{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.007700934219582513,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.9252335548956284e-05,
      "eval_loss": 1.108144998550415,
      "eval_runtime": 1919.3279,
      "eval_samples_per_second": 11.395,
      "eval_steps_per_second": 5.698,
      "step": 1
    },
    {
      "epoch": 9.626167774478142e-05,
      "grad_norm": 0.6659215092658997,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.77,
      "step": 5
    },
    {
      "epoch": 0.00019252335548956284,
      "grad_norm": 0.6601605415344238,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.8377,
      "step": 10
    },
    {
      "epoch": 0.00028878503323434427,
      "grad_norm": 0.822390615940094,
      "learning_rate": 5e-05,
      "loss": 0.8958,
      "step": 15
    },
    {
      "epoch": 0.00038504671097912567,
      "grad_norm": 0.4850705862045288,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.8254,
      "step": 20
    },
    {
      "epoch": 0.0004813083887239071,
      "grad_norm": 0.6110145449638367,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.7778,
      "step": 25
    },
    {
      "epoch": 0.0005775700664686885,
      "grad_norm": 0.8611935973167419,
      "learning_rate": 0.0001,
      "loss": 0.9301,
      "step": 30
    },
    {
      "epoch": 0.0006738317442134699,
      "grad_norm": 0.7456876039505005,
      "learning_rate": 9.995494831023409e-05,
      "loss": 1.071,
      "step": 35
    },
    {
      "epoch": 0.0007700934219582513,
      "grad_norm": 0.9872922301292419,
      "learning_rate": 9.981987442712633e-05,
      "loss": 1.0768,
      "step": 40
    },
    {
      "epoch": 0.0008663550997030327,
      "grad_norm": 1.2160166501998901,
      "learning_rate": 9.959502176294383e-05,
      "loss": 0.9599,
      "step": 45
    },
    {
      "epoch": 0.0009626167774478141,
      "grad_norm": 3.24212384223938,
      "learning_rate": 9.928079551738543e-05,
      "loss": 0.9748,
      "step": 50
    },
    {
      "epoch": 0.0010588784551925955,
      "grad_norm": 0.7632853388786316,
      "learning_rate": 9.887776194738432e-05,
      "loss": 0.6587,
      "step": 55
    },
    {
      "epoch": 0.001155140132937377,
      "grad_norm": 0.48142459988594055,
      "learning_rate": 9.838664734667495e-05,
      "loss": 0.7027,
      "step": 60
    },
    {
      "epoch": 0.0012514018106821584,
      "grad_norm": 0.5475998520851135,
      "learning_rate": 9.780833673696254e-05,
      "loss": 0.6637,
      "step": 65
    },
    {
      "epoch": 0.0013476634884269398,
      "grad_norm": 0.46152353286743164,
      "learning_rate": 9.714387227305422e-05,
      "loss": 0.6983,
      "step": 70
    },
    {
      "epoch": 0.0014439251661717211,
      "grad_norm": 0.45441746711730957,
      "learning_rate": 9.639445136482548e-05,
      "loss": 0.7383,
      "step": 75
    },
    {
      "epoch": 0.0015401868439165027,
      "grad_norm": 0.5577864646911621,
      "learning_rate": 9.55614245194068e-05,
      "loss": 0.8565,
      "step": 80
    },
    {
      "epoch": 0.001636448521661284,
      "grad_norm": 0.6075682044029236,
      "learning_rate": 9.464629290747842e-05,
      "loss": 0.9564,
      "step": 85
    },
    {
      "epoch": 0.0017327101994060654,
      "grad_norm": 0.8520958423614502,
      "learning_rate": 9.365070565805941e-05,
      "loss": 0.9223,
      "step": 90
    },
    {
      "epoch": 0.001828971877150847,
      "grad_norm": 1.0015594959259033,
      "learning_rate": 9.257645688666556e-05,
      "loss": 0.8602,
      "step": 95
    },
    {
      "epoch": 0.0019252335548956283,
      "grad_norm": 1.5310227870941162,
      "learning_rate": 9.142548246219212e-05,
      "loss": 0.7323,
      "step": 100
    },
    {
