{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.10402444574475002,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000260061114361875,
      "eval_loss": 3.210697650909424,
      "eval_runtime": 46.0394,
      "eval_samples_per_second": 140.684,
      "eval_steps_per_second": 17.594,
      "step": 1
    },
    {
      "epoch": 0.001300305571809375,
      "grad_norm": 0.1790143996477127,
      "learning_rate": 5e-05,
      "loss": 3.2141,
      "step": 5
    },
    {
      "epoch": 0.00260061114361875,
      "grad_norm": 0.20394925773143768,
      "learning_rate": 0.0001,
      "loss": 3.1651,
      "step": 10
    },
    {
      "epoch": 0.0039009167154281255,
      "grad_norm": 0.21119458973407745,
      "learning_rate": 9.995944990857849e-05,
      "loss": 3.1673,
      "step": 15
    },
    {
      "epoch": 0.0052012222872375,
      "grad_norm": 0.2528775930404663,
      "learning_rate": 9.983786540671051e-05,
      "loss": 3.1641,
      "step": 20
    },
    {
      "epoch": 0.006501527859046876,
      "grad_norm": 0.2846454381942749,
      "learning_rate": 9.96354437049027e-05,
      "loss": 3.0395,
      "step": 25
    },
    {
      "epoch": 0.007801833430856251,
      "grad_norm": 0.2666814625263214,
      "learning_rate": 9.935251313189564e-05,
      "loss": 2.9841,
      "step": 30
    },
    {
      "epoch": 0.009102139002665627,
      "grad_norm": 0.2622530460357666,
      "learning_rate": 9.898953260211338e-05,
      "loss": 2.7829,
      "step": 35
    },
    {
      "epoch": 0.010402444574475,
      "grad_norm": 0.25730785727500916,
      "learning_rate": 9.85470908713026e-05,
      "loss": 2.911,
      "step": 40
    },
    {
      "epoch": 0.011702750146284377,
      "grad_norm": 0.23502734303474426,
      "learning_rate": 9.802590558156862e-05,
      "loss": 2.7205,
      "step": 45
    },
    {
      "epoch": 0.013003055718093752,
      "grad_norm": 0.22792138159275055,
      "learning_rate": 9.742682209735727e-05,
      "loss": 2.7597,
      "step": 50
    },
    {
      "epoch": 0.014303361289903128,
      "grad_norm": 0.22460439801216125,
      "learning_rate": 9.675081213427076e-05,
      "loss": 2.624,
      "step": 55
    },
    {
      "epoch": 0.015603666861712502,
      "grad_norm": 0.2262052595615387,
      "learning_rate": 9.599897218294122e-05,
      "loss": 2.6747,
      "step": 60
    },
    {
      "epoch": 0.016903972433521878,
      "grad_norm": 0.21055257320404053,
      "learning_rate": 9.517252173051911e-05,
      "loss": 2.6395,
      "step": 65
    },
    {
      "epoch": 0.018204278005331254,
      "grad_norm": 0.20293797552585602,
      "learning_rate": 9.42728012826605e-05,
      "loss": 2.5635,
      "step": 70
    },
    {
      "epoch": 0.01950458357714063,
      "grad_norm": 0.19834651052951813,
      "learning_rate": 9.330127018922194e-05,
      "loss": 2.6046,
      "step": 75
    },
    {
      "epoch": 0.02080488914895,
      "grad_norm": 0.2112269252538681,
      "learning_rate": 9.225950427718975e-05,
      "loss": 2.5376,
      "step": 80
    },
    {
      "epoch": 0.022105194720759377,
      "grad_norm": 0.1964295357465744,
      "learning_rate": 9.114919329468282e-05,
      "loss": 2.4841,
      "step": 85
    },
    {
      "epoch": 0.023405500292568753,
      "grad_norm": 0.20404809713363647,
      "learning_rate": 8.997213817017507e-05,
      "loss": 2.451,
      "step": 90
    },
    {
      "epoch": 0.02470580586437813,
      "grad_norm": 0.2313140332698822,
      "learning_rate": 8.873024809138272e-05,
      "loss": 2.487,
      "step": 95
    },
    {
      "epoch": 0.026006111436187505,
      "grad_norm": 0.23010624945163727,
      "learning_rate": 8.742553740855506e-05,
      "loss": 2.4241,
      "step": 100
    },
    {
      "epoch": 0.026006111436187505,
