{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0070706981430579,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.767674535764475e-05,
      "eval_loss": 0.5372872352600098,
      "eval_runtime": 3075.9695,
      "eval_samples_per_second": 7.744,
      "eval_steps_per_second": 3.872,
      "step": 1
    },
    {
      "epoch": 8.838372678822376e-05,
      "grad_norm": 2.2278647422790527,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.3748,
      "step": 5
    },
    {
      "epoch": 0.00017676745357644752,
      "grad_norm": 1.9082380533218384,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3647,
      "step": 10
    },
    {
      "epoch": 0.00026515118036467126,
      "grad_norm": 1.1403309106826782,
      "learning_rate": 5e-05,
      "loss": 1.1797,
      "step": 15
    },
    {
      "epoch": 0.00035353490715289503,
      "grad_norm": 1.2451469898223877,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.0402,
      "step": 20
    },
    {
      "epoch": 0.00044191863394111875,
      "grad_norm": 0.9050202369689941,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.9482,
      "step": 25
    },
    {
      "epoch": 0.0005303023607293425,
      "grad_norm": 0.9164132475852966,
      "learning_rate": 0.0001,
      "loss": 0.7592,
      "step": 30
    },
    {
      "epoch": 0.0006186860875175662,
      "grad_norm": 1.4143108129501343,
      "learning_rate": 9.995494831023409e-05,
      "loss": 0.7142,
      "step": 35
    },
    {
      "epoch": 0.0007070698143057901,
      "grad_norm": 2.825472116470337,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.1137,
      "step": 40
    },
    {
      "epoch": 0.0007954535410940138,
      "grad_norm": 3.7048728466033936,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.3419,
      "step": 45
    },
    {
      "epoch": 0.0008838372678822375,
      "grad_norm": 5.984016418457031,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.364,
      "step": 50
    },
    {
      "epoch": 0.0009722209946704613,
      "grad_norm": 1.912799596786499,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.7151,
      "step": 55
    },
    {
      "epoch": 0.001060604721458685,
      "grad_norm": 0.8566750884056091,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.8463,
      "step": 60
    },
    {
      "epoch": 0.0011489884482469089,
      "grad_norm": 0.9135806560516357,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.9238,
      "step": 65
    },
    {
      "epoch": 0.0012373721750351325,
      "grad_norm": 0.9114847183227539,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.9054,
      "step": 70
    },
    {
      "epoch": 0.0013257559018233563,
      "grad_norm": 0.8945407867431641,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.8044,
      "step": 75
    },
    {
      "epoch": 0.0014141396286115801,
      "grad_norm": 0.8526774644851685,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.7125,
      "step": 80
    },
    {
      "epoch": 0.0015025233553998037,
      "grad_norm": 2.542604684829712,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.5211,
      "step": 85
    },
    {
      "epoch": 0.0015909070821880276,
      "grad_norm": 3.4258692264556885,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.232,
      "step": 90
    },
    {
      "epoch": 0.0016792908089762514,
      "grad_norm": 4.280972003936768,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.2733,
      "step": 95
    },
    {
      "epoch": 0.001767674535764475,
      "grad_norm": 5.01446008682251,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.3442,
      "step": 100
    },
    {
      "epoch": 0.001767674535764475,
      "eval_loss": 0.3212743103504181,
      "eval_runtime": 3087.4035,
      "eval_samples_per_second": 7.715,
      "eval_steps_per_second": 3.858,
      "step": 100
    },
    {
      "epoch": 0.0018560582625526988,
      "grad_norm": 1.431134819984436,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.0173,
      "step": 105
    },
    {
      "epoch": 0.0019444419893409226,
      "grad_norm": 0.9470636248588562,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.9964,
      "step": 110
    },
    {
      "epoch": 0.0020328257161291463,
      "grad_norm": 1.1996196508407593,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.7888,
      "step": 115
    },
    {
      "epoch": 0.00212120944291737,
      "grad_norm": 1.1377532482147217,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.8801,
      "step": 120
    },
    {
      "epoch": 0.002209593169705594,
      "grad_norm": 1.0124013423919678,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.9192,
      "step": 125
    },
    {
      "epoch": 0.0022979768964938177,
      "grad_norm": 0.8448017239570618,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.7762,
      "step": 130
    },
    {
