{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00970667637334304,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.42666909333576e-05,
      "eval_loss": 2.878453493118286,
      "eval_runtime": 1372.4063,
      "eval_samples_per_second": 12.643,
      "eval_steps_per_second": 6.322,
      "step": 1
    },
    {
      "epoch": 0.000121333454666788,
      "grad_norm": 11.818228721618652,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 9.5301,
      "step": 5
    },
    {
      "epoch": 0.000242666909333576,
      "grad_norm": 10.987421035766602,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 9.7386,
      "step": 10
    },
    {
      "epoch": 0.000364000364000364,
      "grad_norm": 12.346467971801758,
      "learning_rate": 5e-05,
      "loss": 9.5456,
      "step": 15
    },
    {
      "epoch": 0.000485333818667152,
      "grad_norm": 11.592193603515625,
      "learning_rate": 6.666666666666667e-05,
      "loss": 8.9309,
      "step": 20
    },
    {
      "epoch": 0.00060666727333394,
      "grad_norm": 14.079370498657227,
      "learning_rate": 8.333333333333334e-05,
      "loss": 8.7923,
      "step": 25
    },
    {
      "epoch": 0.000728000728000728,
      "grad_norm": 13.561756134033203,
      "learning_rate": 0.0001,
      "loss": 8.3366,
      "step": 30
    },
    {
      "epoch": 0.000849334182667516,
      "grad_norm": 22.25603485107422,
      "learning_rate": 9.995494831023409e-05,
      "loss": 8.7607,
      "step": 35
    },
    {
      "epoch": 0.000970667637334304,
      "grad_norm": 18.023517608642578,
      "learning_rate": 9.981987442712633e-05,
      "loss": 9.2432,
      "step": 40
    },
    {
      "epoch": 0.001092001092001092,
      "grad_norm": 25.709226608276367,
      "learning_rate": 9.959502176294383e-05,
      "loss": 9.2506,
      "step": 45
    },
    {
      "epoch": 0.00121333454666788,
      "grad_norm": 33.24303436279297,
      "learning_rate": 9.928079551738543e-05,
      "loss": 10.1706,
      "step": 50
    },
    {
      "epoch": 0.001334668001334668,
      "grad_norm": 9.444133758544922,
      "learning_rate": 9.887776194738432e-05,
      "loss": 8.8397,
      "step": 55
    },
    {
      "epoch": 0.001456001456001456,
      "grad_norm": 8.350540161132812,
      "learning_rate": 9.838664734667495e-05,
      "loss": 8.4448,
      "step": 60
    },
    {
      "epoch": 0.001577334910668244,
      "grad_norm": 7.977123260498047,
      "learning_rate": 9.780833673696254e-05,
      "loss": 8.3745,
      "step": 65
    },
    {
      "epoch": 0.001698668365335032,
      "grad_norm": 8.620443344116211,
      "learning_rate": 9.714387227305422e-05,
      "loss": 8.2024,
      "step": 70
    },
    {
      "epoch": 0.00182000182000182,
      "grad_norm": 10.907526969909668,
      "learning_rate": 9.639445136482548e-05,
      "loss": 8.5011,
      "step": 75
    },
    {
      "epoch": 0.001941335274668608,
      "grad_norm": 13.035191535949707,
      "learning_rate": 9.55614245194068e-05,
      "loss": 8.7188,
      "step": 80
    },
    {
      "epoch": 0.002062668729335396,
      "grad_norm": 16.095685958862305,
      "learning_rate": 9.464629290747842e-05,
      "loss": 8.6738,
      "step": 85
    },
    {
      "epoch": 0.002184002184002184,
      "grad_norm": 24.661006927490234,
      "learning_rate": 9.365070565805941e-05,
      "loss": 8.3647,
      "step": 90
    },
    {
      "epoch": 0.002305335638668972,
      "grad_norm": 30.535736083984375,
      "learning_rate": 9.257645688666556e-05,
      "loss": 10.0638,
      "step": 95
    },
    {
      "epoch": 0.00242666909333576,
      "grad_norm": 46.029945373535156,
      "learning_rate": 9.142548246219212e-05,
      "loss": 9.7736,
      "step": 100
    },
    {
