{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.16532341392849761,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004133085348212441,
      "eval_loss": 1.703283429145813,
      "eval_runtime": 130.4689,
      "eval_samples_per_second": 7.81,
      "eval_steps_per_second": 3.909,
      "step": 1
    },
    {
      "epoch": 0.0020665426741062203,
      "grad_norm": 1.026974081993103,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 1.6789,
      "step": 5
    },
    {
      "epoch": 0.0041330853482124405,
      "grad_norm": 0.8587822318077087,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.5597,
      "step": 10
    },
    {
      "epoch": 0.006199628022318661,
      "grad_norm": 1.4193518161773682,
      "learning_rate": 5e-05,
      "loss": 1.853,
      "step": 15
    },
    {
      "epoch": 0.008266170696424881,
      "grad_norm": 1.894394040107727,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.6418,
      "step": 20
    },
    {
      "epoch": 0.010332713370531101,
      "grad_norm": 1.5550564527511597,
      "learning_rate": 8.333333333333334e-05,
      "loss": 1.3564,
      "step": 25
    },
    {
      "epoch": 0.012399256044637322,
      "grad_norm": 2.1608707904815674,
      "learning_rate": 0.0001,
      "loss": 1.7369,
      "step": 30
    },
    {
      "epoch": 0.014465798718743542,
      "grad_norm": 1.5144590139389038,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.0681,
      "step": 35
    },
    {
      "epoch": 0.016532341392849762,
      "grad_norm": 1.3637126684188843,
      "learning_rate": 9.981987442712633e-05,
      "loss": 0.9692,
      "step": 40
    },
    {
      "epoch": 0.018598884066955982,
      "grad_norm": 1.5348516702651978,
      "learning_rate": 9.959502176294383e-05,
      "loss": 1.2228,
      "step": 45
    },
    {
      "epoch": 0.020665426741062202,
      "grad_norm": 2.122760534286499,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.9679,
      "step": 50
    },
    {
      "epoch": 0.02273196941516842,
      "grad_norm": 1.2727136611938477,
      "learning_rate": 9.887776194738432e-05,
      "loss": 1.1951,
      "step": 55
    },
    {
      "epoch": 0.024798512089274645,
      "grad_norm": 0.9782228469848633,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.9479,
      "step": 60
    },
    {
      "epoch": 0.026865054763380865,
      "grad_norm": 1.4281666278839111,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.817,
      "step": 65
    },
    {
      "epoch": 0.028931597437487085,
      "grad_norm": 1.0529621839523315,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.83,
      "step": 70
    },
    {
      "epoch": 0.030998140111593304,
      "grad_norm": 1.318174958229065,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.9337,
      "step": 75
    },
    {
      "epoch": 0.033064682785699524,
      "grad_norm": 1.516811728477478,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.8914,
      "step": 80
    },
    {
      "epoch": 0.035131225459805744,
      "grad_norm": 1.2559555768966675,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.8251,
      "step": 85
    },
    {
      "epoch": 0.037197768133911964,
      "grad_norm": 1.7071189880371094,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.9287,
      "step": 90
    },
    {
      "epoch": 0.039264310808018184,
      "grad_norm": 1.842026710510254,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.8464,
      "step": 95
    },
    {
      "epoch": 0.041330853482124404,
      "grad_norm": 2.377781867980957,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.7113,
      "step": 100
    },
    {
      "epoch": 0.041330853482124404,
      "eval_loss": 0.8705713748931885,
      "eval_runtime": 132.3524,
      "eval_samples_per_second": 7.699,
      "eval_steps_per_second": 3.853,
      "step": 100
    },
    {
      "epoch": 0.04339739615623062,
      "grad_norm": 1.1244537830352783,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.0297,
      "step": 105
    },
    {
      "epoch": 0.04546393883033684,
      "grad_norm": 0.866783857345581,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.6887,
      "step": 110
    },
    {
      "epoch": 0.04753048150444307,
      "grad_norm": 1.2207870483398438,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.9184,
      "step": 115
    },
    {
      "epoch": 0.04959702417854929,
      "grad_norm": 1.4106080532073975,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.0763,
      "step": 120
    },
    {
      "epoch": 0.05166356685265551,
      "grad_norm": 1.3751602172851562,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.822,
      "step": 125
    },
    {
      "epoch": 0.05373010952676173,
      "grad_norm": 1.327123999595642,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.817,
      "step": 130
