{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004615766303752041,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.1539415759380102e-05,
      "eval_loss": 2.6116342544555664,
      "eval_runtime": 963.3024,
      "eval_samples_per_second": 37.879,
      "eval_steps_per_second": 18.94,
      "step": 1
    },
    {
      "epoch": 5.7697078796900516e-05,
      "grad_norm": 0.10074934363365173,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.2267,
      "step": 5
    },
    {
      "epoch": 0.00011539415759380103,
      "grad_norm": 0.13795822858810425,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.3436,
      "step": 10
    },
    {
      "epoch": 0.00017309123639070153,
      "grad_norm": 0.15493352711200714,
      "learning_rate": 5e-05,
      "loss": 2.4926,
      "step": 15
    },
    {
      "epoch": 0.00023078831518760207,
      "grad_norm": 0.19500400125980377,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.584,
      "step": 20
    },
    {
      "epoch": 0.0002884853939845026,
      "grad_norm": 0.2148405909538269,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.5117,
      "step": 25
    },
    {
      "epoch": 0.00034618247278140306,
      "grad_norm": 0.26830676198005676,
      "learning_rate": 0.0001,
      "loss": 2.5332,
      "step": 30
    },
    {
      "epoch": 0.0004038795515783036,
      "grad_norm": 0.28529003262519836,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.5869,
      "step": 35
    },
    {
      "epoch": 0.00046157663037520413,
      "grad_norm": 0.3338567614555359,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.5912,
      "step": 40
    },
    {
      "epoch": 0.0005192737091721046,
      "grad_norm": 0.3954179584980011,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.5669,
      "step": 45
    },
    {
      "epoch": 0.0005769707879690051,
      "grad_norm": 0.7015699148178101,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.7321,
      "step": 50
    },
    {
      "epoch": 0.0006346678667659057,
      "grad_norm": 0.2624838054180145,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.1123,
      "step": 55
    },
    {
      "epoch": 0.0006923649455628061,
      "grad_norm": 0.32643792033195496,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.1381,
      "step": 60
    },
    {
      "epoch": 0.0007500620243597067,
      "grad_norm": 0.32245364785194397,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.1583,
      "step": 65
    },
    {
      "epoch": 0.0008077591031566072,
      "grad_norm": 0.3583735227584839,
      "learning_rate": 9.714387227305422e-05,
      "loss": 2.1498,
      "step": 70
    },
    {
      "epoch": 0.0008654561819535077,
      "grad_norm": 0.42148590087890625,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.1263,
      "step": 75
    },
    {
      "epoch": 0.0009231532607504083,
      "grad_norm": 0.4721578359603882,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.1456,
      "step": 80
    },
    {
      "epoch": 0.0009808503395473088,
      "grad_norm": 0.45783913135528564,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.0714,
      "step": 85
    },
    {
      "epoch": 0.0010385474183442092,
      "grad_norm": 0.5551944971084595,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.0272,
      "step": 90
    },
    {
      "epoch": 0.0010962444971411097,
      "grad_norm": 0.5281091332435608,
      "learning_rate": 9.257645688666556e-05,
      "loss": 1.8899,
      "step": 95
    },
    {
      "epoch": 0.0011539415759380103,
      "grad_norm": 0.8300865888595581,
      "learning_rate": 9.142548246219212e-05,
      "loss": 1.8428,
      "step": 100
    },
    {
      "epoch": 0.0011539415759380103,
      "eval_loss": 1.8705904483795166,
      "eval_runtime": 962.77,
      "eval_samples_per_second": 37.9,
      "eval_steps_per_second": 18.951,
      "step": 100
    },
    {
      "epoch": 0.0012116386547349107,
      "grad_norm": 0.38176557421684265,
      "learning_rate": 9.019985651834703e-05,
      "loss": 1.9289,
      "step": 105
    },
    {
      "epoch": 0.0012693357335318114,
      "grad_norm": 0.40435314178466797,
      "learning_rate": 8.890178771592199e-05,
      "loss": 1.9484,
      "step": 110
    },
    {
      "epoch": 0.0013270328123287118,
      "grad_norm": 0.41454848647117615,
      "learning_rate": 8.753361526263621e-05,
      "loss": 1.8564,
      "step": 115
    },
    {
      "epoch": 0.0013847298911256122,
      "grad_norm": 0.3869158625602722,
      "learning_rate": 8.609780469772623e-05,
      "loss": 1.7796,
      "step": 120
    },
    {
      "epoch": 0.0014424269699225129,
      "grad_norm": 0.45108917355537415,
      "learning_rate": 8.459694344887732e-05,
      "loss": 1.807,
      "step": 125
    },
    {
      "epoch": 0.0015001240487194133,
      "grad_norm": 0.5212119817733765,
      "learning_rate": 8.303373616950408e-05,
      "loss": 1.7816,
      "step": 130
    },
    {
      "epoch": 0.001557821127516314,