      "epoch": 0.0019252335548956283,
      "eval_loss": 0.7984132170677185,
      "eval_runtime": 1928.5905,
      "eval_samples_per_second": 11.34,
      "eval_steps_per_second": 5.67,
      "step": 100
    },
    {
      "epoch": 0.00202149523264041,
      "grad_norm": 0.44278082251548767,
      "learning_rate": 9.019985651834703e-05,
      "loss": 0.6448,
      "step": 105
    },
    {
      "epoch": 0.002117756910385191,
      "grad_norm": 0.40506282448768616,
      "learning_rate": 8.890178771592199e-05,
      "loss": 0.7086,
      "step": 110
    },
    {
      "epoch": 0.0022140185881299726,
      "grad_norm": 0.42748236656188965,
      "learning_rate": 8.753361526263621e-05,
      "loss": 0.6731,
      "step": 115
    },
    {
      "epoch": 0.002310280265874754,
      "grad_norm": 0.45535221695899963,
      "learning_rate": 8.609780469772623e-05,
      "loss": 0.7811,
      "step": 120
    },
    {
      "epoch": 0.0024065419436195353,
      "grad_norm": 0.43903645873069763,
      "learning_rate": 8.459694344887732e-05,
      "loss": 0.7796,
      "step": 125
    },
    {
      "epoch": 0.002502803621364317,
      "grad_norm": 0.5445039868354797,
      "learning_rate": 8.303373616950408e-05,
      "loss": 0.8867,
      "step": 130
    },
    {
      "epoch": 0.002599065299109098,
      "grad_norm": 0.7192273139953613,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.0437,
      "step": 135
    },
    {
      "epoch": 0.0026953269768538795,
      "grad_norm": 0.6920287013053894,
      "learning_rate": 7.973165881521434e-05,
      "loss": 0.8471,
      "step": 140
    },
    {
      "epoch": 0.002791588654598661,
      "grad_norm": 1.0348949432373047,
      "learning_rate": 7.799873930687978e-05,
      "loss": 0.9321,
      "step": 145
    },
    {
      "epoch": 0.0028878503323434422,
      "grad_norm": 1.2998476028442383,
      "learning_rate": 7.621536417786159e-05,
      "loss": 0.8626,
      "step": 150
    },
    {
      "epoch": 0.002984112010088224,
      "grad_norm": 0.3901401162147522,
      "learning_rate": 7.438474719068173e-05,
      "loss": 0.6218,
      "step": 155
    },
    {
      "epoch": 0.0030803736878330054,
      "grad_norm": 0.4046913981437683,
      "learning_rate": 7.251018724088367e-05,
      "loss": 0.6306,
      "step": 160
    },
    {
      "epoch": 0.0031766353655777865,
      "grad_norm": 0.42889705300331116,
      "learning_rate": 7.059506241219965e-05,
      "loss": 0.6758,
      "step": 165
    },
    {
      "epoch": 0.003272897043322568,
      "grad_norm": 0.48536989092826843,
      "learning_rate": 6.864282388901544e-05,
      "loss": 0.7582,
      "step": 170
    },
    {
      "epoch": 0.0033691587210673496,
      "grad_norm": 0.4803304076194763,
      "learning_rate": 6.665698973710288e-05,
      "loss": 0.7234,
      "step": 175
    },
    {
      "epoch": 0.0034654203988121308,
      "grad_norm": 0.46377551555633545,
      "learning_rate": 6.464113856382752e-05,
      "loss": 0.8018,
      "step": 180
    },
    {
      "epoch": 0.0035616820765569123,
      "grad_norm": 0.6397562026977539,
      "learning_rate": 6.259890306925627e-05,
      "loss": 0.893,
      "step": 185
    },
    {
      "epoch": 0.003657943754301694,
      "grad_norm": 0.7519800066947937,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 0.9103,
      "step": 190
    },
    {
      "epoch": 0.003754205432046475,
      "grad_norm": 0.9030217528343201,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 0.8878,
      "step": 195
    },
    {
      "epoch": 0.0038504671097912566,
      "grad_norm": 1.6634423732757568,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 0.8051,
      "step": 200
    },
    {
      "epoch": 0.0038504671097912566,
      "eval_loss": 0.7720447182655334,