      "epoch": 0.00242666909333576,
      "eval_loss": 2.331610918045044,
      "eval_runtime": 1377.2905,
      "eval_samples_per_second": 12.598,
      "eval_steps_per_second": 6.299,
      "step": 100
    },
    {
      "epoch": 0.002548002548002548,
      "grad_norm": 12.967903137207031,
      "learning_rate": 9.019985651834703e-05,
      "loss": 8.8067,
      "step": 105
    },
    {
      "epoch": 0.002669336002669336,
      "grad_norm": 8.18023681640625,
      "learning_rate": 8.890178771592199e-05,
      "loss": 8.9571,
      "step": 110
    },
    {
      "epoch": 0.002790669457336124,
      "grad_norm": 8.041296005249023,
      "learning_rate": 8.753361526263621e-05,
      "loss": 8.3393,
      "step": 115
    },
    {
      "epoch": 0.002912002912002912,
      "grad_norm": 9.720775604248047,
      "learning_rate": 8.609780469772623e-05,
      "loss": 8.3803,
      "step": 120
    },
    {
      "epoch": 0.0030333363666697,
      "grad_norm": 11.025723457336426,
      "learning_rate": 8.459694344887732e-05,
      "loss": 8.1113,
      "step": 125
    },
    {
      "epoch": 0.003154669821336488,
      "grad_norm": 14.601977348327637,
      "learning_rate": 8.303373616950408e-05,
      "loss": 8.8132,
      "step": 130
    },
    {
      "epoch": 0.003276003276003276,
      "grad_norm": 14.005407333374023,
      "learning_rate": 8.141099986478212e-05,
      "loss": 8.5404,
      "step": 135
    },
    {
      "epoch": 0.003397336730670064,
      "grad_norm": 19.68910026550293,
      "learning_rate": 7.973165881521434e-05,
      "loss": 8.8285,
      "step": 140
    },
    {
      "epoch": 0.003518670185336852,
      "grad_norm": 26.25465965270996,
      "learning_rate": 7.799873930687978e-05,
      "loss": 9.6295,
      "step": 145
    },
    {
      "epoch": 0.00364000364000364,
      "grad_norm": 31.541311264038086,
      "learning_rate": 7.621536417786159e-05,
      "loss": 9.3287,
      "step": 150
    },
    {
      "epoch": 0.003761337094670428,
      "grad_norm": 8.852987289428711,
      "learning_rate": 7.438474719068173e-05,
      "loss": 8.5892,
      "step": 155
    },
    {
      "epoch": 0.003882670549337216,
      "grad_norm": 6.915546417236328,
      "learning_rate": 7.251018724088367e-05,
      "loss": 8.5808,
      "step": 160
    },
    {
      "epoch": 0.004004004004004004,
      "grad_norm": 8.234546661376953,
      "learning_rate": 7.059506241219965e-05,
      "loss": 8.3382,
      "step": 165
    },
    {
      "epoch": 0.004125337458670792,
      "grad_norm": 9.939790725708008,
      "learning_rate": 6.864282388901544e-05,
      "loss": 8.1358,
      "step": 170
    },
    {
      "epoch": 0.00424667091333758,
      "grad_norm": 9.333702087402344,
      "learning_rate": 6.665698973710288e-05,
      "loss": 8.4612,
      "step": 175
    },
    {
      "epoch": 0.004368004368004368,
      "grad_norm": 11.787590980529785,
      "learning_rate": 6.464113856382752e-05,
      "loss": 7.9593,
      "step": 180
    },
    {
      "epoch": 0.004489337822671156,
      "grad_norm": 12.82723331451416,
      "learning_rate": 6.259890306925627e-05,
      "loss": 8.0649,
      "step": 185
    },
    {
      "epoch": 0.004610671277337944,
      "grad_norm": 15.473737716674805,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 8.3759,
      "step": 190
    },
    {
      "epoch": 0.004732004732004732,
      "grad_norm": 30.10947608947754,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 8.452,
      "step": 195
    },
    {
      "epoch": 0.00485333818667152,
      "grad_norm": 34.635498046875,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 9.8912,
      "step": 200
    },
    {
      "epoch": 0.00485333818667152,
      "eval_loss": 2.1580023765563965,