      "grad_norm": 0.4871671795845032,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.7782,
      "step": 135
    },
    {
      "epoch": 0.0016155182063132144,
      "grad_norm": 0.590176522731781,
      "learning_rate": 7.973165881521434e-05,
      "loss": 1.6827,
      "step": 140
    },
    {
      "epoch": 0.0016732152851101148,
      "grad_norm": 0.5965710282325745,
      "learning_rate": 7.799873930687978e-05,
      "loss": 1.7181,
      "step": 145
    },
    {
      "epoch": 0.0017309123639070154,
      "grad_norm": 0.9051038026809692,
      "learning_rate": 7.621536417786159e-05,
      "loss": 1.7685,
      "step": 150
    },
    {
      "epoch": 0.0017886094427039159,
      "grad_norm": 0.38182660937309265,
      "learning_rate": 7.438474719068173e-05,
      "loss": 1.9226,
      "step": 155
    },
    {
      "epoch": 0.0018463065215008165,
      "grad_norm": 0.48448461294174194,
      "learning_rate": 7.251018724088367e-05,
      "loss": 1.9197,
      "step": 160
    },
    {
      "epoch": 0.001904003600297717,
      "grad_norm": 0.4199281334877014,
      "learning_rate": 7.059506241219965e-05,
      "loss": 1.8433,
      "step": 165
    },
    {
      "epoch": 0.0019617006790946176,
      "grad_norm": 0.4792007505893707,
      "learning_rate": 6.864282388901544e-05,
      "loss": 1.7767,
      "step": 170
    },
    {
      "epoch": 0.002019397757891518,
      "grad_norm": 0.5187090635299683,
      "learning_rate": 6.665698973710288e-05,
      "loss": 1.7417,
      "step": 175
    },
    {
      "epoch": 0.0020770948366884185,
      "grad_norm": 0.4906215965747833,
      "learning_rate": 6.464113856382752e-05,
      "loss": 1.7668,
      "step": 180
    },
    {
      "epoch": 0.002134791915485319,
      "grad_norm": 0.5257192254066467,
      "learning_rate": 6.259890306925627e-05,
      "loss": 1.6353,
      "step": 185
    },
    {
      "epoch": 0.0021924889942822193,
      "grad_norm": 0.5866225957870483,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 1.7546,
      "step": 190
    },
    {
      "epoch": 0.00225018607307912,
      "grad_norm": 0.6971685290336609,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 1.6497,
      "step": 195
    },
    {
      "epoch": 0.0023078831518760206,
      "grad_norm": 1.1953887939453125,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 1.6536,
      "step": 200
    },
    {
      "epoch": 0.0023078831518760206,
      "eval_loss": 1.7406009435653687,
      "eval_runtime": 960.4655,
      "eval_samples_per_second": 37.991,
      "eval_steps_per_second": 18.996,
      "step": 200
    },
    {
      "epoch": 0.0023655802306729212,
      "grad_norm": 0.4501577317714691,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 1.8511,
      "step": 205
    },
    {
      "epoch": 0.0024232773094698215,
      "grad_norm": 0.4853840470314026,
      "learning_rate": 5.212206015980742e-05,
      "loss": 1.86,
      "step": 210
    },
    {
      "epoch": 0.002480974388266722,
      "grad_norm": 0.5209008455276489,
      "learning_rate": 5e-05,
      "loss": 1.7783,
      "step": 215
    },
    {
      "epoch": 0.0025386714670636227,
      "grad_norm": 0.5276066064834595,
      "learning_rate": 4.78779398401926e-05,
      "loss": 1.7463,
      "step": 220
    },
    {
      "epoch": 0.002596368545860523,
      "grad_norm": 0.5926941633224487,
      "learning_rate": 4.575970377622456e-05,
      "loss": 1.6383,
      "step": 225
    },
    {
      "epoch": 0.0026540656246574236,
      "grad_norm": 0.6365469694137573,
      "learning_rate": 4.364910901265606e-05,
      "loss": 1.7336,
      "step": 230
    },
    {
      "epoch": 0.0027117627034543242,
      "grad_norm": 0.6373388171195984,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 1.6353,
      "step": 235
    },
    {
      "epoch": 0.0027694597822512245,
      "grad_norm": 0.6907333731651306,
      "learning_rate": 3.94660365002137e-05,
      "loss": 1.5492,
      "step": 240
    },
    {
      "epoch": 0.002827156861048125,
      "grad_norm": 0.7751602530479431,
      "learning_rate": 3.740109693074375e-05,
      "loss": 1.661,
      "step": 245
    },
    {
      "epoch": 0.0028848539398450257,
      "grad_norm": 0.8952168822288513,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 1.6128,
      "step": 250
    },
    {
      "epoch": 0.002942551018641926,
      "grad_norm": 0.46908143162727356,
      "learning_rate": 3.334301026289712e-05,
      "loss": 1.8182,
      "step": 255
    },
    {
      "epoch": 0.0030002480974388266,
      "grad_norm": 0.4967330992221832,
      "learning_rate": 3.135717611098458e-05,
      "loss": 1.849,
      "step": 260
    },
    {
      "epoch": 0.0030579451762357272,
      "grad_norm": 0.529554545879364,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 1.817,
      "step": 265
    },
    {
      "epoch": 0.003115642255032628,
      "grad_norm": 0.5606085658073425,
      "learning_rate": 2.748981275911633e-05,
      "loss": 1.7628,
      "step": 270
