{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2846975088967972,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0035587188612099642,
      "grad_norm": 3.714656812928013,
      "learning_rate": 3.521126760563381e-06,
      "loss": 1.2324,
      "mean_token_accuracy": 0.706312108039856,
      "step": 5
    },
    {
      "epoch": 0.0071174377224199285,
      "grad_norm": 2.538884412766077,
      "learning_rate": 7.042253521126762e-06,
      "loss": 1.1399,
      "mean_token_accuracy": 0.7131082773208618,
      "step": 10
    },
    {
      "epoch": 0.010676156583629894,
      "grad_norm": 1.7771129703443833,
      "learning_rate": 1.056338028169014e-05,
      "loss": 0.9862,
      "mean_token_accuracy": 0.7257840037345886,
      "step": 15
    },
    {
      "epoch": 0.014234875444839857,
      "grad_norm": 1.1549668455493816,
      "learning_rate": 1.4084507042253523e-05,
      "loss": 0.8305,
      "mean_token_accuracy": 0.7594800233840943,
      "step": 20
    },
    {
      "epoch": 0.017793594306049824,
      "grad_norm": 0.8084059187346242,
      "learning_rate": 1.7605633802816902e-05,
      "loss": 0.7989,
      "mean_token_accuracy": 0.7640575289726257,
      "step": 25
    },
    {
      "epoch": 0.021352313167259787,
      "grad_norm": 0.8267562843107086,
      "learning_rate": 2.112676056338028e-05,
      "loss": 0.7668,
      "mean_token_accuracy": 0.7727443218231201,
      "step": 30
    },
    {
      "epoch": 0.02491103202846975,
      "grad_norm": 0.7851378820161544,
      "learning_rate": 2.4647887323943664e-05,
      "loss": 0.7649,
      "mean_token_accuracy": 0.7709716081619262,
      "step": 35
    },
    {
      "epoch": 0.028469750889679714,
      "grad_norm": 0.7637956379243507,
      "learning_rate": 2.8169014084507046e-05,
      "loss": 0.7394,
      "mean_token_accuracy": 0.7772023797035217,
      "step": 40
    },
    {
      "epoch": 0.03202846975088968,
      "grad_norm": 0.7732620068824387,
      "learning_rate": 3.1690140845070426e-05,
      "loss": 0.7346,
      "mean_token_accuracy": 0.779318380355835,
      "step": 45
    },
    {
      "epoch": 0.03558718861209965,
      "grad_norm": 0.7696301616562734,
      "learning_rate": 3.5211267605633805e-05,
      "loss": 0.7206,
      "mean_token_accuracy": 0.7811890006065368,
      "step": 50
    },
    {
      "epoch": 0.03914590747330961,
      "grad_norm": 0.7965650840150478,
      "learning_rate": 3.8732394366197184e-05,
      "loss": 0.7099,
      "mean_token_accuracy": 0.7832624912261963,
      "step": 55
    },
    {
      "epoch": 0.042704626334519574,
      "grad_norm": 0.732913212165206,
      "learning_rate": 4.225352112676056e-05,
      "loss": 0.7365,
      "mean_token_accuracy": 0.778208339214325,
      "step": 60
    },
    {
      "epoch": 0.046263345195729534,
      "grad_norm": 0.840463903142822,
      "learning_rate": 4.577464788732395e-05,
      "loss": 0.7158,
      "mean_token_accuracy": 0.7836069345474244,
      "step": 65
    },
    {
      "epoch": 0.0498220640569395,
      "grad_norm": 0.7796733146584423,
      "learning_rate": 4.929577464788733e-05,
      "loss": 0.6948,
      "mean_token_accuracy": 0.7882483005523682,
      "step": 70
    },
    {
      "epoch": 0.05338078291814947,
      "grad_norm": 0.7826425373484522,
      "learning_rate": 4.999900170848507e-05,
      "loss": 0.7299,
      "mean_token_accuracy": 0.7795511484146118,
      "step": 75
    },
    {
      "epoch": 0.05693950177935943,
      "grad_norm": 0.7664471564553723,
      "learning_rate": 4.9994946301028825e-05,
      "loss": 0.7205,
      "mean_token_accuracy": 0.7806410670280457,
      "step": 80
    },
    {
      "epoch": 0.060498220640569395,
      "grad_norm": 0.6968982746230619,
      "learning_rate": 4.99877719462654e-05,
