{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03364030108069467,
  "eval_steps": 100,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.410075270173668e-05,
      "eval_loss": 2.455552101135254,
      "eval_runtime": 136.724,
      "eval_samples_per_second": 36.621,
      "eval_steps_per_second": 18.314,
      "step": 1
    },
    {
      "epoch": 0.0004205037635086834,
      "grad_norm": 0.061516229063272476,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 2.5665,
      "step": 5
    },
    {
      "epoch": 0.0008410075270173668,
      "grad_norm": 0.06682025641202927,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 2.4569,
      "step": 10
    },
    {
      "epoch": 0.0012615112905260501,
      "grad_norm": 0.07316667586565018,
      "learning_rate": 5e-05,
      "loss": 2.3649,
      "step": 15
    },
    {
      "epoch": 0.0016820150540347335,
      "grad_norm": 0.07515250891447067,
      "learning_rate": 6.666666666666667e-05,
      "loss": 2.578,
      "step": 20
    },
    {
      "epoch": 0.002102518817543417,
      "grad_norm": 0.09295528382062912,
      "learning_rate": 8.333333333333334e-05,
      "loss": 2.4301,
      "step": 25
    },
    {
      "epoch": 0.0025230225810521003,
      "grad_norm": 0.10444117337465286,
      "learning_rate": 0.0001,
      "loss": 2.3964,
      "step": 30
    },
    {
      "epoch": 0.0029435263445607837,
      "grad_norm": 0.1318625807762146,
      "learning_rate": 9.995494831023409e-05,
      "loss": 2.3552,
      "step": 35
    },
    {
      "epoch": 0.003364030108069467,
      "grad_norm": 0.16391368210315704,
      "learning_rate": 9.981987442712633e-05,
      "loss": 2.3698,
      "step": 40
    },
    {
      "epoch": 0.0037845338715781504,
      "grad_norm": 0.17712588608264923,
      "learning_rate": 9.959502176294383e-05,
      "loss": 2.3925,
      "step": 45
    },
    {
      "epoch": 0.004205037635086834,
      "grad_norm": 0.39612510800361633,
      "learning_rate": 9.928079551738543e-05,
      "loss": 2.4663,
      "step": 50
    },
    {
      "epoch": 0.004625541398595517,
      "grad_norm": 0.09515935927629471,
      "learning_rate": 9.887776194738432e-05,
      "loss": 2.4983,
      "step": 55
    },
    {
      "epoch": 0.005046045162104201,
      "grad_norm": 0.11080324649810791,
      "learning_rate": 9.838664734667495e-05,
      "loss": 2.2962,
      "step": 60
    },
    {
      "epoch": 0.005466548925612884,
      "grad_norm": 0.13558542728424072,
      "learning_rate": 9.780833673696254e-05,
      "loss": 2.4226,
      "step": 65
    },
    {
      "epoch": 0.005887052689121567,
      "grad_norm": 0.1685813069343567,
      "learning_rate": 9.714387227305422e-05,
      "loss": 2.1086,
      "step": 70
    },
    {
      "epoch": 0.006307556452630251,
      "grad_norm": 0.17459285259246826,
      "learning_rate": 9.639445136482548e-05,
      "loss": 2.2214,
      "step": 75
    },
    {
      "epoch": 0.006728060216138934,
      "grad_norm": 0.16025687754154205,
      "learning_rate": 9.55614245194068e-05,
      "loss": 2.214,
      "step": 80
    },
    {
      "epoch": 0.0071485639796476175,
      "grad_norm": 0.1828812062740326,
      "learning_rate": 9.464629290747842e-05,
      "loss": 2.2223,
      "step": 85
    },
    {
      "epoch": 0.007569067743156301,
      "grad_norm": 0.27228423953056335,
      "learning_rate": 9.365070565805941e-05,
      "loss": 2.1236,
      "step": 90
    },
    {
      "epoch": 0.007989571506664985,
      "grad_norm": 0.26386409997940063,
      "learning_rate": 9.257645688666556e-05,
      "loss": 2.1231,
      "step": 95
    },
    {
      "epoch": 0.008410075270173668,
      "grad_norm": 0.5400829911231995,
      "learning_rate": 9.142548246219212e-05,
      "loss": 2.2237,
      "step": 100
    },
    {