    },
    {
      "epoch": 0.05579665220086795,
      "grad_norm": 1.3972790241241455,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.0442,
      "step": 135
    },
    {
      "epoch": 0.05786319487497417,
      "grad_norm": 1.3133134841918945,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.7807,
      "step": 140
    },
    {
      "epoch": 0.05992973754908039,
      "grad_norm": 1.2477699518203735,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.8035,
      "step": 145
    },
    {
      "epoch": 0.06199628022318661,
      "grad_norm": 2.311676025390625,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.7261,
      "step": 150
    },
    {
      "epoch": 0.06406282289729283,
      "grad_norm": 1.013773798942566,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.8035,
      "step": 155
    },
    {
      "epoch": 0.06612936557139905,
      "grad_norm": 1.2594728469848633,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.2357,
      "step": 160
    },
    {
      "epoch": 0.06819590824550527,
      "grad_norm": 1.3990025520324707,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.9476,
      "step": 165
    },
    {
      "epoch": 0.07026245091961149,
      "grad_norm": 1.3124955892562866,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.0208,
      "step": 170
    },
    {
      "epoch": 0.07232899359371771,
      "grad_norm": 1.2700549364089966,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.8046,
      "step": 175
    },
    {
      "epoch": 0.07439553626782393,
      "grad_norm": 0.9456565380096436,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.9784,
      "step": 180
    },
    {
      "epoch": 0.07646207894193015,
      "grad_norm": 1.3909025192260742,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.8895,
      "step": 185
    },
    {
      "epoch": 0.07852862161603637,
      "grad_norm": 1.400960087776184,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.6296,
      "step": 190
    },
    {
      "epoch": 0.08059516429014259,
      "grad_norm": 1.4584358930587769,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.8387,
      "step": 195
    },
    {
      "epoch": 0.08266170696424881,
      "grad_norm": 1.6872780323028564,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.6882,
      "step": 200
    },
    {
      "epoch": 0.08266170696424881,
      "eval_loss": 0.8160419464111328,
      "eval_runtime": 132.2449,
      "eval_samples_per_second": 7.705,
      "eval_steps_per_second": 3.856,
      "step": 200
    },
    {
      "epoch": 0.08472824963835503,
      "grad_norm": 0.7275150418281555,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.1285,
      "step": 205
    },
    {
      "epoch": 0.08679479231246125,
      "grad_norm": 1.6055395603179932,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.0795,
      "step": 210
    },
    {
      "epoch": 0.08886133498656747,
      "grad_norm": 1.6460407972335815,
      "learning_rate": 5e-05,
      "loss": 0.7667,
      "step": 215
    },
    {
      "epoch": 0.09092787766067369,
      "grad_norm": 1.2784044742584229,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.0481,
      "step": 220
    },
    {
      "epoch": 0.0929944203347799,
      "grad_norm": 1.3674898147583008,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.7733,
      "step": 225
    },
    {
      "epoch": 0.09506096300888614,
      "grad_norm": 1.7782163619995117,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.075,
      "step": 230
    },
    {
      "epoch": 0.09712750568299236,
      "grad_norm": 1.6913050413131714,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.8413,
      "step": 235
    },
    {
      "epoch": 0.09919404835709858,
      "grad_norm": 1.4041593074798584,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.7328,
      "step": 240
    },
    {
      "epoch": 0.1012605910312048,
      "grad_norm": 1.8579920530319214,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.6929,
      "step": 245
    },
    {
      "epoch": 0.10332713370531102,
      "grad_norm": 1.874348759651184,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.628,
      "step": 250
    },
    {
      "epoch": 0.10539367637941724,
      "grad_norm": 1.1385961771011353,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.0175,
      "step": 255
    },
    {
      "epoch": 0.10746021905352346,
      "grad_norm": 1.177496075630188,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.8475,
      "step": 260
    },
    {
      "epoch": 0.10952676172762968,
      "grad_norm": 0.819813072681427,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.7876,
      "step": 265
    },
    {
      "epoch": 0.1115933044017359,
      "grad_norm": 1.1457738876342773,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.7686,
      "step": 270