      "eval_runtime": 1932.2039,
      "eval_samples_per_second": 11.319,
      "eval_steps_per_second": 5.66,
      "step": 200
    },
    {
      "epoch": 0.003946728787536038,
      "grad_norm": 0.42693620920181274,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 0.6239,
      "step": 205
    },
    {
      "epoch": 0.00404299046528082,
      "grad_norm": 0.3707335889339447,
      "learning_rate": 5.212206015980742e-05,
      "loss": 0.5839,
      "step": 210
    },
    {
      "epoch": 0.0041392521430256,
      "grad_norm": 0.44132792949676514,
      "learning_rate": 5e-05,
      "loss": 0.6042,
      "step": 215
    },
    {
      "epoch": 0.004235513820770382,
      "grad_norm": 0.530677855014801,
      "learning_rate": 4.78779398401926e-05,
      "loss": 0.7432,
      "step": 220
    },
    {
      "epoch": 0.0043317754985151636,
      "grad_norm": 0.45090410113334656,
      "learning_rate": 4.575970377622456e-05,
      "loss": 0.7411,
      "step": 225
    },
    {
      "epoch": 0.004428037176259945,
      "grad_norm": 0.5574643015861511,
      "learning_rate": 4.364910901265606e-05,
      "loss": 0.8073,
      "step": 230
    },
    {
      "epoch": 0.004524298854004727,
      "grad_norm": 0.6338116526603699,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 0.8879,
      "step": 235
    },
    {
      "epoch": 0.004620560531749508,
      "grad_norm": 0.7863397598266602,
      "learning_rate": 3.94660365002137e-05,
      "loss": 0.9401,
      "step": 240
    },
    {
      "epoch": 0.004716822209494289,
      "grad_norm": 0.9480910897254944,
      "learning_rate": 3.740109693074375e-05,
      "loss": 0.8849,
      "step": 245
    },
    {
      "epoch": 0.0048130838872390705,
      "grad_norm": 1.8533746004104614,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 0.7833,
      "step": 250
    },
    {
      "epoch": 0.004909345564983852,
      "grad_norm": 0.5215345025062561,
      "learning_rate": 3.334301026289712e-05,
      "loss": 0.6496,
      "step": 255
    },
    {
      "epoch": 0.005005607242728634,
      "grad_norm": 0.37707287073135376,
      "learning_rate": 3.135717611098458e-05,
      "loss": 0.5934,
      "step": 260
    },
    {
      "epoch": 0.005101868920473415,
      "grad_norm": 0.3559814989566803,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 0.6554,
      "step": 265
    },
    {
      "epoch": 0.005198130598218196,
      "grad_norm": 0.49917322397232056,
      "learning_rate": 2.748981275911633e-05,
      "loss": 0.6842,
      "step": 270
    },
    {
      "epoch": 0.0052943922759629775,
      "grad_norm": 0.4471706449985504,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 0.7675,
      "step": 275
    },
    {
      "epoch": 0.005390653953707759,
      "grad_norm": 0.6053714752197266,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 0.9775,
      "step": 280
    },
    {
      "epoch": 0.005486915631452541,
      "grad_norm": 0.661923348903656,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 0.9233,
      "step": 285
    },
    {
      "epoch": 0.005583177309197322,
      "grad_norm": 0.7124205231666565,
      "learning_rate": 2.026834118478567e-05,
      "loss": 0.8823,
      "step": 290
    },
    {
      "epoch": 0.005679438986942104,
      "grad_norm": 0.8524189591407776,
      "learning_rate": 1.858900013521788e-05,
      "loss": 0.8674,
      "step": 295
    },
    {
      "epoch": 0.0057757006646868845,
      "grad_norm": 1.4636945724487305,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 0.8147,
      "step": 300
    },
    {
      "epoch": 0.0057757006646868845,
      "eval_loss": 0.7641729712486267,
      "eval_runtime": 1931.0634,
      "eval_samples_per_second": 11.326,
      "eval_steps_per_second": 5.663,
      "step": 300