      "epoch": 0.008410075270173668,
      "eval_loss": 2.2322306632995605,
      "eval_runtime": 137.6954,
      "eval_samples_per_second": 36.363,
      "eval_steps_per_second": 18.185,
      "step": 100
    },
    {
      "epoch": 0.008830579033682352,
      "grad_norm": 0.15684477984905243,
      "learning_rate": 9.019985651834703e-05,
      "loss": 2.5101,
      "step": 105
    },
    {
      "epoch": 0.009251082797191034,
      "grad_norm": 0.1612066924571991,
      "learning_rate": 8.890178771592199e-05,
      "loss": 2.2813,
      "step": 110
    },
    {
      "epoch": 0.009671586560699719,
      "grad_norm": 0.16366064548492432,
      "learning_rate": 8.753361526263621e-05,
      "loss": 2.1971,
      "step": 115
    },
    {
      "epoch": 0.010092090324208401,
      "grad_norm": 0.14715352654457092,
      "learning_rate": 8.609780469772623e-05,
      "loss": 2.2583,
      "step": 120
    },
    {
      "epoch": 0.010512594087717085,
      "grad_norm": 0.14901845157146454,
      "learning_rate": 8.459694344887732e-05,
      "loss": 2.2686,
      "step": 125
    },
    {
      "epoch": 0.010933097851225768,
      "grad_norm": 0.15839141607284546,
      "learning_rate": 8.303373616950408e-05,
      "loss": 2.1073,
      "step": 130
    },
    {
      "epoch": 0.011353601614734452,
      "grad_norm": 0.17715802788734436,
      "learning_rate": 8.141099986478212e-05,
      "loss": 1.9419,
      "step": 135
    },
    {
      "epoch": 0.011774105378243135,
      "grad_norm": 0.26136475801467896,
      "learning_rate": 7.973165881521434e-05,
      "loss": 2.2758,
      "step": 140
    },
    {
      "epoch": 0.012194609141751819,
      "grad_norm": 0.3973328173160553,
      "learning_rate": 7.799873930687978e-05,
      "loss": 2.2096,
      "step": 145
    },
    {
      "epoch": 0.012615112905260501,
      "grad_norm": 0.5721274614334106,
      "learning_rate": 7.621536417786159e-05,
      "loss": 2.3204,
      "step": 150
    },
    {
      "epoch": 0.013035616668769186,
      "grad_norm": 0.14594975113868713,
      "learning_rate": 7.438474719068173e-05,
      "loss": 2.5064,
      "step": 155
    },
    {
      "epoch": 0.013456120432277868,
      "grad_norm": 0.15619051456451416,
      "learning_rate": 7.251018724088367e-05,
      "loss": 2.4115,
      "step": 160
    },
    {
      "epoch": 0.013876624195786552,
      "grad_norm": 0.1778382658958435,
      "learning_rate": 7.059506241219965e-05,
      "loss": 2.2572,
      "step": 165
    },
    {
      "epoch": 0.014297127959295235,
      "grad_norm": 0.1677156537771225,
      "learning_rate": 6.864282388901544e-05,
      "loss": 2.2979,
      "step": 170
    },
    {
      "epoch": 0.01471763172280392,
      "grad_norm": 0.1879958063364029,
      "learning_rate": 6.665698973710288e-05,
      "loss": 2.3639,
      "step": 175
    },
    {
      "epoch": 0.015138135486312602,
      "grad_norm": 0.16478297114372253,
      "learning_rate": 6.464113856382752e-05,
      "loss": 2.069,
      "step": 180
    },
    {
      "epoch": 0.015558639249821286,
      "grad_norm": 0.2005874663591385,
      "learning_rate": 6.259890306925627e-05,
      "loss": 2.2069,
      "step": 185
    },
    {
      "epoch": 0.01597914301332997,
      "grad_norm": 0.19986580312252045,
      "learning_rate": 6.0533963499786314e-05,
      "loss": 2.0721,
      "step": 190
    },
    {
      "epoch": 0.016399646776838653,
      "grad_norm": 0.26056787371635437,
      "learning_rate": 5.8450041016092464e-05,
      "loss": 2.0954,
      "step": 195
    },
    {
      "epoch": 0.016820150540347335,
      "grad_norm": 0.5209627747535706,
      "learning_rate": 5.6350890987343944e-05,
      "loss": 2.2024,
      "step": 200
    },
    {
      "epoch": 0.016820150540347335,
      "eval_loss": 2.1986591815948486,
      "eval_runtime": 136.7325,