      "epoch": 0.002386360623282041,
      "grad_norm": 2.1916205883026123,
      "learning_rate": 8.141099986478212e-05,
      "loss": 0.8963,
      "step": 135
    },
    {
      "epoch": 0.002474744350070265,
      "grad_norm": 3.528238534927368,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.1816,
      "step": 140
    },
    {
      "epoch": 0.0025631280768584888,
      "grad_norm": 3.383457660675049,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.291,
      "step": 145
    },
    {
      "epoch": 0.0026515118036467126,
      "grad_norm": 5.739030361175537,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.3132,
      "step": 150
    },
    {
      "epoch": 0.0027398955304349364,
      "grad_norm": 0.8546879887580872,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.891,
      "step": 155
    },
    {
      "epoch": 0.0028282792572231603,
      "grad_norm": 0.9319010972976685,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.8968,
      "step": 160
    },
    {
      "epoch": 0.0029166629840113836,
      "grad_norm": 0.9063301086425781,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.7938,
      "step": 165
    },
    {
      "epoch": 0.0030050467107996075,
      "grad_norm": 0.8464365601539612,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.9262,
      "step": 170
    },
    {
      "epoch": 0.0030934304375878313,
      "grad_norm": 1.000476598739624,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.7753,
      "step": 175
    },
    {
      "epoch": 0.003181814164376055,
      "grad_norm": 0.7965553998947144,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.6623,
      "step": 180
    },
    {
      "epoch": 0.003270197891164279,
      "grad_norm": 1.8223626613616943,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.9768,
      "step": 185
    },
    {
      "epoch": 0.0033585816179525028,
      "grad_norm": 3.0601987838745117,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.2059,
      "step": 190
    },
    {
      "epoch": 0.003446965344740726,
      "grad_norm": 3.8258354663848877,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.329,
      "step": 195
    },
    {
      "epoch": 0.00353534907152895,
      "grad_norm": 5.148533344268799,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.0605,
      "step": 200
    },
    {
      "epoch": 0.00353534907152895,
      "eval_loss": 0.3107931613922119,
      "eval_runtime": 3085.5449,
      "eval_samples_per_second": 7.72,
      "eval_steps_per_second": 3.86,
      "step": 200
    },
    {
      "epoch": 0.003623732798317174,
      "grad_norm": 0.7606380581855774,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.8572,
      "step": 205
    },
    {
      "epoch": 0.0037121165251053976,
      "grad_norm": 0.829315185546875,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.0276,
      "step": 210
    },
    {
      "epoch": 0.0038005002518936215,
      "grad_norm": 0.8054685592651367,
      "learning_rate": 5e-05,
      "loss": 0.812,
      "step": 215
    },
    {
      "epoch": 0.0038888839786818453,
      "grad_norm": 0.7430157661437988,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.6373,
      "step": 220
    },
    {
      "epoch": 0.003977267705470069,
      "grad_norm": 0.7938749194145203,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.7831,
      "step": 225
    },
    {
      "epoch": 0.0040656514322582925,
      "grad_norm": 0.6796129941940308,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.6196,
      "step": 230
    },
    {
      "epoch": 0.004154035159046517,
      "grad_norm": 1.8476696014404297,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.1534,
      "step": 235
    },
    {
      "epoch": 0.00424241888583474,
      "grad_norm": 2.7192931175231934,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.9933,
      "step": 240
    },
    {
      "epoch": 0.0043308026126229636,
      "grad_norm": 3.7205464839935303,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.1978,
      "step": 245
    },
    {
      "epoch": 0.004419186339411188,
      "grad_norm": 5.386031627655029,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.1391,
      "step": 250
    },
    {
      "epoch": 0.004507570066199411,
      "grad_norm": 0.9558156132698059,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.783,
      "step": 255
    },
    {
      "epoch": 0.0045959537929876355,
      "grad_norm": 0.9140355587005615,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.8551,
      "step": 260
    },
    {
      "epoch": 0.004684337519775859,
      "grad_norm": 0.7540270686149597,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.836,
      "step": 265
    },
    {
      "epoch": 0.004772721246564082,
      "grad_norm": 1.0133373737335205,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.8893,
      "step": 270
