{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03375171395422424,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.437928488556059e-05,
      "eval_loss": 0.9957674145698547,
      "eval_runtime": 419.6878,
      "eval_samples_per_second": 11.89,
      "eval_steps_per_second": 5.945,
      "step": 1
    },
    {
      "epoch": 0.00042189642442780296,
      "grad_norm": 0.4106890559196472,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.8825,
      "step": 5
    },
    {
      "epoch": 0.0008437928488556059,
      "grad_norm": 0.5586373209953308,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.9305,
      "step": 10
    },
    {
      "epoch": 0.0012656892732834089,
      "grad_norm": 0.5272752046585083,
      "learning_rate": 5e-05,
      "loss": 0.9003,
      "step": 15
    },
    {
      "epoch": 0.0016875856977112118,
      "grad_norm": 0.5173702836036682,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.7796,
      "step": 20
    },
    {
      "epoch": 0.002109482122139015,
      "grad_norm": 0.5352601408958435,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.8669,
      "step": 25
    },
    {
      "epoch": 0.0025313785465668178,
      "grad_norm": 0.48157429695129395,
      "learning_rate": 0.0001,
      "loss": 0.835,
      "step": 30
    },
    {
      "epoch": 0.0029532749709946207,
      "grad_norm": 0.5189157724380493,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.7987,
      "step": 35
    },
    {
      "epoch": 0.0033751713954224237,
      "grad_norm": 0.5436115860939026,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.9009,
      "step": 40
    },
    {
      "epoch": 0.0037970678198502267,
      "grad_norm": 0.6219505071640015,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.8412,
      "step": 45
    },
    {
      "epoch": 0.00421896424427803,
      "grad_norm": 1.6684471368789673,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.9159,
      "step": 50
    },
    {
      "epoch": 0.004640860668705833,
      "grad_norm": 0.5012656450271606,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.7569,
      "step": 55
    },
    {
      "epoch": 0.0050627570931336355,
      "grad_norm": 0.35097789764404297,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.7247,
      "step": 60
    },
    {
      "epoch": 0.005484653517561439,
      "grad_norm": 0.4114624261856079,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.78,
      "step": 65
    },
    {
      "epoch": 0.0059065499419892415,
      "grad_norm": 0.39524176716804504,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.7716,
      "step": 70
    },
    {
      "epoch": 0.006328446366417045,
      "grad_norm": 0.39941051602363586,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.8346,
      "step": 75
    },
    {
      "epoch": 0.006750342790844847,
      "grad_norm": 0.38641512393951416,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.7287,
      "step": 80
    },
    {
      "epoch": 0.007172239215272651,
      "grad_norm": 0.5262604355812073,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.7636,
      "step": 85
    },
    {
      "epoch": 0.007594135639700453,
      "grad_norm": 0.605768084526062,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.8944,
      "step": 90
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 0.6336283683776855,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.8311,
      "step": 95
    },
    {
      "epoch": 0.00843792848855606,
      "grad_norm": 1.458014965057373,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.8093,
      "step": 100
    },
    {
      "epoch": 0.00843792848855606,
      "eval_loss": 0.7453532814979553,
      "eval_runtime": 421.5346,
      "eval_samples_per_second": 11.838,
      "eval_steps_per_second": 5.919,
      "step": 100
    },
    {
      "epoch": 0.008859824912983863,
      "grad_norm": 0.3544303774833679,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.6757,
      "step": 105
    },
    {
      "epoch": 0.009281721337411666,
      "grad_norm": 0.31981468200683594,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.7116,
      "step": 110
    },
    {
      "epoch": 0.009703617761839468,
      "grad_norm": 0.3641217350959778,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.704,
      "step": 115
    },
    {
      "epoch": 0.010125514186267271,
      "grad_norm": 0.41695696115493774,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.6933,
      "step": 120
    },
    {
      "epoch": 0.010547410610695074,
      "grad_norm": 0.40811964869499207,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.7293,
      "step": 125
    },
    {
      "epoch": 0.010969307035122878,
      "grad_norm": 0.4640657901763916,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.8195,
      "step": 130
    },
    {