      "eval_samples_per_second": 36.619,
      "eval_steps_per_second": 18.313,
      "step": 200
    },
    {
      "epoch": 0.017240654303856018,
      "grad_norm": 0.13844060897827148,
      "learning_rate": 5.4240296223775465e-05,
      "loss": 2.4311,
      "step": 205
    },
    {
      "epoch": 0.017661158067364704,
      "grad_norm": 0.1341000646352768,
      "learning_rate": 5.212206015980742e-05,
      "loss": 2.3207,
      "step": 210
    },
    {
      "epoch": 0.018081661830873386,
      "grad_norm": 0.1552341878414154,
      "learning_rate": 5e-05,
      "loss": 2.1699,
      "step": 215
    },
    {
      "epoch": 0.01850216559438207,
      "grad_norm": 0.16552487015724182,
      "learning_rate": 4.78779398401926e-05,
      "loss": 2.2501,
      "step": 220
    },
    {
      "epoch": 0.018922669357890755,
      "grad_norm": 0.1618565171957016,
      "learning_rate": 4.575970377622456e-05,
      "loss": 2.1608,
      "step": 225
    },
    {
      "epoch": 0.019343173121399437,
      "grad_norm": 0.22135402262210846,
      "learning_rate": 4.364910901265606e-05,
      "loss": 2.2906,
      "step": 230
    },
    {
      "epoch": 0.01976367688490812,
      "grad_norm": 0.19016629457473755,
      "learning_rate": 4.1549958983907555e-05,
      "loss": 2.2022,
      "step": 235
    },
    {
      "epoch": 0.020184180648416802,
      "grad_norm": 0.23073601722717285,
      "learning_rate": 3.94660365002137e-05,
      "loss": 2.2141,
      "step": 240
    },
    {
      "epoch": 0.02060468441192549,
      "grad_norm": 0.24301667511463165,
      "learning_rate": 3.740109693074375e-05,
      "loss": 2.0205,
      "step": 245
    },
    {
      "epoch": 0.02102518817543417,
      "grad_norm": 0.5293435454368591,
      "learning_rate": 3.5358861436172485e-05,
      "loss": 2.4058,
      "step": 250
    },
    {
      "epoch": 0.021445691938942853,
      "grad_norm": 0.1276913732290268,
      "learning_rate": 3.334301026289712e-05,
      "loss": 2.396,
      "step": 255
    },
    {
      "epoch": 0.021866195702451536,
      "grad_norm": 0.1355343610048294,
      "learning_rate": 3.135717611098458e-05,
      "loss": 2.4526,
      "step": 260
    },
    {
      "epoch": 0.022286699465960222,
      "grad_norm": 0.19372831284999847,
      "learning_rate": 2.9404937587800375e-05,
      "loss": 2.2503,
      "step": 265
    },
    {
      "epoch": 0.022707203229468904,
      "grad_norm": 0.15309953689575195,
      "learning_rate": 2.748981275911633e-05,
      "loss": 2.2225,
      "step": 270
    },
    {
      "epoch": 0.023127706992977587,
      "grad_norm": 0.16677720844745636,
      "learning_rate": 2.5615252809318284e-05,
      "loss": 2.3229,
      "step": 275
    },
    {
      "epoch": 0.02354821075648627,
      "grad_norm": 0.18368959426879883,
      "learning_rate": 2.3784635822138424e-05,
      "loss": 2.0278,
      "step": 280
    },
    {
      "epoch": 0.023968714519994955,
      "grad_norm": 0.21546456217765808,
      "learning_rate": 2.2001260693120233e-05,
      "loss": 2.1724,
      "step": 285
    },
    {
      "epoch": 0.024389218283503638,
      "grad_norm": 0.20836783945560455,
      "learning_rate": 2.026834118478567e-05,
      "loss": 2.1573,
      "step": 290
    },
    {
      "epoch": 0.02480972204701232,
      "grad_norm": 0.33140066266059875,
      "learning_rate": 1.858900013521788e-05,
      "loss": 2.0417,
      "step": 295
    },
    {
      "epoch": 0.025230225810521003,
      "grad_norm": 0.5527989864349365,
      "learning_rate": 1.6966263830495936e-05,
      "loss": 2.0386,
      "step": 300
    },
    {
      "epoch": 0.025230225810521003,
      "eval_loss": 2.1904244422912598,
      "eval_runtime": 135.9065,
      "eval_samples_per_second": 36.842,
      "eval_steps_per_second": 18.424,
      "step": 300