      "eval_loss": 2.4956908226013184,
      "eval_runtime": 45.9142,
      "eval_samples_per_second": 141.067,
      "eval_steps_per_second": 17.642,
      "step": 100
    },
    {
      "epoch": 0.02730641700799688,
      "grad_norm": 0.2048594206571579,
      "learning_rate": 8.606012236719073e-05,
      "loss": 2.473,
      "step": 105
    },
    {
      "epoch": 0.028606722579806256,
      "grad_norm": 0.2099340707063675,
      "learning_rate": 8.463621767547998e-05,
      "loss": 2.5045,
      "step": 110
    },
    {
      "epoch": 0.02990702815161563,
      "grad_norm": 0.18916481733322144,
      "learning_rate": 8.315613291203976e-05,
      "loss": 2.4466,
      "step": 115
    },
    {
      "epoch": 0.031207333723425004,
      "grad_norm": 0.20611602067947388,
      "learning_rate": 8.162226877976887e-05,
      "loss": 2.4546,
      "step": 120
    },
    {
      "epoch": 0.03250763929523438,
      "grad_norm": 0.21061871945858002,
      "learning_rate": 8.003711321189895e-05,
      "loss": 2.4797,
      "step": 125
    },
    {
      "epoch": 0.033807944867043756,
      "grad_norm": 0.20406612753868103,
      "learning_rate": 7.840323733655778e-05,
      "loss": 2.5568,
      "step": 130
    },
    {
      "epoch": 0.03510825043885313,
      "grad_norm": 0.21400322020053864,
      "learning_rate": 7.672329130639005e-05,
      "loss": 2.4747,
      "step": 135
    },
    {
      "epoch": 0.03640855601066251,
      "grad_norm": 0.22233155369758606,
      "learning_rate": 7.500000000000001e-05,
      "loss": 2.5571,
      "step": 140
    },
    {
      "epoch": 0.03770886158247188,
      "grad_norm": 0.21888834238052368,
      "learning_rate": 7.323615860218843e-05,
      "loss": 2.4723,
      "step": 145
    },
    {
      "epoch": 0.03900916715428126,
      "grad_norm": 0.21492037177085876,
      "learning_rate": 7.143462807015271e-05,
      "loss": 2.4496,
      "step": 150
    },
    {
      "epoch": 0.04030947272609063,
      "grad_norm": 0.229643777012825,
      "learning_rate": 6.959833049300377e-05,
      "loss": 2.4829,
      "step": 155
    },
    {
      "epoch": 0.0416097782979,
      "grad_norm": 0.19544768333435059,
      "learning_rate": 6.773024435212678e-05,
      "loss": 2.4211,
      "step": 160
    },
    {
      "epoch": 0.04291008386970938,
      "grad_norm": 0.2128247320652008,
      "learning_rate": 6.583339969007363e-05,
      "loss": 2.3166,
      "step": 165
    },
    {
      "epoch": 0.044210389441518755,
      "grad_norm": 0.2158002257347107,
      "learning_rate": 6.391087319582264e-05,
      "loss": 2.4202,
      "step": 170
    },
    {
      "epoch": 0.045510695013328134,
      "grad_norm": 0.23509222269058228,
      "learning_rate": 6.19657832143779e-05,
      "loss": 2.381,
      "step": 175
    },
    {
      "epoch": 0.046811000585137506,
      "grad_norm": 0.21844059228897095,
      "learning_rate": 6.0001284688802226e-05,
      "loss": 2.4878,
      "step": 180
    },
    {
      "epoch": 0.048111306156946886,
      "grad_norm": 0.22377453744411469,
      "learning_rate": 5.8020564042888015e-05,
      "loss": 2.3867,
      "step": 185
    },
    {
      "epoch": 0.04941161172875626,
      "grad_norm": 0.22664517164230347,
      "learning_rate": 5.602683401276615e-05,
      "loss": 2.4527,
      "step": 190
    },
    {
      "epoch": 0.05071191730056563,
      "grad_norm": 0.21447192132472992,
      "learning_rate": 5.402332843583631e-05,
      "loss": 2.3911,
      "step": 195
    },
    {
      "epoch": 0.05201222287237501,
      "grad_norm": 0.22999480366706848,
      "learning_rate": 5.201329700547076e-05,
      "loss": 2.4612,
      "step": 200
    },
    {
      "epoch": 0.05201222287237501,
      "eval_loss": 2.436123847961426,
      "eval_runtime": 45.8777,
      "eval_samples_per_second": 141.18,