      "epoch": 0.01139120345955068,
      "grad_norm": 0.4916837811470032,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.7061,
      "step": 135
    },
    {
      "epoch": 0.011813099883978483,
      "grad_norm": 0.43793752789497375,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.8276,
      "step": 140
    },
    {
      "epoch": 0.012234996308406286,
      "grad_norm": 0.6117736101150513,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.893,
      "step": 145
    },
    {
      "epoch": 0.01265689273283409,
      "grad_norm": 1.3102891445159912,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.8688,
      "step": 150
    },
    {
      "epoch": 0.013078789157261891,
      "grad_norm": 0.35164037346839905,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.5983,
      "step": 155
    },
    {
      "epoch": 0.013500685581689695,
      "grad_norm": 0.32440951466560364,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.6319,
      "step": 160
    },
    {
      "epoch": 0.013922582006117498,
      "grad_norm": 0.36062324047088623,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.6391,
      "step": 165
    },
    {
      "epoch": 0.014344478430545302,
      "grad_norm": 0.38565579056739807,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.6643,
      "step": 170
    },
    {
      "epoch": 0.014766374854973103,
      "grad_norm": 0.411285400390625,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.7558,
      "step": 175
    },
    {
      "epoch": 0.015188271279400907,
      "grad_norm": 0.3739734888076782,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.6523,
      "step": 180
    },
    {
      "epoch": 0.01561016770382871,
      "grad_norm": 0.4831923842430115,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.7802,
      "step": 185
    },
    {
      "epoch": 0.01603206412825651,
      "grad_norm": 0.5024823546409607,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.6872,
      "step": 190
    },
    {
      "epoch": 0.016453960552684315,
      "grad_norm": 0.6557715535163879,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.7473,
      "step": 195
    },
    {
      "epoch": 0.01687585697711212,
      "grad_norm": 1.3833485841751099,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.8261,
      "step": 200
    },
    {
      "epoch": 0.01687585697711212,
      "eval_loss": 0.7295480370521545,
      "eval_runtime": 421.3959,
      "eval_samples_per_second": 11.842,
      "eval_steps_per_second": 5.921,
      "step": 200
    },
    {
      "epoch": 0.017297753401539922,
      "grad_norm": 0.4051777720451355,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.6449,
      "step": 205
    },
    {
      "epoch": 0.017719649825967725,
      "grad_norm": 0.36194536089897156,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.7147,
      "step": 210
    },
    {
      "epoch": 0.01814154625039553,
      "grad_norm": 0.37661212682724,
      "learning_rate": 5e-05,
      "loss": 0.734,
      "step": 215
    },
    {
      "epoch": 0.018563442674823332,
      "grad_norm": 0.37295767664909363,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.6716,
      "step": 220
    },
    {
      "epoch": 0.018985339099251135,
      "grad_norm": 0.474931001663208,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.749,
      "step": 225
    },
    {
      "epoch": 0.019407235523678935,
      "grad_norm": 0.5339241027832031,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.8035,
      "step": 230
    },
    {
      "epoch": 0.01982913194810674,
      "grad_norm": 0.546904981136322,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.7336,
      "step": 235
    },
    {
      "epoch": 0.020251028372534542,
      "grad_norm": 0.5156819820404053,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.7587,
      "step": 240
    },
    {
      "epoch": 0.020672924796962346,
      "grad_norm": 0.5965439677238464,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.9158,
      "step": 245
    },
    {
      "epoch": 0.02109482122139015,
      "grad_norm": 1.0562564134597778,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.0234,
      "step": 250
    },
    {
      "epoch": 0.021516717645817952,
      "grad_norm": 0.33975425362586975,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.6781,
      "step": 255
    },
    {
      "epoch": 0.021938614070245756,
      "grad_norm": 0.31108027696609497,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.6653,
      "step": 260
    },
    {
      "epoch": 0.02236051049467356,
      "grad_norm": 0.3663179874420166,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.6752,
      "step": 265
    },
    {
      "epoch": 0.02278240691910136,
      "grad_norm": 0.5073758363723755,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.7357,
      "step": 270
    },
