{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.08056394763343404,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002014098690835851,
      "eval_loss": 3.9293839931488037,
      "eval_runtime": 260.3257,
      "eval_samples_per_second": 8.032,
      "eval_steps_per_second": 4.018,
      "step": 1
    },
    {
      "epoch": 0.0010070493454179255,
      "grad_norm": 1.801853895187378,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.5497,
      "step": 5
    },
    {
      "epoch": 0.002014098690835851,
      "grad_norm": 2.3337671756744385,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3354,
      "step": 10
    },
    {
      "epoch": 0.0030211480362537764,
      "grad_norm": 2.0608904361724854,
      "learning_rate": 5e-05,
      "loss": 2.1899,
      "step": 15
    },
    {
      "epoch": 0.004028197381671702,
      "grad_norm": 1.8448073863983154,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.3414,
      "step": 20
    },
    {
      "epoch": 0.005035246727089627,
      "grad_norm": 1.518567442893982,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.1116,
      "step": 25
    },
    {
      "epoch": 0.006042296072507553,
      "grad_norm": 1.5217000246047974,
      "learning_rate": 0.0001,
      "loss": 1.8218,
      "step": 30
    },
    {
      "epoch": 0.007049345417925478,
      "grad_norm": 2.240260124206543,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.9933,
      "step": 35
    },
    {
      "epoch": 0.008056394763343404,
      "grad_norm": 11.408411979675293,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.534,
      "step": 40
    },
    {
      "epoch": 0.00906344410876133,
      "grad_norm": 3.084709644317627,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.0311,
      "step": 45
    },
    {
      "epoch": 0.010070493454179255,
      "grad_norm": 1.8154520988464355,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.11,
      "step": 50
    },
    {
      "epoch": 0.011077542799597181,
      "grad_norm": 1.8713270425796509,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.9133,
      "step": 55
    },
    {
      "epoch": 0.012084592145015106,
      "grad_norm": 1.747025966644287,
      "learning_rate": 9.838664734667495e-05,
      "loss": 1.3745,
      "step": 60
    },
    {
      "epoch": 0.013091641490433032,
      "grad_norm": 1.7378616333007812,
      "learning_rate": 9.780833673696254e-05,
      "loss": 1.7327,
      "step": 65
    },
    {
      "epoch": 0.014098690835850957,
      "grad_norm": 1.4642333984375,
      "learning_rate": 9.714387227305422e-05,
      "loss": 1.9047,
      "step": 70
    },
    {
      "epoch": 0.015105740181268883,
      "grad_norm": 1.4582387208938599,
      "learning_rate": 9.639445136482548e-05,
      "loss": 1.7437,
      "step": 75
    },
    {
      "epoch": 0.016112789526686808,
      "grad_norm": 1.7316182851791382,
      "learning_rate": 9.55614245194068e-05,
      "loss": 1.957,
      "step": 80
    },
    {
      "epoch": 0.017119838872104734,
      "grad_norm": 2.643414258956909,
      "learning_rate": 9.464629290747842e-05,
      "loss": 1.6853,
      "step": 85
    },
    {
      "epoch": 0.01812688821752266,
      "grad_norm": 0.9490913152694702,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.8754,
      "step": 90
    },
    {
      "epoch": 0.019133937562940583,
      "grad_norm": 0.9377123713493347,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.0984,
      "step": 95
    },
    {
      "epoch": 0.02014098690835851,
      "grad_norm": 1.0288959741592407,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.1233,
      "step": 100
    },
    {
      "epoch": 0.02014098690835851,
      "eval_loss": 1.1744722127914429,
      "eval_runtime": 262.3545,
      "eval_samples_per_second": 7.97,
      "eval_steps_per_second": 3.987,
      "step": 100
    },
    {
      "epoch": 0.021148036253776436,
      "grad_norm": 1.6373826265335083,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.6488,
      "step": 105
    },
    {
      "epoch": 0.022155085599194362,
      "grad_norm": 1.4394736289978027,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.1644,
      "step": 110
    },
    {
      "epoch": 0.023162134944612285,
      "grad_norm": 1.6303774118423462,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.516,
      "step": 115
    },
    {
      "epoch": 0.02416918429003021,
      "grad_norm": 1.0350350141525269,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.8225,
      "step": 120
    },
    {
      "epoch": 0.025176233635448138,
      "grad_norm": 1.2534977197647095,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.7505,
      "step": 125
    },
    {
      "epoch": 0.026183282980866064,
      "grad_norm": 1.3360565900802612,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.665,