      "eval_steps_per_second": 17.656,
      "step": 200
    },
    {
      "epoch": 0.05331252844418438,
      "grad_norm": 0.2229231297969818,
      "learning_rate": 5e-05,
      "loss": 2.4477,
      "step": 205
    },
    {
      "epoch": 0.05461283401599376,
      "grad_norm": 0.22189436852931976,
      "learning_rate": 4.798670299452926e-05,
      "loss": 2.4228,
      "step": 210
    },
    {
      "epoch": 0.05591313958780313,
      "grad_norm": 0.21090376377105713,
      "learning_rate": 4.597667156416371e-05,
      "loss": 2.3939,
      "step": 215
    },
    {
      "epoch": 0.05721344515961251,
      "grad_norm": 0.20227909088134766,
      "learning_rate": 4.397316598723385e-05,
      "loss": 2.37,
      "step": 220
    },
    {
      "epoch": 0.058513750731421885,
      "grad_norm": 0.21790654957294464,
      "learning_rate": 4.197943595711198e-05,
      "loss": 2.4721,
      "step": 225
    },
    {
      "epoch": 0.05981405630323126,
      "grad_norm": 0.1942271739244461,
      "learning_rate": 3.9998715311197785e-05,
      "loss": 2.4373,
      "step": 230
    },
    {
      "epoch": 0.061114361875040636,
      "grad_norm": 0.20492784678936005,
      "learning_rate": 3.803421678562213e-05,
      "loss": 2.4142,
      "step": 235
    },
    {
      "epoch": 0.06241466744685001,
      "grad_norm": 0.23484589159488678,
      "learning_rate": 3.608912680417737e-05,
      "loss": 2.5037,
      "step": 240
    },
    {
      "epoch": 0.06371497301865939,
      "grad_norm": 0.20387956500053406,
      "learning_rate": 3.4166600309926387e-05,
      "loss": 2.4313,
      "step": 245
    },
    {
      "epoch": 0.06501527859046877,
      "grad_norm": 0.21440523862838745,
      "learning_rate": 3.226975564787322e-05,
      "loss": 2.3804,
      "step": 250
    },
    {
      "epoch": 0.06631558416227813,
      "grad_norm": 0.21894583106040955,
      "learning_rate": 3.0401669506996256e-05,
      "loss": 2.3944,
      "step": 255
    },
    {
      "epoch": 0.06761588973408751,
      "grad_norm": 0.23404517769813538,
      "learning_rate": 2.8565371929847284e-05,
      "loss": 2.4495,
      "step": 260
    },
    {
      "epoch": 0.06891619530589689,
      "grad_norm": 0.22827592492103577,
      "learning_rate": 2.6763841397811573e-05,
      "loss": 2.4284,
      "step": 265
    },
    {
      "epoch": 0.07021650087770626,
      "grad_norm": 0.2367011457681656,
      "learning_rate": 2.500000000000001e-05,
      "loss": 2.4119,
      "step": 270
    },
    {
      "epoch": 0.07151680644951564,
      "grad_norm": 0.23400311172008514,
      "learning_rate": 2.3276708693609943e-05,
      "loss": 2.5657,
      "step": 275
    },
    {
      "epoch": 0.07281711202132501,
      "grad_norm": 0.22112374007701874,
      "learning_rate": 2.1596762663442218e-05,
      "loss": 2.5174,
      "step": 280
    },
    {
      "epoch": 0.07411741759313438,
      "grad_norm": 0.22433413565158844,
      "learning_rate": 1.996288678810105e-05,
      "loss": 2.4226,
      "step": 285
    },
    {
      "epoch": 0.07541772316494376,
      "grad_norm": 0.21052949130535126,
      "learning_rate": 1.837773122023114e-05,
      "loss": 2.4243,
      "step": 290
    },
    {
      "epoch": 0.07671802873675314,
      "grad_norm": 0.21205665171146393,
      "learning_rate": 1.684386708796025e-05,
      "loss": 2.4338,
      "step": 295
    },
    {
      "epoch": 0.07801833430856252,
      "grad_norm": 0.23179137706756592,
      "learning_rate": 1.536378232452003e-05,
      "loss": 2.3962,
      "step": 300
    },
    {
      "epoch": 0.07801833430856252,
      "eval_loss": 2.4198389053344727,
      "eval_runtime": 45.9519,
      "eval_samples_per_second": 140.952,
      "eval_steps_per_second": 17.627,
      "step": 300
    },
    {
      "epoch": 0.07931863988037188,