    },
    {
      "epoch": 0.11365984707584212,
      "grad_norm": 1.3542187213897705,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.9639,
      "step": 275
    },
    {
      "epoch": 0.11572638974994834,
      "grad_norm": 1.3880482912063599,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.6768,
      "step": 280
    },
    {
      "epoch": 0.11779293242405456,
      "grad_norm": 1.575758934020996,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.8948,
      "step": 285
    },
    {
      "epoch": 0.11985947509816078,
      "grad_norm": 1.2389308214187622,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.7186,
      "step": 290
    },
    {
      "epoch": 0.121926017772267,
      "grad_norm": 1.2766398191452026,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.693,
      "step": 295
    },
    {
      "epoch": 0.12399256044637322,
      "grad_norm": 1.8179432153701782,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.6462,
      "step": 300
    },
    {
      "epoch": 0.12399256044637322,
      "eval_loss": 0.7967092990875244,
      "eval_runtime": 132.1257,
      "eval_samples_per_second": 7.712,
      "eval_steps_per_second": 3.86,
      "step": 300
    },
    {
      "epoch": 0.12605910312047944,
      "grad_norm": 0.7972692847251892,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.9078,
      "step": 305
    },
    {
      "epoch": 0.12812564579458566,
      "grad_norm": 1.3046032190322876,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.0395,
      "step": 310
    },
    {
      "epoch": 0.13019218846869188,
      "grad_norm": 1.3980432748794556,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.1,
      "step": 315
    },
    {
      "epoch": 0.1322587311427981,
      "grad_norm": 1.0495986938476562,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.7195,
      "step": 320
    },
    {
      "epoch": 0.13432527381690432,
      "grad_norm": 1.4138555526733398,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.7553,
      "step": 325
    },
    {
      "epoch": 0.13639181649101054,
      "grad_norm": 1.1162981986999512,
      "learning_rate": 8.574517537807897e-06,
      "loss": 0.7799,
      "step": 330
    },
    {
      "epoch": 0.13845835916511676,
      "grad_norm": 1.5671554803848267,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.6911,
      "step": 335
    },
    {
      "epoch": 0.14052490183922298,
      "grad_norm": 2.3479394912719727,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.8078,
      "step": 340
    },
    {
      "epoch": 0.1425914445133292,
      "grad_norm": 1.5182538032531738,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.648,
      "step": 345
    },
    {
      "epoch": 0.14465798718743542,
      "grad_norm": 2.3883490562438965,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.9168,
      "step": 350
    },
    {
      "epoch": 0.14672452986154164,
      "grad_norm": 1.0066900253295898,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.9429,
      "step": 355
    },
    {
      "epoch": 0.14879107253564786,
      "grad_norm": 1.1294912099838257,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.9248,
      "step": 360
    },
    {
      "epoch": 0.15085761520975408,
      "grad_norm": 0.8687814474105835,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.5667,
      "step": 365
    },
    {
      "epoch": 0.1529241578838603,
      "grad_norm": 1.3007910251617432,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.7796,
      "step": 370
    },
    {
      "epoch": 0.15499070055796652,
      "grad_norm": 1.1952354907989502,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.8654,
      "step": 375
    },
    {
      "epoch": 0.15705724323207274,
      "grad_norm": 1.6118597984313965,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.6932,
      "step": 380
    },
    {
      "epoch": 0.15912378590617896,
      "grad_norm": 1.714866042137146,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.7152,
      "step": 385
    },
    {
      "epoch": 0.16119032858028517,
      "grad_norm": 1.3845038414001465,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.8241,
      "step": 390
    },
    {
      "epoch": 0.1632568712543914,
      "grad_norm": 1.519347071647644,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.8239,
      "step": 395
    },
    {
      "epoch": 0.16532341392849761,
      "grad_norm": 2.4190309047698975,
      "learning_rate": 0.0,
      "loss": 0.5018,
      "step": 400
    },
    {
      "epoch": 0.16532341392849761,
      "eval_loss": 0.7933396100997925,
      "eval_runtime": 132.3088,
      "eval_samples_per_second": 7.702,
      "eval_steps_per_second": 3.855,
      "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": 2.53296434479104e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}