{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.032287357481586114,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.071839370396528e-05,
      "eval_loss": 2.9267213344573975,
      "eval_runtime": 254.0364,
      "eval_samples_per_second": 20.536,
      "eval_steps_per_second": 10.27,
      "step": 1
    },
    {
      "epoch": 0.0004035919685198265,
      "grad_norm": 1.9665324687957764,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.1213,
      "step": 5
    },
    {
      "epoch": 0.000807183937039653,
      "grad_norm": 2.853644609451294,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.1493,
      "step": 10
    },
    {
      "epoch": 0.0012107759055594793,
      "grad_norm": 2.8174123764038086,
      "learning_rate": 5e-05,
      "loss": 2.1459,
      "step": 15
    },
    {
      "epoch": 0.001614367874079306,
      "grad_norm": 2.9458963871002197,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.028,
      "step": 20
    },
    {
      "epoch": 0.002017959842599132,
      "grad_norm": 2.6082279682159424,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.7688,
      "step": 25
    },
    {
      "epoch": 0.0024215518111189585,
      "grad_norm": 3.298877477645874,
      "learning_rate": 0.0001,
      "loss": 1.7904,
      "step": 30
    },
    {
      "epoch": 0.0028251437796387854,
      "grad_norm": 3.37107515335083,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.8178,
      "step": 35
    },
    {
      "epoch": 0.003228735748158612,
      "grad_norm": 3.6182897090911865,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.8115,
      "step": 40
    },
    {
      "epoch": 0.0036323277166784382,
      "grad_norm": 5.977401256561279,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.6287,
      "step": 45
    },
    {
      "epoch": 0.004035919685198264,
      "grad_norm": 10.792816162109375,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.2742,
      "step": 50
    },
    {
      "epoch": 0.004439511653718091,
      "grad_norm": 2.0686330795288086,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.7218,
      "step": 55
    },
    {
      "epoch": 0.004843103622237917,
      "grad_norm": 1.7458947896957397,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.6616,
      "step": 60
    },
    {
      "epoch": 0.005246695590757744,
      "grad_norm": 1.9402254819869995,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.6819,
      "step": 65
    },
    {
      "epoch": 0.005650287559277571,
      "grad_norm": 2.1699295043945312,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.6935,
      "step": 70
    },
    {
      "epoch": 0.006053879527797397,
      "grad_norm": 2.3528671264648438,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.5328,
      "step": 75
    },
    {
      "epoch": 0.006457471496317224,
      "grad_norm": 2.841615676879883,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.7692,
      "step": 80
    },
    {
      "epoch": 0.00686106346483705,
      "grad_norm": 2.9968481063842773,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.6042,
      "step": 85
    },
    {
      "epoch": 0.0072646554333568765,
      "grad_norm": 4.039740562438965,
      "learning_rate": 9.365070565805941e-05,
      "loss": 1.8302,
      "step": 90
    },
    {
      "epoch": 0.0076682474018767025,
      "grad_norm": 4.861767768859863,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.5007,
      "step": 95
    },
    {
      "epoch": 0.008071839370396528,
      "grad_norm": 7.6796956062316895,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.7338,
      "step": 100
    },
    {
      "epoch": 0.008071839370396528,
      "eval_loss": 1.672619104385376,
      "eval_runtime": 254.2426,
      "eval_samples_per_second": 20.52,
      "eval_steps_per_second": 10.262,
      "step": 100
    },
    {
      "epoch": 0.008475431338916355,
      "grad_norm": 1.7291655540466309,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.7688,
      "step": 105
    },
    {
      "epoch": 0.008879023307436182,
      "grad_norm": 1.6311088800430298,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.6704,
      "step": 110
    },
    {
      "epoch": 0.009282615275956009,
      "grad_norm": 1.9020378589630127,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.6435,
      "step": 115
    },
    {
      "epoch": 0.009686207244475834,
      "grad_norm": 1.9643412828445435,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.6372,
      "step": 120
    },
    {
      "epoch": 0.010089799212995661,
      "grad_norm": 1.8814764022827148,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.6451,
      "step": 125
    },
    {
      "epoch": 0.010493391181515488,
      "grad_norm": 2.3360278606414795,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.6052,
      "step": 130
    },