      "grad_norm": 0.22041112184524536,
      "learning_rate": 1.3939877632809278e-05,
      "loss": 2.406,
      "step": 305
    },
    {
      "epoch": 0.08061894545218126,
      "grad_norm": 0.2416123002767563,
      "learning_rate": 1.257446259144494e-05,
      "loss": 2.3487,
      "step": 310
    },
    {
      "epoch": 0.08191925102399064,
      "grad_norm": 0.21595120429992676,
      "learning_rate": 1.1269751908617277e-05,
      "loss": 2.3856,
      "step": 315
    },
    {
      "epoch": 0.0832195565958,
      "grad_norm": 0.21398255228996277,
      "learning_rate": 1.0027861829824952e-05,
      "loss": 2.4034,
      "step": 320
    },
    {
      "epoch": 0.08451986216760939,
      "grad_norm": 0.2343326061964035,
      "learning_rate": 8.850806705317183e-06,
      "loss": 2.3638,
      "step": 325
    },
    {
      "epoch": 0.08582016773941877,
      "grad_norm": 0.23280276358127594,
      "learning_rate": 7.740495722810271e-06,
      "loss": 2.3899,
      "step": 330
    },
    {
      "epoch": 0.08712047331122814,
      "grad_norm": 0.22366644442081451,
      "learning_rate": 6.698729810778065e-06,
      "loss": 2.4007,
      "step": 335
    },
    {
      "epoch": 0.08842077888303751,
      "grad_norm": 0.25122907757759094,
      "learning_rate": 5.727198717339511e-06,
      "loss": 2.3721,
      "step": 340
    },
    {
      "epoch": 0.08972108445484689,
      "grad_norm": 0.25753486156463623,
      "learning_rate": 4.827478269480895e-06,
      "loss": 2.3808,
      "step": 345
    },
    {
      "epoch": 0.09102139002665627,
      "grad_norm": 0.22881199419498444,
      "learning_rate": 4.001027817058789e-06,
      "loss": 2.3813,
      "step": 350
    },
    {
      "epoch": 0.09232169559846563,
      "grad_norm": 0.22728504240512848,
      "learning_rate": 3.249187865729264e-06,
      "loss": 2.3886,
      "step": 355
    },
    {
      "epoch": 0.09362200117027501,
      "grad_norm": 0.2537117898464203,
      "learning_rate": 2.573177902642726e-06,
      "loss": 2.4104,
      "step": 360
    },
    {
      "epoch": 0.09492230674208439,
      "grad_norm": 0.2203947901725769,
      "learning_rate": 1.974094418431388e-06,
      "loss": 2.3652,
      "step": 365
    },
    {
      "epoch": 0.09622261231389377,
      "grad_norm": 0.24142761528491974,
      "learning_rate": 1.4529091286973995e-06,
      "loss": 2.4902,
      "step": 370
    },
    {
      "epoch": 0.09752291788570314,
      "grad_norm": 0.2279200553894043,
      "learning_rate": 1.0104673978866164e-06,
      "loss": 2.4341,
      "step": 375
    },
    {
      "epoch": 0.09882322345751252,
      "grad_norm": 0.22958961129188538,
      "learning_rate": 6.474868681043578e-07,
      "loss": 2.2886,
      "step": 380
    },
    {
      "epoch": 0.1001235290293219,
      "grad_norm": 0.25041958689689636,
      "learning_rate": 3.6455629509730136e-07,
      "loss": 2.3789,
      "step": 385
    },
    {
      "epoch": 0.10142383460113126,
      "grad_norm": 0.2322605699300766,
      "learning_rate": 1.6213459328950352e-07,
      "loss": 2.4435,
      "step": 390
    },
    {
      "epoch": 0.10272414017294064,
      "grad_norm": 0.22026541829109192,
      "learning_rate": 4.055009142152067e-08,
      "loss": 2.3933,
      "step": 395
    },
    {
      "epoch": 0.10402444574475002,
      "grad_norm": 0.22310110926628113,
      "learning_rate": 0.0,
      "loss": 2.3593,
      "step": 400
    },
    {
      "epoch": 0.10402444574475002,
      "eval_loss": 2.4176995754241943,
      "eval_runtime": 46.0549,
      "eval_samples_per_second": 140.636,
      "eval_steps_per_second": 17.588,
      "step": 400
    }
  ],
  "logging_steps": 5,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.5375418471153664e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}