    },
    {
      "epoch": 0.0048611049733523065,
      "grad_norm": 0.9587008357048035,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.833,
      "step": 275
    },
    {
      "epoch": 0.00494948870014053,
      "grad_norm": 0.8091663122177124,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.6511,
      "step": 280
    },
    {
      "epoch": 0.005037872426928754,
      "grad_norm": 1.8884278535842896,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.1074,
      "step": 285
    },
    {
      "epoch": 0.0051262561537169776,
      "grad_norm": 2.654372453689575,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.8667,
      "step": 290
    },
    {
      "epoch": 0.005214639880505201,
      "grad_norm": 3.637286424636841,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.4647,
      "step": 295
    },
    {
      "epoch": 0.005303023607293425,
      "grad_norm": 6.978252410888672,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.0052,
      "step": 300
    },
    {
      "epoch": 0.005303023607293425,
      "eval_loss": 0.29683175683021545,
      "eval_runtime": 3086.2182,
      "eval_samples_per_second": 7.718,
      "eval_steps_per_second": 3.859,
      "step": 300
    },
    {
      "epoch": 0.005391407334081649,
      "grad_norm": 0.8735937476158142,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.8976,
      "step": 305
    },
    {
      "epoch": 0.005479791060869873,
      "grad_norm": 1.0058103799819946,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.9457,
      "step": 310
    },
    {
      "epoch": 0.005568174787658096,
      "grad_norm": 0.8313906788825989,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.8553,
      "step": 315
    },
    {
      "epoch": 0.0056565585144463205,
      "grad_norm": 0.8653046488761902,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.8907,
      "step": 320
    },
    {
      "epoch": 0.005744942241234544,
      "grad_norm": 0.847143292427063,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.6989,
      "step": 325
    },
    {
      "epoch": 0.005833325968022767,
      "grad_norm": 0.68266761302948,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.5254,
      "step": 330
    },
    {
      "epoch": 0.0059217096948109916,
      "grad_norm": 1.959128975868225,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.4868,
      "step": 335
    },
    {
      "epoch": 0.006010093421599215,
      "grad_norm": 2.8061609268188477,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.8476,
      "step": 340
    },
    {
      "epoch": 0.006098477148387439,
      "grad_norm": 3.494671106338501,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.9511,
      "step": 345
    },
    {
      "epoch": 0.006186860875175663,
      "grad_norm": 5.8989458084106445,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.348,
      "step": 350
    },
    {
      "epoch": 0.006275244601963886,
      "grad_norm": 1.1299041509628296,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.8424,
      "step": 355
    },
    {
      "epoch": 0.00636362832875211,
      "grad_norm": 0.7857906222343445,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.7691,
      "step": 360
    },
    {
      "epoch": 0.006452012055540334,
      "grad_norm": 0.8707722425460815,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.8601,
      "step": 365
    },
    {
      "epoch": 0.006540395782328558,
      "grad_norm": 0.9295032620429993,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.7463,
      "step": 370
    },
    {
      "epoch": 0.006628779509116781,
      "grad_norm": 1.0481330156326294,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.86,
      "step": 375
    },
    {
      "epoch": 0.0067171632359050056,
      "grad_norm": 0.8074281811714172,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.5899,
      "step": 380
    },
    {
      "epoch": 0.006805546962693229,
      "grad_norm": 1.9890309572219849,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.0344,
      "step": 385
    },
    {
      "epoch": 0.006893930689481452,
      "grad_norm": 2.80163311958313,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.9024,
      "step": 390
    },
    {
      "epoch": 0.006982314416269677,
      "grad_norm": 4.167541980743408,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.1198,
      "step": 395
    },
    {
      "epoch": 0.0070706981430579,
      "grad_norm": 5.854891777038574,
      "learning_rate": 0.0,
      "loss": 2.1522,
      "step": 400
    },
    {
      "epoch": 0.0070706981430579,
      "eval_loss": 0.29341384768486023,
      "eval_runtime": 3086.1522,
      "eval_samples_per_second": 7.718,
      "eval_steps_per_second": 3.859,
      "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": 2.32404280575787e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}