      "eval_runtime": 1378.5777,
      "eval_samples_per_second": 12.586,
      "eval_steps_per_second": 6.293,
      "step": 200
    },
    {
      "epoch": 0.004974671641338308,
      "grad_norm": 7.406271934509277,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 8.5834,
      "step": 205
    },
    {
      "epoch": 0.005096005096005096,
      "grad_norm": 7.651792049407959,
      "learning_rate": 5.212206015980742e-05,
      "loss": 8.4876,
      "step": 210
    },
    {
      "epoch": 0.005217338550671884,
      "grad_norm": 7.223945617675781,
      "learning_rate": 5e-05,
      "loss": 8.0378,
      "step": 215
    },
    {
      "epoch": 0.005338672005338672,
      "grad_norm": 9.113810539245605,
      "learning_rate": 4.78779398401926e-05,
      "loss": 8.6686,
      "step": 220
    },
    {
      "epoch": 0.00546000546000546,
      "grad_norm": 9.819528579711914,
      "learning_rate": 4.575970377622456e-05,
      "loss": 8.2328,
      "step": 225
    },
    {
      "epoch": 0.005581338914672248,
      "grad_norm": 12.666204452514648,
      "learning_rate": 4.364910901265606e-05,
      "loss": 8.1959,
      "step": 230
    },
    {
      "epoch": 0.005702672369339036,
      "grad_norm": 14.743393898010254,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 8.423,
      "step": 235
    },
    {
      "epoch": 0.005824005824005824,
      "grad_norm": 16.668725967407227,
      "learning_rate": 3.94660365002137e-05,
      "loss": 8.2184,
      "step": 240
    },
    {
      "epoch": 0.005945339278672612,
      "grad_norm": 22.31512451171875,
      "learning_rate": 3.740109693074375e-05,
      "loss": 8.5404,
      "step": 245
    },
    {
      "epoch": 0.0060666727333394,
      "grad_norm": 29.229515075683594,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 8.5538,
      "step": 250
    },
    {
      "epoch": 0.006188006188006188,
      "grad_norm": 5.700004577636719,
      "learning_rate": 3.334301026289712e-05,
      "loss": 8.3141,
      "step": 255
    },
    {
      "epoch": 0.006309339642672976,
      "grad_norm": 6.940698623657227,
      "learning_rate": 3.135717611098458e-05,
      "loss": 8.3771,
      "step": 260
    },
    {
      "epoch": 0.006430673097339764,
      "grad_norm": 7.7714996337890625,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 8.2132,
      "step": 265
    },
    {
      "epoch": 0.006552006552006552,
      "grad_norm": 7.959089279174805,
      "learning_rate": 2.748981275911633e-05,
      "loss": 8.0231,
      "step": 270
    },
    {
      "epoch": 0.00667334000667334,
      "grad_norm": 9.615630149841309,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 8.3783,
      "step": 275
    },
    {
      "epoch": 0.006794673461340128,
      "grad_norm": 10.886713027954102,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 8.1763,
      "step": 280
    },
    {
      "epoch": 0.006916006916006916,
      "grad_norm": 13.622564315795898,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 8.4149,
      "step": 285
    },
    {
      "epoch": 0.007037340370673704,
      "grad_norm": 12.632689476013184,
      "learning_rate": 2.026834118478567e-05,
      "loss": 8.6351,
      "step": 290
    },
    {
      "epoch": 0.007158673825340492,
      "grad_norm": 23.478530883789062,
      "learning_rate": 1.858900013521788e-05,
      "loss": 9.0105,
      "step": 295
    },
    {
      "epoch": 0.00728000728000728,
      "grad_norm": 38.015594482421875,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 10.2111,
      "step": 300
    },
    {
      "epoch": 0.00728000728000728,
      "eval_loss": 2.095071792602539,
      "eval_runtime": 1377.368,
      "eval_samples_per_second": 12.597,
      "eval_steps_per_second": 6.299,
      "step": 300
