{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 455,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 1.9999761633493754e-05,
      "loss": 1.0423,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 1.9994041405510705e-05,
      "loss": 2.4374,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 1.997617272301248e-05,
      "loss": 0.8502,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 1.9946415246951928e-05,
      "loss": 0.646,
      "step": 15
    },
    {
      "epoch": 0.04,
      "learning_rate": 1.9904804439875635e-05,
      "loss": 0.6536,
      "step": 20
    },
    {
      "epoch": 0.05,
      "learning_rate": 1.9851389890168738e-05,
      "loss": 0.5722,
      "step": 25
    },
    {
      "epoch": 0.07,
      "learning_rate": 1.9786235252959555e-05,
      "loss": 0.6106,
      "step": 30
    },
    {
      "epoch": 0.08,
      "learning_rate": 1.9709418174260523e-05,
      "loss": 0.6526,
      "step": 35
    },
    {
      "epoch": 0.09,
      "learning_rate": 1.9621030198436007e-05,
      "loss": 0.6348,
      "step": 40
    },
    {
      "epoch": 0.1,
      "learning_rate": 1.952117665910714e-05,
      "loss": 0.5979,
      "step": 45
    },
    {
      "epoch": 0.11,
      "learning_rate": 1.9409976553623767e-05,
      "loss": 0.5756,
      "step": 50
    },
    {
      "epoch": 0.12,
      "learning_rate": 1.9287562401253023e-05,
      "loss": 0.5432,
      "step": 55
    },
    {
      "epoch": 0.13,
      "learning_rate": 1.9154080085253665e-05,
      "loss": 0.5857,
      "step": 60
    },
    {
      "epoch": 0.14,
      "learning_rate": 1.900968867902419e-05,
      "loss": 0.5409,
      "step": 65
    },
    {
      "epoch": 0.15,
      "learning_rate": 1.8854560256532098e-05,
      "loss": 0.5595,
      "step": 70
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.8688879687250067e-05,
      "loss": 0.5723,
      "step": 75
    },
    {
      "epoch": 0.18,
      "learning_rate": 1.8512844415843514e-05,
      "loss": 0.5951,
      "step": 80
    },
    {
      "epoch": 0.19,
      "learning_rate": 1.8326664226872063e-05,
      "loss": 0.558,
      "step": 85
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.8130560994785325e-05,
      "loss": 0.5562,
      "step": 90
    },
    {
      "epoch": 0.21,
      "learning_rate": 1.7924768419510906e-05,
      "loss": 0.5595,
      "step": 95
    },
    {
      "epoch": 0.22,
      "learning_rate": 1.7709531747949796e-05,
      "loss": 0.5818,
      "step": 100
    },
    {
      "epoch": 0.23,
      "learning_rate": 1.7485107481711014e-05,
      "loss": 0.5446,
      "step": 105
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.7251763071433767e-05,
      "loss": 0.5287,
      "step": 110
    },
    {
      "epoch": 0.25,
      "learning_rate": 1.7009776598061496e-05,
      "loss": 0.5039,
      "step": 115
    },
    {
      "epoch": 0.26,
      "learning_rate": 1.6759436441447544e-05,
      "loss": 0.5484,
      "step": 120
    },
    {
      "epoch": 0.27,
      "learning_rate": 1.6501040936687444e-05,
      "loss": 0.5968,
      "step": 125
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.6234898018587336e-05,
      "loss": 0.514,
      "step": 130
    },
    {
      "epoch": 0.3,
      "learning_rate": 1.5961324854692254e-05,
      "loss": 0.5413,
      "step": 135
    },
    {
      "epoch": 0.31,
      "learning_rate": 1.568064746731156e-05,
      "loss": 0.497,
      "step": 140
    },
    {
      "epoch": 0.32,
      "learning_rate": 1.5393200344991993e-05,
      "loss": 0.4721,
      "step": 145
    },
    {
      "epoch": 0.33,
      "learning_rate": 1.5099326043901361e-05,
      "loss": 0.5212,
      "step": 150
    },
    {
      "epoch": 0.34,
      "learning_rate": 1.4799374779597866e-05,
      "loss": 0.5039,
      "step": 155
    },
    {
      "epoch": 0.35,