    {
      "epoch": 0.010896983150035315,
      "grad_norm": 2.4458420276641846,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.6387,
      "step": 135
    },
    {
      "epoch": 0.011300575118555142,
      "grad_norm": 3.890840768814087,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.7651,
      "step": 140
    },
    {
      "epoch": 0.011704167087074967,
      "grad_norm": 4.642307281494141,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.5713,
      "step": 145
    },
    {
      "epoch": 0.012107759055594794,
      "grad_norm": 10.579557418823242,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.0303,
      "step": 150
    },
    {
      "epoch": 0.01251135102411462,
      "grad_norm": 1.335777997970581,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.7595,
      "step": 155
    },
    {
      "epoch": 0.012914942992634447,
      "grad_norm": 1.4348762035369873,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.6011,
      "step": 160
    },
    {
      "epoch": 0.013318534961154272,
      "grad_norm": 1.7582004070281982,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.693,
      "step": 165
    },
    {
      "epoch": 0.0137221269296741,
      "grad_norm": 1.784987449645996,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.5561,
      "step": 170
    },
    {
      "epoch": 0.014125718898193926,
      "grad_norm": 1.9758257865905762,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.5579,
      "step": 175
    },
    {
      "epoch": 0.014529310866713753,
      "grad_norm": 2.6056525707244873,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.4892,
      "step": 180
    },
    {
      "epoch": 0.014932902835233578,
      "grad_norm": 2.6069564819335938,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.5848,
      "step": 185
    },
    {
      "epoch": 0.015336494803753405,
      "grad_norm": 3.2598531246185303,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.4015,
      "step": 190
    },
    {
      "epoch": 0.015740086772273232,
      "grad_norm": 4.954011917114258,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.4134,
      "step": 195
    },
    {
      "epoch": 0.016143678740793057,
      "grad_norm": 7.3740739822387695,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.9365,
      "step": 200
    },
    {
      "epoch": 0.016143678740793057,
      "eval_loss": 1.6026960611343384,
      "eval_runtime": 254.1386,
      "eval_samples_per_second": 20.528,
      "eval_steps_per_second": 10.266,
      "step": 200
    },
    {
      "epoch": 0.016547270709312886,
      "grad_norm": 1.6438796520233154,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.8224,
      "step": 205
    },
    {
      "epoch": 0.01695086267783271,
      "grad_norm": 1.6149935722351074,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.6417,
      "step": 210
    },
    {
      "epoch": 0.01735445464635254,
      "grad_norm": 2.108107328414917,
      "learning_rate": 5e-05,
      "loss": 1.5764,
      "step": 215
    },
    {
      "epoch": 0.017758046614872364,
      "grad_norm": 2.1685428619384766,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.6863,
      "step": 220
    },
    {
      "epoch": 0.01816163858339219,
      "grad_norm": 1.8654464483261108,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.4793,
      "step": 225
    },
    {
      "epoch": 0.018565230551912018,
      "grad_norm": 2.7222697734832764,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.6539,
      "step": 230
    },
    {
      "epoch": 0.018968822520431843,
      "grad_norm": 2.229513168334961,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.5234,
      "step": 235
    },
    {
      "epoch": 0.01937241448895167,
      "grad_norm": 3.0781612396240234,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.6744,
      "step": 240
    },
    {
      "epoch": 0.019776006457471497,
      "grad_norm": 5.477749347686768,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.5976,
      "step": 245
    },
    {
      "epoch": 0.020179598425991322,
      "grad_norm": 11.044695854187012,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.0293,
      "step": 250
    },
    {
      "epoch": 0.02058319039451115,
      "grad_norm": 1.5895485877990723,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.7317,
      "step": 255
    },
    {
      "epoch": 0.020986782363030976,
      "grad_norm": 1.6849926710128784,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.7916,
      "step": 260
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 1.9075335264205933,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.5403,
      "step": 265
    },
    {
      "epoch": 0.02179396630007063,
      "grad_norm": 2.1406710147857666,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.6099,
      "step": 270
    },