    },
    {
      "epoch": 0.003173339333829528,
      "grad_norm": 0.5795584917068481,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 1.6654,
      "step": 275
    },
    {
      "epoch": 0.0032310364126264287,
      "grad_norm": 0.6071023344993591,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 1.6112,
      "step": 280
    },
    {
      "epoch": 0.0032887334914233294,
      "grad_norm": 0.6555030345916748,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 1.625,
      "step": 285
    },
    {
      "epoch": 0.0033464305702202296,
      "grad_norm": 0.7921385169029236,
      "learning_rate": 2.026834118478567e-05,
      "loss": 1.7255,
      "step": 290
    },
    {
      "epoch": 0.0034041276490171303,
      "grad_norm": 0.7531300783157349,
      "learning_rate": 1.858900013521788e-05,
      "loss": 1.598,
      "step": 295
    },
    {
      "epoch": 0.003461824727814031,
      "grad_norm": 1.1491597890853882,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 1.5894,
      "step": 300
    },
    {
      "epoch": 0.003461824727814031,
      "eval_loss": 1.696458339691162,
      "eval_runtime": 957.4278,
      "eval_samples_per_second": 38.111,
      "eval_steps_per_second": 19.056,
      "step": 300
    },
    {
      "epoch": 0.003519521806610931,
      "grad_norm": 0.4294973611831665,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 1.8232,
      "step": 305
    },
    {
      "epoch": 0.0035772188854078318,
      "grad_norm": 0.48770248889923096,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 1.7483,
      "step": 310
    },
    {
      "epoch": 0.0036349159642047324,
      "grad_norm": 0.5328405499458313,
      "learning_rate": 1.246638473736378e-05,
      "loss": 1.7723,
      "step": 315
    },
    {
      "epoch": 0.003692613043001633,
      "grad_norm": 0.584344208240509,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 1.6877,
      "step": 320
    },
    {
      "epoch": 0.0037503101217985333,
      "grad_norm": 0.6256000995635986,
      "learning_rate": 9.800143481652979e-06,
      "loss": 1.7171,
      "step": 325
    },
    {
      "epoch": 0.003808007200595434,
      "grad_norm": 0.6042689681053162,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.6601,
      "step": 330
    },
    {
      "epoch": 0.0038657042793923345,
      "grad_norm": 0.7034847736358643,
      "learning_rate": 7.423543113334436e-06,
      "loss": 1.6067,
      "step": 335
    },
    {
      "epoch": 0.003923401358189235,
      "grad_norm": 0.7719807624816895,
      "learning_rate": 6.349294341940593e-06,
      "loss": 1.5586,
      "step": 340
    },
    {
      "epoch": 0.003981098436986135,
      "grad_norm": 0.9979642033576965,
      "learning_rate": 5.353707092521582e-06,
      "loss": 1.6876,
      "step": 345
    },
    {
      "epoch": 0.004038795515783036,
      "grad_norm": 1.4790928363800049,
      "learning_rate": 4.43857548059321e-06,
      "loss": 1.5962,
      "step": 350
    },
    {
      "epoch": 0.004096492594579937,
      "grad_norm": 0.45558443665504456,
      "learning_rate": 3.605548635174533e-06,
      "loss": 1.8923,
      "step": 355
    },
    {
      "epoch": 0.004154189673376837,
      "grad_norm": 0.5109541416168213,
      "learning_rate": 2.85612772694579e-06,
      "loss": 1.8088,
      "step": 360
    },
    {
      "epoch": 0.004211886752173737,
      "grad_norm": 0.4755468964576721,
      "learning_rate": 2.191663263037458e-06,
      "loss": 1.7673,
      "step": 365
    },
    {
      "epoch": 0.004269583830970638,
      "grad_norm": 0.6231192946434021,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 1.8191,
      "step": 370
    },
    {
      "epoch": 0.004327280909767538,
      "grad_norm": 0.691005289554596,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 1.6029,
      "step": 375
    },
    {
      "epoch": 0.004384977988564439,
      "grad_norm": 0.6638383269309998,
      "learning_rate": 7.192044826145771e-07,
      "loss": 1.6519,
      "step": 380
    },
    {
      "epoch": 0.00444267506736134,
      "grad_norm": 0.6720619201660156,
      "learning_rate": 4.049782370561583e-07,
      "loss": 1.6002,
      "step": 385
    },
    {
      "epoch": 0.00450037214615824,
      "grad_norm": 0.6364055871963501,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 1.5384,
      "step": 390
    },
    {
      "epoch": 0.00455806922495514,
      "grad_norm": 0.8002621531486511,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 1.6922,
      "step": 395
    },
    {
      "epoch": 0.004615766303752041,
      "grad_norm": 1.0289967060089111,
      "learning_rate": 0.0,
      "loss": 1.516,
      "step": 400
    },
    {
      "epoch": 0.004615766303752041,
      "eval_loss": 1.690679907798767,
      "eval_runtime": 958.463,
      "eval_samples_per_second": 38.07,
      "eval_steps_per_second": 19.036,
      "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": 6271342215168000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}