      "learning_rate": 1.4493704009671614e-05,
      "loss": 0.5297,
      "step": 160
    },
    {
      "epoch": 0.36,
      "learning_rate": 1.4182678007755653e-05,
      "loss": 0.5203,
      "step": 165
    },
    {
      "epoch": 0.37,
      "learning_rate": 1.3866667429414188e-05,
      "loss": 0.5279,
      "step": 170
    },
    {
      "epoch": 0.38,
      "learning_rate": 1.3546048870425356e-05,
      "loss": 0.5102,
      "step": 175
    },
    {
      "epoch": 0.4,
      "learning_rate": 1.3221204417984907e-05,
      "loss": 0.5044,
      "step": 180
    },
    {
      "epoch": 0.41,
      "learning_rate": 1.2892521195365679e-05,
      "loss": 0.5134,
      "step": 185
    },
    {
      "epoch": 0.42,
      "learning_rate": 1.2560390900575472e-05,
      "loss": 0.463,
      "step": 190
    },
    {
      "epoch": 0.43,
      "learning_rate": 1.2225209339563144e-05,
      "loss": 0.4506,
      "step": 195
    },
    {
      "epoch": 0.44,
      "learning_rate": 1.1887375954529167e-05,
      "loss": 0.5345,
      "step": 200
    },
    {
      "epoch": 0.45,
      "learning_rate": 1.1547293347902813e-05,
      "loss": 0.4631,
      "step": 205
    },
    {
      "epoch": 0.46,
      "learning_rate": 1.1205366802553231e-05,
      "loss": 0.5217,
      "step": 210
    },
    {
      "epoch": 0.47,
      "learning_rate": 1.0862003798806195e-05,
      "loss": 0.4843,
      "step": 215
    },
    {
      "epoch": 0.48,
      "learning_rate": 1.0517613528842096e-05,
      "loss": 0.4694,
      "step": 220
    },
    {
      "epoch": 0.49,
      "learning_rate": 1.0172606409053887e-05,
      "loss": 0.4658,
      "step": 225
    },
    {
      "epoch": 0.51,
      "learning_rate": 9.827393590946116e-06,
      "loss": 0.5038,
      "step": 230
    },
    {
      "epoch": 0.52,
      "learning_rate": 9.482386471157905e-06,
      "loss": 0.4652,
      "step": 235
    },
    {
      "epoch": 0.53,
      "learning_rate": 9.137996201193807e-06,
      "loss": 0.4731,
      "step": 240
    },
    {
      "epoch": 0.54,
      "learning_rate": 8.79463319744677e-06,
      "loss": 0.4803,
      "step": 245
    },
    {
      "epoch": 0.55,
      "learning_rate": 8.452706652097187e-06,
      "loss": 0.4798,
      "step": 250
    },
    {
      "epoch": 0.56,
      "learning_rate": 8.112624045470834e-06,
      "loss": 0.4305,
      "step": 255
    },
    {
      "epoch": 0.57,
      "learning_rate": 7.774790660436857e-06,
      "loss": 0.4479,
      "step": 260
    },
    {
      "epoch": 0.58,
      "learning_rate": 7.4396090994245295e-06,
      "loss": 0.4585,
      "step": 265
    },
    {
      "epoch": 0.59,
      "learning_rate": 7.107478804634324e-06,
      "loss": 0.4788,
      "step": 270
    },
    {
      "epoch": 0.6,
      "learning_rate": 6.778795582015096e-06,
      "loss": 0.4784,
      "step": 275
    },
    {
      "epoch": 0.62,
      "learning_rate": 6.453951129574644e-06,
      "loss": 0.4377,
      "step": 280
    },
    {
      "epoch": 0.63,
      "learning_rate": 6.133332570585813e-06,
      "loss": 0.4303,
      "step": 285
    },
    {
      "epoch": 0.64,
      "learning_rate": 5.8173219922443516e-06,
      "loss": 0.4167,
      "step": 290
    },
    {
      "epoch": 0.65,
      "learning_rate": 5.5062959903283855e-06,
      "loss": 0.4651,
      "step": 295
    },
    {
      "epoch": 0.66,
      "learning_rate": 5.200625220402139e-06,
      "loss": 0.45,
      "step": 300
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.900673956098644e-06,
      "loss": 0.436,
      "step": 305
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.606799655008009e-06,
      "loss": 0.445,
      "step": 310
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.319352532688444e-06,
      "loss": 0.4008,
      "step": 315
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.038675145307747e-06,
      "loss": 0.432,