    },
    {
      "epoch": 0.005871962342431666,
      "grad_norm": 0.4203615188598633,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 0.6767,
      "step": 305
    },
    {
      "epoch": 0.005968224020176448,
      "grad_norm": 0.4005977511405945,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 0.624,
      "step": 310
    },
    {
      "epoch": 0.006064485697921229,
      "grad_norm": 0.43250247836112976,
      "learning_rate": 1.246638473736378e-05,
      "loss": 0.6811,
      "step": 315
    },
    {
      "epoch": 0.006160747375666011,
      "grad_norm": 0.4517424702644348,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 0.7448,
      "step": 320
    },
    {
      "epoch": 0.006257009053410792,
      "grad_norm": 0.48707225918769836,
      "learning_rate": 9.800143481652979e-06,
      "loss": 0.7806,
      "step": 325
    },
    {
      "epoch": 0.006353270731155573,
      "grad_norm": 0.6228247880935669,
      "learning_rate": 8.574517537807897e-06,
      "loss": 1.0334,
      "step": 330
    },
    {
      "epoch": 0.0064495324089003546,
      "grad_norm": 0.6839772462844849,
      "learning_rate": 7.423543113334436e-06,
      "loss": 0.9423,
      "step": 335
    },
    {
      "epoch": 0.006545794086645136,
      "grad_norm": 0.8296107649803162,
      "learning_rate": 6.349294341940593e-06,
      "loss": 0.8357,
      "step": 340
    },
    {
      "epoch": 0.006642055764389918,
      "grad_norm": 0.8969528675079346,
      "learning_rate": 5.353707092521582e-06,
      "loss": 0.9268,
      "step": 345
    },
    {
      "epoch": 0.006738317442134699,
      "grad_norm": 1.4726608991622925,
      "learning_rate": 4.43857548059321e-06,
      "loss": 0.7864,
      "step": 350
    },
    {
      "epoch": 0.00683457911987948,
      "grad_norm": 0.39658182859420776,
      "learning_rate": 3.605548635174533e-06,
      "loss": 0.5849,
      "step": 355
    },
    {
      "epoch": 0.0069308407976242615,
      "grad_norm": 0.39953601360321045,
      "learning_rate": 2.85612772694579e-06,
      "loss": 0.6068,
      "step": 360
    },
    {
      "epoch": 0.007027102475369043,
      "grad_norm": 0.3993167579174042,
      "learning_rate": 2.191663263037458e-06,
      "loss": 0.6077,
      "step": 365
    },
    {
      "epoch": 0.007123364153113825,
      "grad_norm": 0.45908135175704956,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 0.6605,
      "step": 370
    },
    {
      "epoch": 0.007219625830858606,
      "grad_norm": 0.493380606174469,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 0.7103,
      "step": 375
    },
    {
      "epoch": 0.007315887508603388,
      "grad_norm": 0.5427780151367188,
      "learning_rate": 7.192044826145771e-07,
      "loss": 0.8139,
      "step": 380
    },
    {
      "epoch": 0.0074121491863481685,
      "grad_norm": 0.6110123991966248,
      "learning_rate": 4.049782370561583e-07,
      "loss": 0.9834,
      "step": 385
    },
    {
      "epoch": 0.00750841086409295,
      "grad_norm": 0.6845661997795105,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 0.8251,
      "step": 390
    },
    {
      "epoch": 0.007604672541837732,
      "grad_norm": 0.8650242686271667,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 0.8855,
      "step": 395
    },
    {
      "epoch": 0.007700934219582513,
      "grad_norm": 1.3182352781295776,
      "learning_rate": 0.0,
      "loss": 0.7168,
      "step": 400
    },
    {
      "epoch": 0.007700934219582513,
      "eval_loss": 0.7636958956718445,
      "eval_runtime": 1930.0198,
      "eval_samples_per_second": 11.332,
      "eval_steps_per_second": 5.666,
      "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": 1.598948292522148e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}