      "loss": 0.7217,
      "mean_token_accuracy": 0.7813021302223205,
      "step": 85
    },
    {
      "epoch": 0.06405693950177936,
      "grad_norm": 0.7093605930206083,
      "learning_rate": 4.997747963892645e-05,
      "loss": 0.7337,
      "mean_token_accuracy": 0.7769145965576172,
      "step": 90
    },
    {
      "epoch": 0.06761565836298933,
      "grad_norm": 0.7406894880280147,
      "learning_rate": 4.99640708060509e-05,
      "loss": 0.7337,
      "mean_token_accuracy": 0.7780750393867493,
      "step": 95
    },
    {
      "epoch": 0.0711743772241993,
      "grad_norm": 0.7318985545441932,
      "learning_rate": 4.994754730678713e-05,
      "loss": 0.727,
      "mean_token_accuracy": 0.7799831032752991,
      "step": 100
    },
    {
      "epoch": 0.07473309608540925,
      "grad_norm": 0.7639016380490891,
      "learning_rate": 4.992791143213523e-05,
      "loss": 0.7247,
      "mean_token_accuracy": 0.7811060786247254,
      "step": 105
    },
    {
      "epoch": 0.07829181494661921,
      "grad_norm": 0.8011798663105023,
      "learning_rate": 4.990516590462928e-05,
      "loss": 0.7161,
      "mean_token_accuracy": 0.7826329588890075,
      "step": 110
    },
    {
      "epoch": 0.08185053380782918,
      "grad_norm": 0.7616291847324664,
      "learning_rate": 4.9879313877959934e-05,
      "loss": 0.7172,
      "mean_token_accuracy": 0.7815984845161438,
      "step": 115
    },
    {
      "epoch": 0.08540925266903915,
      "grad_norm": 0.6970328489587734,
      "learning_rate": 4.985035893653713e-05,
      "loss": 0.6988,
      "mean_token_accuracy": 0.7884742975234985,
      "step": 120
    },
    {
      "epoch": 0.08896797153024912,
      "grad_norm": 0.6887071171016819,
      "learning_rate": 4.9818305094993096e-05,
      "loss": 0.7252,
      "mean_token_accuracy": 0.7797473907470703,
      "step": 125
    },
    {
      "epoch": 0.09252669039145907,
      "grad_norm": 0.782855999297394,
      "learning_rate": 4.978315679762574e-05,
      "loss": 0.7182,
      "mean_token_accuracy": 0.7811893105506897,
      "step": 130
    },
    {
      "epoch": 0.09608540925266904,
      "grad_norm": 0.6962527878171872,
      "learning_rate": 4.9744918917782446e-05,
      "loss": 0.7274,
      "mean_token_accuracy": 0.7792230010032654,
      "step": 135
    },
    {
      "epoch": 0.099644128113879,
      "grad_norm": 0.6966111313941732,
      "learning_rate": 4.9703596757184346e-05,
      "loss": 0.6958,
      "mean_token_accuracy": 0.78841632604599,
      "step": 140
    },
    {
      "epoch": 0.10320284697508897,
      "grad_norm": 0.6965295119485749,
      "learning_rate": 4.965919604519125e-05,
      "loss": 0.7158,
      "mean_token_accuracy": 0.782188069820404,
      "step": 145
    },
    {
      "epoch": 0.10676156583629894,
      "grad_norm": 0.7008145512070334,
      "learning_rate": 4.96117229380073e-05,
      "loss": 0.7311,
      "mean_token_accuracy": 0.7790884852409363,
      "step": 150
    },
    {
      "epoch": 0.1103202846975089,
      "grad_norm": 0.7210254246058475,
      "learning_rate": 4.956118401782734e-05,
      "loss": 0.6856,
      "mean_token_accuracy": 0.7896694540977478,
      "step": 155
    },
    {
      "epoch": 0.11387900355871886,
      "grad_norm": 0.7230055796086301,
      "learning_rate": 4.950758629192433e-05,
      "loss": 0.7205,
      "mean_token_accuracy": 0.7811832308769227,
      "step": 160
    },
    {
      "epoch": 0.11743772241992882,
      "grad_norm": 0.7177778907287135,
      "learning_rate": 4.945093719167778e-05,
      "loss": 0.7033,
      "mean_token_accuracy": 0.7855350494384765,
      "step": 165
    },
    {
      "epoch": 0.12099644128113879,
      "grad_norm": 0.6993140429254685,
      "learning_rate": 4.939124457154336e-05,
