": 2.2202,
      "step": 3000
    },
    {
      "epoch": 3.878004443546758,
      "eval_loss": 2.148362398147583,
      "eval_runtime": 668.4731,
      "eval_samples_per_second": 12.334,
      "eval_steps_per_second": 12.334,
      "step": 3000
    },
    {
      "epoch": 3.942637850939204,
      "grad_norm": 0.2713201940059662,
      "learning_rate": 2.1646746347941568e-05,
      "loss": 2.2085,
      "step": 3050
    },
    {
      "epoch": 4.0072712583316505,
      "grad_norm": 0.28700971603393555,
      "learning_rate": 2.0318725099601595e-05,
      "loss": 2.2154,
      "step": 3100
    },
    {
      "epoch": 4.071904665724096,
      "grad_norm": 0.2836604714393616,
      "learning_rate": 1.899070385126162e-05,
      "loss": 2.2011,
      "step": 3150
    },
    {
      "epoch": 4.136538073116542,
      "grad_norm": 0.26256245374679565,
      "learning_rate": 1.7662682602921647e-05,
      "loss": 2.2102,
      "step": 3200
    },
    {
      "epoch": 4.201171480508988,
      "grad_norm": 0.2922552227973938,
      "learning_rate": 1.6334661354581674e-05,
      "loss": 2.1935,
      "step": 3250
    },
    {
      "epoch": 4.265804887901434,
      "grad_norm": 0.26275578141212463,
      "learning_rate": 1.5006640106241702e-05,
      "loss": 2.209,
      "step": 3300
    },
    {
      "epoch": 4.33043829529388,
      "grad_norm": 0.28638267517089844,
      "learning_rate": 1.3678618857901726e-05,
      "loss": 2.2105,
      "step": 3350
    },
    {
      "epoch": 4.395071702686326,
      "grad_norm": 0.27328747510910034,
      "learning_rate": 1.2350597609561753e-05,
      "loss": 2.2171,
      "step": 3400
    },
    {
      "epoch": 4.459705110078772,
      "grad_norm": 0.2329448014497757,
      "learning_rate": 1.102257636122178e-05,
      "loss": 2.2133,
      "step": 3450
    },
    {
      "epoch": 4.524338517471218,
      "grad_norm": 0.24032790958881378,
      "learning_rate": 9.694555112881806e-06,
      "loss": 2.2225,
      "step": 3500
    },
    {
      "epoch": 4.588971924863664,
      "grad_norm": 0.2536959648132324,
      "learning_rate": 8.366533864541832e-06,
      "loss": 2.2047,
      "step": 3550
    },
    {
      "epoch": 4.6536053322561095,
      "grad_norm": 0.2353695183992386,
      "learning_rate": 7.03851261620186e-06,
      "loss": 2.2158,
      "step": 3600
    },
    {
      "epoch": 4.718238739648556,
      "grad_norm": 0.23979786038398743,
      "learning_rate": 5.710491367861886e-06,
      "loss": 2.219,
      "step": 3650
    },
    {
      "epoch": 4.782872147041002,
      "grad_norm": 0.2803194522857666,
      "learning_rate": 4.382470119521913e-06,
      "loss": 2.193,
      "step": 3700
    },
    {
      "epoch": 4.8475055544334475,
      "grad_norm": 0.24206270277500153,
      "learning_rate": 3.054448871181939e-06,
      "loss": 2.2079,
      "step": 3750
    },
    {
      "epoch": 4.8475055544334475,
      "eval_loss": 2.145188093185425,
      "eval_runtime": 669.1927,
      "eval_samples_per_second": 12.321,
      "eval_steps_per_second": 12.321,
      "step": 3750
    }
  ],
  "logging_steps": 50,
  "max_steps": 3865,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 750,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3013315141632e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}