      "step": 320
    },
    {
      "epoch": 0.71,
      "learning_rate": 3.7651019814126656e-06,
      "loss": 0.4396,
      "step": 325
    },
    {
      "epoch": 0.73,
      "learning_rate": 3.4989590633125583e-06,
      "loss": 0.4207,
      "step": 330
    },
    {
      "epoch": 0.74,
      "learning_rate": 3.2405635585524566e-06,
      "loss": 0.4439,
      "step": 335
    },
    {
      "epoch": 0.75,
      "learning_rate": 2.9902234019385056e-06,
      "loss": 0.4375,
      "step": 340
    },
    {
      "epoch": 0.76,
      "learning_rate": 2.748236928566238e-06,
      "loss": 0.423,
      "step": 345
    },
    {
      "epoch": 0.77,
      "learning_rate": 2.514892518288988e-06,
      "loss": 0.3762,
      "step": 350
    },
    {
      "epoch": 0.78,
      "learning_rate": 2.290468252050204e-06,
      "loss": 0.4148,
      "step": 355
    },
    {
      "epoch": 0.79,
      "learning_rate": 2.075231580489098e-06,
      "loss": 0.4162,
      "step": 360
    },
    {
      "epoch": 0.8,
      "learning_rate": 1.8694390052146737e-06,
      "loss": 0.376,
      "step": 365
    },
    {
      "epoch": 0.81,
      "learning_rate": 1.6733357731279375e-06,
      "loss": 0.4164,
      "step": 370
    },
    {
      "epoch": 0.82,
      "learning_rate": 1.4871555841564889e-06,
      "loss": 0.4212,
      "step": 375
    },
    {
      "epoch": 0.84,
      "learning_rate": 1.311120312749935e-06,
      "loss": 0.4117,
      "step": 380
    },
    {
      "epoch": 0.85,
      "learning_rate": 1.1454397434679022e-06,
      "loss": 0.3915,
      "step": 385
    },
    {
      "epoch": 0.86,
      "learning_rate": 9.903113209758098e-07,
      "loss": 0.4401,
      "step": 390
    },
    {
      "epoch": 0.87,
      "learning_rate": 8.459199147463371e-07,
      "loss": 0.4279,
      "step": 395
    },
    {
      "epoch": 0.88,
      "learning_rate": 7.124375987469767e-07,
      "loss": 0.4203,
      "step": 400
    },
    {
      "epoch": 0.89,
      "learning_rate": 5.900234463762367e-07,
      "loss": 0.4094,
      "step": 405
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.788233408928588e-07,
      "loss": 0.4232,
      "step": 410
    },
    {
      "epoch": 0.91,
      "learning_rate": 3.7896980156399533e-07,
      "loss": 0.3935,
      "step": 415
    },
    {
      "epoch": 0.92,
      "learning_rate": 2.905818257394799e-07,
      "loss": 0.3882,
      "step": 420
    },
    {
      "epoch": 0.93,
      "learning_rate": 2.1376474704044693e-07,
      "loss": 0.3723,
      "step": 425
    },
    {
      "epoch": 0.95,
      "learning_rate": 1.4861010983126202e-07,
      "loss": 0.445,
      "step": 430
    },
    {
      "epoch": 0.96,
      "learning_rate": 9.519556012436815e-08,
      "loss": 0.3977,
      "step": 435
    },
    {
      "epoch": 0.97,
      "learning_rate": 5.3584753048073756e-08,
      "loss": 0.3754,
      "step": 440
    },
    {
      "epoch": 0.98,
      "learning_rate": 2.3827276987524738e-08,
      "loss": 0.3606,
      "step": 445
    },
    {
      "epoch": 0.99,
      "learning_rate": 5.958594489295921e-09,
      "loss": 0.4188,
      "step": 450
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.0,
      "loss": 0.3753,
      "step": 455
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.377094566822052,
      "eval_runtime": 10.8473,
      "eval_samples_per_second": 18.438,
      "eval_steps_per_second": 0.369,
      "step": 455
    },
    {
      "epoch": 1.0,
      "step": 455,
      "total_flos": 3232394280960.0,
      "train_loss": 0.5052832438395574,
      "train_runtime": 3169.7819,
      "train_samples_per_second": 2.294,
      "train_steps_per_second": 0.144
    }
  ],
  "logging_steps": 5,
  "max_steps": 455,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "total_flos": 3232394280960.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}