      "step": 130
    },
    {
      "epoch": 0.027190332326283987,
      "grad_norm": 1.8108255863189697,
      "learning_rate": 8.141099986478212e-05,
      "loss": 2.0406,
      "step": 135
    },
    {
      "epoch": 0.028197381671701913,
      "grad_norm": 1.2478952407836914,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.7422,
      "step": 140
    },
    {
      "epoch": 0.02920443101711984,
      "grad_norm": 1.5493501424789429,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.0855,
      "step": 145
    },
    {
      "epoch": 0.030211480362537766,
      "grad_norm": 0.7311913371086121,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.0916,
      "step": 150
    },
    {
      "epoch": 0.03121852970795569,
      "grad_norm": 1.139947533607483,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.6681,
      "step": 155
    },
    {
      "epoch": 0.032225579053373615,
      "grad_norm": 1.029541254043579,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.2154,
      "step": 160
    },
    {
      "epoch": 0.03323262839879154,
      "grad_norm": 1.1326689720153809,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.6574,
      "step": 165
    },
    {
      "epoch": 0.03423967774420947,
      "grad_norm": 1.2490378618240356,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.918,
      "step": 170
    },
    {
      "epoch": 0.035246727089627394,
      "grad_norm": 1.1004718542099,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.7279,
      "step": 175
    },
    {
      "epoch": 0.03625377643504532,
      "grad_norm": 2.3052480220794678,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.6032,
      "step": 180
    },
    {
      "epoch": 0.03726082578046324,
      "grad_norm": 1.3891737461090088,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.6649,
      "step": 185
    },
    {
      "epoch": 0.038267875125881166,
      "grad_norm": 0.5351678133010864,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.8816,
      "step": 190
    },
    {
      "epoch": 0.03927492447129909,
      "grad_norm": 0.5733966827392578,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.1185,
      "step": 195
    },
    {
      "epoch": 0.04028197381671702,
      "grad_norm": 0.7451675534248352,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.0807,
      "step": 200
    },
    {
      "epoch": 0.04028197381671702,
      "eval_loss": 1.101949691772461,
      "eval_runtime": 262.1064,
      "eval_samples_per_second": 7.978,
      "eval_steps_per_second": 3.991,
      "step": 200
    },
    {
      "epoch": 0.041289023162134945,
      "grad_norm": 1.1515811681747437,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.4196,
      "step": 205
    },
    {
      "epoch": 0.04229607250755287,
      "grad_norm": 1.1933273077011108,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.1938,
      "step": 210
    },
    {
      "epoch": 0.0433031218529708,
      "grad_norm": 1.1736282110214233,
      "learning_rate": 5e-05,
      "loss": 1.5697,
      "step": 215
    },
    {
      "epoch": 0.044310171198388724,
      "grad_norm": 1.115051031112671,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.4818,
      "step": 220
    },
    {
      "epoch": 0.045317220543806644,
      "grad_norm": 1.5317729711532593,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.663,
      "step": 225
    },
    {
      "epoch": 0.04632426988922457,
      "grad_norm": 1.6221399307250977,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.9217,
      "step": 230
    },
    {
      "epoch": 0.0473313192346425,
      "grad_norm": 2.3496367931365967,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.5364,
      "step": 235
    },
    {
      "epoch": 0.04833836858006042,
      "grad_norm": 1.6498185396194458,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.5086,
      "step": 240
    },
    {
      "epoch": 0.04934541792547835,
      "grad_norm": 0.3783971071243286,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.1267,
      "step": 245
    },
    {
      "epoch": 0.050352467270896276,
      "grad_norm": 0.4561294615268707,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.0765,
      "step": 250
    },
    {
      "epoch": 0.0513595166163142,
      "grad_norm": 1.6815731525421143,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.4269,
      "step": 255
    },
    {
      "epoch": 0.05236656596173213,
      "grad_norm": 1.1096322536468506,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.2917,
      "step": 260
    },
    {
      "epoch": 0.05337361530715005,
      "grad_norm": 2.5379202365875244,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.2065,
      "step": 265
    },
    {
      "epoch": 0.054380664652567974,
      "grad_norm": 1.0986319780349731,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.8164,