    },
    {
      "epoch": 0.02565072957402969,
      "grad_norm": 0.1280973106622696,
      "learning_rate": 1.5403056551122697e-05,
      "loss": 2.3235,
      "step": 305
    },
    {
      "epoch": 0.02607123333753837,
      "grad_norm": 0.34544607996940613,
      "learning_rate": 1.3902195302273779e-05,
      "loss": 2.2402,
      "step": 310
    },
    {
      "epoch": 0.026491737101047054,
      "grad_norm": 0.16120262444019318,
      "learning_rate": 1.246638473736378e-05,
      "loss": 2.2911,
      "step": 315
    },
    {
      "epoch": 0.026912240864555736,
      "grad_norm": 0.14794592559337616,
      "learning_rate": 1.1098212284078036e-05,
      "loss": 2.1851,
      "step": 320
    },
    {
      "epoch": 0.027332744628064422,
      "grad_norm": 0.1898762285709381,
      "learning_rate": 9.800143481652979e-06,
      "loss": 2.2621,
      "step": 325
    },
    {
      "epoch": 0.027753248391573105,
      "grad_norm": 0.17783233523368835,
      "learning_rate": 8.574517537807897e-06,
      "loss": 2.0929,
      "step": 330
    },
    {
      "epoch": 0.028173752155081788,
      "grad_norm": 0.2266913205385208,
      "learning_rate": 7.423543113334436e-06,
      "loss": 2.0296,
      "step": 335
    },
    {
      "epoch": 0.02859425591859047,
      "grad_norm": 0.25079411268234253,
      "learning_rate": 6.349294341940593e-06,
      "loss": 2.1823,
      "step": 340
    },
    {
      "epoch": 0.029014759682099156,
      "grad_norm": 0.27541884779930115,
      "learning_rate": 5.353707092521582e-06,
      "loss": 2.0869,
      "step": 345
    },
    {
      "epoch": 0.02943526344560784,
      "grad_norm": 0.5358629822731018,
      "learning_rate": 4.43857548059321e-06,
      "loss": 2.0394,
      "step": 350
    },
    {
      "epoch": 0.02985576720911652,
      "grad_norm": 0.12496625632047653,
      "learning_rate": 3.605548635174533e-06,
      "loss": 2.4878,
      "step": 355
    },
    {
      "epoch": 0.030276270972625204,
      "grad_norm": 0.14630809426307678,
      "learning_rate": 2.85612772694579e-06,
      "loss": 2.3984,
      "step": 360
    },
    {
      "epoch": 0.03069677473613389,
      "grad_norm": 0.16718946397304535,
      "learning_rate": 2.191663263037458e-06,
      "loss": 2.1948,
      "step": 365
    },
    {
      "epoch": 0.031117278499642572,
      "grad_norm": 0.1454736739397049,
      "learning_rate": 1.6133526533250565e-06,
      "loss": 2.1282,
      "step": 370
    },
    {
      "epoch": 0.03153778226315126,
      "grad_norm": 0.18479801714420319,
      "learning_rate": 1.1222380526156928e-06,
      "loss": 2.304,
      "step": 375
    },
    {
      "epoch": 0.03195828602665994,
      "grad_norm": 0.19204293191432953,
      "learning_rate": 7.192044826145771e-07,
      "loss": 2.1793,
      "step": 380
    },
    {
      "epoch": 0.03237878979016862,
      "grad_norm": 0.19590827822685242,
      "learning_rate": 4.049782370561583e-07,
      "loss": 2.2266,
      "step": 385
    },
    {
      "epoch": 0.032799293553677306,
      "grad_norm": 0.2132268100976944,
      "learning_rate": 1.8012557287367392e-07,
      "loss": 2.031,
      "step": 390
    },
    {
      "epoch": 0.03321979731718599,
      "grad_norm": 0.31217649579048157,
      "learning_rate": 4.5051689765929214e-08,
      "loss": 2.0957,
      "step": 395
    },
    {
      "epoch": 0.03364030108069467,
      "grad_norm": 0.5439748167991638,
      "learning_rate": 0.0,
      "loss": 2.0577,
      "step": 400
    },
    {
      "epoch": 0.03364030108069467,
      "eval_loss": 2.1888887882232666,
      "eval_runtime": 136.3401,
      "eval_samples_per_second": 36.724,
      "eval_steps_per_second": 18.366,
      "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": 6279181392936960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}