    {
      "epoch": 0.022197558268590455,
      "grad_norm": 2.293320417404175,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.5294,
      "step": 275
    },
    {
      "epoch": 0.022601150237110283,
      "grad_norm": 2.5017166137695312,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.6145,
      "step": 280
    },
    {
      "epoch": 0.02300474220563011,
      "grad_norm": 2.492234468460083,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.4807,
      "step": 285
    },
    {
      "epoch": 0.023408334174149933,
      "grad_norm": 3.7977869510650635,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.5995,
      "step": 290
    },
    {
      "epoch": 0.023811926142669762,
      "grad_norm": 5.191235542297363,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.7034,
      "step": 295
    },
    {
      "epoch": 0.024215518111189587,
      "grad_norm": 12.2208890914917,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.7647,
      "step": 300
    },
    {
      "epoch": 0.024215518111189587,
      "eval_loss": 1.5724891424179077,
      "eval_runtime": 254.2461,
      "eval_samples_per_second": 20.519,
      "eval_steps_per_second": 10.262,
      "step": 300
    },
    {
      "epoch": 0.024619110079709412,
      "grad_norm": 1.5499060153961182,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.6583,
      "step": 305
    },
    {
      "epoch": 0.02502270204822924,
      "grad_norm": 1.684057354927063,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.6127,
      "step": 310
    },
    {
      "epoch": 0.025426294016749066,
      "grad_norm": 1.7628695964813232,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.5816,
      "step": 315
    },
    {
      "epoch": 0.025829885985268895,
      "grad_norm": 2.0090019702911377,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.4357,
      "step": 320
    },
    {
      "epoch": 0.02623347795378872,
      "grad_norm": 1.926121711730957,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.5156,
      "step": 325
    },
    {
      "epoch": 0.026637069922308545,
      "grad_norm": 2.229292392730713,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.5255,
      "step": 330
    },
    {
      "epoch": 0.027040661890828373,
      "grad_norm": 2.711609363555908,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.5087,
      "step": 335
    },
    {
      "epoch": 0.0274442538593482,
      "grad_norm": 3.811401605606079,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.4701,
      "step": 340
    },
    {
      "epoch": 0.027847845827868027,
      "grad_norm": 4.1732497215271,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.6562,
      "step": 345
    },
    {
      "epoch": 0.028251437796387852,
      "grad_norm": 14.904296875,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.6435,
      "step": 350
    },
    {
      "epoch": 0.028655029764907677,
      "grad_norm": 1.3880417346954346,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.6036,
      "step": 355
    },
    {
      "epoch": 0.029058621733427506,
      "grad_norm": 1.6037483215332031,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.5786,
      "step": 360
    },
    {
      "epoch": 0.02946221370194733,
      "grad_norm": 1.7933096885681152,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.6051,
      "step": 365
    },
    {
      "epoch": 0.029865805670467156,
      "grad_norm": 2.014568328857422,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.5183,
      "step": 370
    },
    {
      "epoch": 0.030269397638986985,
      "grad_norm": 2.4542417526245117,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.7436,
      "step": 375
    },
    {
      "epoch": 0.03067298960750681,
      "grad_norm": 2.3807358741760254,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.6063,
      "step": 380
    },
    {
      "epoch": 0.03107658157602664,
      "grad_norm": 2.7650787830352783,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.5745,
      "step": 385
    },
    {
      "epoch": 0.031480173544546464,
      "grad_norm": 3.726191997528076,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.4227,
      "step": 390
    },
    {
      "epoch": 0.03188376551306629,
      "grad_norm": 4.394490718841553,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.5233,
      "step": 395
    },
    {
      "epoch": 0.032287357481586114,
      "grad_norm": 10.233359336853027,
      "learning_rate": 0.0,
      "loss": 1.7269,
      "step": 400
    },
    {
      "epoch": 0.032287357481586114,
      "eval_loss": 1.5665189027786255,
      "eval_runtime": 254.1014,
      "eval_samples_per_second": 20.531,
      "eval_steps_per_second": 10.268,
      "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": 4.003279132321382e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}