      "step": 270
    },
    {
      "epoch": 0.0553877139979859,
      "grad_norm": 1.1980137825012207,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.6385,
      "step": 275
    },
    {
      "epoch": 0.05639476334340383,
      "grad_norm": 1.3705934286117554,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.7463,
      "step": 280
    },
    {
      "epoch": 0.05740181268882175,
      "grad_norm": 1.463427186012268,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.6451,
      "step": 285
    },
    {
      "epoch": 0.05840886203423968,
      "grad_norm": 2.7053167819976807,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.6137,
      "step": 290
    },
    {
      "epoch": 0.059415911379657606,
      "grad_norm": 0.5753213167190552,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.2913,
      "step": 295
    },
    {
      "epoch": 0.06042296072507553,
      "grad_norm": 0.49553295969963074,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.0934,
      "step": 300
    },
    {
      "epoch": 0.06042296072507553,
      "eval_loss": 1.0825552940368652,
      "eval_runtime": 262.0128,
      "eval_samples_per_second": 7.981,
      "eval_steps_per_second": 3.992,
      "step": 300
    },
    {
      "epoch": 0.06143001007049345,
      "grad_norm": 1.4289567470550537,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.354,
      "step": 305
    },
    {
      "epoch": 0.06243705941591138,
      "grad_norm": 1.0329123735427856,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.1872,
      "step": 310
    },
    {
      "epoch": 0.0634441087613293,
      "grad_norm": 0.9463292360305786,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.7491,
      "step": 315
    },
    {
      "epoch": 0.06445115810674723,
      "grad_norm": 0.9617361426353455,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.6255,
      "step": 320
    },
    {
      "epoch": 0.06545820745216516,
      "grad_norm": 1.237847924232483,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.5588,
      "step": 325
    },
    {
      "epoch": 0.06646525679758308,
      "grad_norm": 1.1357839107513428,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.6803,
      "step": 330
    },
    {
      "epoch": 0.06747230614300101,
      "grad_norm": 1.6565706729888916,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.5482,
      "step": 335
    },
    {
      "epoch": 0.06847935548841894,
      "grad_norm": 1.7569267749786377,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.0579,
      "step": 340
    },
    {
      "epoch": 0.06948640483383686,
      "grad_norm": 0.8012557029724121,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.0947,
      "step": 345
    },
    {
      "epoch": 0.07049345417925479,
      "grad_norm": 0.8056464791297913,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.1081,
      "step": 350
    },
    {
      "epoch": 0.07150050352467271,
      "grad_norm": 1.1648321151733398,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.4778,
      "step": 355
    },
    {
      "epoch": 0.07250755287009064,
      "grad_norm": 1.3627045154571533,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.218,
      "step": 360
    },
    {
      "epoch": 0.07351460221550855,
      "grad_norm": 1.473477840423584,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.8776,
      "step": 365
    },
    {
      "epoch": 0.07452165156092648,
      "grad_norm": 1.1581178903579712,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.7462,
      "step": 370
    },
    {
      "epoch": 0.0755287009063444,
      "grad_norm": 1.3446756601333618,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.7935,
      "step": 375
    },
    {
      "epoch": 0.07653575025176233,
      "grad_norm": 1.2879818677902222,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.5786,
      "step": 380
    },
    {
      "epoch": 0.07754279959718026,
      "grad_norm": 2.0988075733184814,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.7596,
      "step": 385
    },
    {
      "epoch": 0.07854984894259819,
      "grad_norm": 2.1626410484313965,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.2932,
      "step": 390
    },
    {
      "epoch": 0.07955689828801611,
      "grad_norm": 0.7162337899208069,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.0821,
      "step": 395
    },
    {
      "epoch": 0.08056394763343404,
      "grad_norm": 0.9629455804824829,
      "learning_rate": 0.0,
      "loss": 0.1163,
      "step": 400
    },
    {
      "epoch": 0.08056394763343404,
      "eval_loss": 1.070724368095398,
      "eval_runtime": 261.9703,
      "eval_samples_per_second": 7.982,
      "eval_steps_per_second": 3.993,
      "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": 1.792765824734331e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}