    {
      "epoch": 0.023204303343529162,
      "grad_norm": 0.41087105870246887,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.6715,
      "step": 275
    },
    {
      "epoch": 0.023626199767956966,
      "grad_norm": 0.4009557068347931,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.6759,
      "step": 280
    },
    {
      "epoch": 0.02404809619238477,
      "grad_norm": 0.46906349062919617,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.7395,
      "step": 285
    },
    {
      "epoch": 0.024469992616812573,
      "grad_norm": 0.6131988763809204,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.8374,
      "step": 290
    },
    {
      "epoch": 0.024891889041240376,
      "grad_norm": 0.735552191734314,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.9337,
      "step": 295
    },
    {
      "epoch": 0.02531378546566818,
      "grad_norm": 1.2397476434707642,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.8693,
      "step": 300
    },
    {
      "epoch": 0.02531378546566818,
      "eval_loss": 0.718722939491272,
      "eval_runtime": 421.5469,
      "eval_samples_per_second": 11.837,
      "eval_steps_per_second": 5.919,
      "step": 300
    },
    {
      "epoch": 0.025735681890095983,
      "grad_norm": 0.2928362786769867,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.6769,
      "step": 305
    },
    {
      "epoch": 0.026157578314523783,
      "grad_norm": 0.35365402698516846,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.6254,
      "step": 310
    },
    {
      "epoch": 0.026579474738951586,
      "grad_norm": 0.3873966634273529,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.7157,
      "step": 315
    },
    {
      "epoch": 0.02700137116337939,
      "grad_norm": 0.42512309551239014,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.7382,
      "step": 320
    },
    {
      "epoch": 0.027423267587807193,
      "grad_norm": 0.45126789808273315,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.6671,
      "step": 325
    },
    {
      "epoch": 0.027845164012234996,
      "grad_norm": 0.4876130223274231,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.7558,
      "step": 330
    },
    {
      "epoch": 0.0282670604366628,
      "grad_norm": 0.4966984689235687,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.7365,
      "step": 335
    },
    {
      "epoch": 0.028688956861090603,
      "grad_norm": 0.4963556230068207,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.7839,
      "step": 340
    },
    {
      "epoch": 0.029110853285518407,
      "grad_norm": 0.5703970193862915,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.6884,
      "step": 345
    },
    {
      "epoch": 0.029532749709946206,
      "grad_norm": 1.9548819065093994,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.012,
      "step": 350
    },
    {
      "epoch": 0.02995464613437401,
      "grad_norm": 0.31155750155448914,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.6154,
      "step": 355
    },
    {
      "epoch": 0.030376542558801813,
      "grad_norm": 0.2996324896812439,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.733,
      "step": 360
    },
    {
      "epoch": 0.030798438983229617,
      "grad_norm": 0.37856683135032654,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.6717,
      "step": 365
    },
    {
      "epoch": 0.03122033540765742,
      "grad_norm": 0.37820345163345337,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.6931,
      "step": 370
    },
    {
      "epoch": 0.03164223183208522,
      "grad_norm": 0.39253878593444824,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.6896,
      "step": 375
    },
    {
      "epoch": 0.03206412825651302,
      "grad_norm": 0.4378221035003662,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.752,
      "step": 380
    },
    {
      "epoch": 0.03248602468094083,
      "grad_norm": 0.5840653777122498,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.6758,
      "step": 385
    },
    {
      "epoch": 0.03290792110536863,
      "grad_norm": 0.6441401839256287,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.7952,
      "step": 390
    },
    {
      "epoch": 0.033329817529796434,
      "grad_norm": 0.6340252161026001,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.779,
      "step": 395
    },
    {
      "epoch": 0.03375171395422424,
      "grad_norm": 1.275892734527588,
      "learning_rate": 0.0,
      "loss": 0.9144,
      "step": 400
    },
    {
      "epoch": 0.03375171395422424,
      "eval_loss": 0.7176097631454468,
      "eval_runtime": 421.8457,
      "eval_samples_per_second": 11.829,
      "eval_steps_per_second": 5.914,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 1.5129435549833626e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}