    },
    {
      "epoch": 0.007401340734674068,
      "grad_norm": 5.979774475097656,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 8.241,
      "step": 305
    },
    {
      "epoch": 0.007522674189340856,
      "grad_norm": 7.0730977058410645,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 8.447,
      "step": 310
    },
    {
      "epoch": 0.007644007644007644,
      "grad_norm": 8.113957405090332,
      "learning_rate": 1.246638473736378e-05,
      "loss": 7.9333,
      "step": 315
    },
    {
      "epoch": 0.007765341098674432,
      "grad_norm": 8.48040771484375,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 7.9684,
      "step": 320
    },
    {
      "epoch": 0.00788667455334122,
      "grad_norm": 10.31874942779541,
      "learning_rate": 9.800143481652979e-06,
      "loss": 8.1914,
      "step": 325
    },
    {
      "epoch": 0.008008008008008008,
      "grad_norm": 11.321582794189453,
      "learning_rate": 8.574517537807897e-06,
      "loss": 7.8632,
      "step": 330
    },
    {
      "epoch": 0.008129341462674796,
      "grad_norm": 13.255796432495117,
      "learning_rate": 7.423543113334436e-06,
      "loss": 8.512,
      "step": 335
    },
    {
      "epoch": 0.008250674917341584,
      "grad_norm": 15.251378059387207,
      "learning_rate": 6.349294341940593e-06,
      "loss": 7.9517,
      "step": 340
    },
    {
      "epoch": 0.008372008372008372,
      "grad_norm": 27.332515716552734,
      "learning_rate": 5.353707092521582e-06,
      "loss": 8.3471,
      "step": 345
    },
    {
      "epoch": 0.00849334182667516,
      "grad_norm": 31.89665985107422,
      "learning_rate": 4.43857548059321e-06,
      "loss": 10.6653,
      "step": 350
    },
    {
      "epoch": 0.008614675281341948,
      "grad_norm": 5.819257736206055,
      "learning_rate": 3.605548635174533e-06,
      "loss": 8.2614,
      "step": 355
    },
    {
      "epoch": 0.008736008736008737,
      "grad_norm": 6.525805950164795,
      "learning_rate": 2.85612772694579e-06,
      "loss": 8.3166,
      "step": 360
    },
    {
      "epoch": 0.008857342190675525,
      "grad_norm": 7.613458156585693,
      "learning_rate": 2.191663263037458e-06,
      "loss": 8.2945,
      "step": 365
    },
    {
      "epoch": 0.008978675645342313,
      "grad_norm": 8.144882202148438,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 8.2034,
      "step": 370
    },
    {
      "epoch": 0.009100009100009101,
      "grad_norm": 11.035107612609863,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 8.6847,
      "step": 375
    },
    {
      "epoch": 0.009221342554675887,
      "grad_norm": 10.601295471191406,
      "learning_rate": 7.192044826145771e-07,
      "loss": 8.3069,
      "step": 380
    },
    {
      "epoch": 0.009342676009342675,
      "grad_norm": 13.104430198669434,
      "learning_rate": 4.049782370561583e-07,
      "loss": 7.9392,
      "step": 385
    },
    {
      "epoch": 0.009464009464009463,
      "grad_norm": 15.135002136230469,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 8.3515,
      "step": 390
    },
    {
      "epoch": 0.009585342918676252,
      "grad_norm": 21.206899642944336,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 8.7798,
      "step": 395
    },
    {
      "epoch": 0.00970667637334304,
      "grad_norm": 25.19953727722168,
      "learning_rate": 0.0,
      "loss": 9.0401,
      "step": 400
    },
    {
      "epoch": 0.00970667637334304,
      "eval_loss": 2.0877583026885986,
      "eval_runtime": 1377.6722,
      "eval_samples_per_second": 12.594,
      "eval_steps_per_second": 6.298,
      "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": 1.403012163651502e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}