      "loss": 0.716,
      "mean_token_accuracy": 0.7823803782463074,
      "step": 170
    },
    {
      "epoch": 0.12455516014234876,
      "grad_norm": 0.749036299071456,
      "learning_rate": 4.932851670796389e-05,
      "loss": 0.6944,
      "mean_token_accuracy": 0.78707515001297,
      "step": 175
    },
    {
      "epoch": 0.12811387900355872,
      "grad_norm": 0.8003534588080977,
      "learning_rate": 4.926276229822181e-05,
      "loss": 0.7039,
      "mean_token_accuracy": 0.7855878114700318,
      "step": 180
    },
    {
      "epoch": 0.13167259786476868,
      "grad_norm": 0.6511982930622267,
      "learning_rate": 4.919399045923326e-05,
      "loss": 0.7046,
      "mean_token_accuracy": 0.7856501579284668,
      "step": 185
    },
    {
      "epoch": 0.13523131672597866,
      "grad_norm": 0.6631202589315934,
      "learning_rate": 4.9122210726284046e-05,
      "loss": 0.6918,
      "mean_token_accuracy": 0.789514684677124,
      "step": 190
    },
    {
      "epoch": 0.1387900355871886,
      "grad_norm": 0.6877007898563937,
      "learning_rate": 4.904743305170753e-05,
      "loss": 0.6973,
      "mean_token_accuracy": 0.7876662492752076,
      "step": 195
    },
    {
      "epoch": 0.1423487544483986,
      "grad_norm": 0.6594871153113472,
      "learning_rate": 4.896966780350477e-05,
      "loss": 0.7106,
      "mean_token_accuracy": 0.7843179941177368,
      "step": 200
    },
    {
      "epoch": 0.14590747330960854,
      "grad_norm": 0.7077337595180323,
      "learning_rate": 4.888892576390694e-05,
      "loss": 0.7124,
      "mean_token_accuracy": 0.7831673264503479,
      "step": 205
    },
    {
      "epoch": 0.1494661921708185,
      "grad_norm": 0.6734240121888417,
      "learning_rate": 4.88052181278804e-05,
      "loss": 0.6822,
      "mean_token_accuracy": 0.7912026405334472,
      "step": 210
    },
    {
      "epoch": 0.15302491103202848,
      "grad_norm": 0.6209145189032446,
      "learning_rate": 4.871855650157446e-05,
      "loss": 0.7311,
      "mean_token_accuracy": 0.779719889163971,
      "step": 215
    },
    {
      "epoch": 0.15658362989323843,
      "grad_norm": 0.6857572196473167,
      "learning_rate": 4.8628952900712265e-05,
      "loss": 0.7039,
      "mean_token_accuracy": 0.7850899338722229,
      "step": 220
    },
    {
      "epoch": 0.1601423487544484,
      "grad_norm": 0.721269601531556,
      "learning_rate": 4.853641974892466e-05,
      "loss": 0.6751,
      "mean_token_accuracy": 0.7923677682876586,
      "step": 225
    },
    {
      "epoch": 0.16370106761565836,
      "grad_norm": 0.6569686267689558,
      "learning_rate": 4.8440969876027794e-05,
      "loss": 0.6902,
      "mean_token_accuracy": 0.7885013699531556,
      "step": 230
    },
    {
      "epoch": 0.16725978647686832,
      "grad_norm": 0.652284057104664,
      "learning_rate": 4.834261651624412e-05,
      "loss": 0.7002,
      "mean_token_accuracy": 0.7859378337860108,
      "step": 235
    },
    {
      "epoch": 0.1708185053380783,
      "grad_norm": 0.6985712892311762,
      "learning_rate": 4.824137330636756e-05,
      "loss": 0.6937,
      "mean_token_accuracy": 0.7884337782859803,
      "step": 240
    },
    {
      "epoch": 0.17437722419928825,
      "grad_norm": 0.6981291268835246,
      "learning_rate": 4.8137254283872696e-05,
      "loss": 0.706,
      "mean_token_accuracy": 0.7852147102355957,
      "step": 245
    },
    {
      "epoch": 0.17793594306049823,
      "grad_norm": 0.6830081055108704,
      "learning_rate": 4.803027388496845e-05,
      "loss": 0.6813,
      "mean_token_accuracy": 0.7909272313117981,
      "step": 250
    },
    {
      "epoch": 0.18149466192170818,
      "grad_norm": 0.6763389483738134,
      "learning_rate": 4.7920446942596535e-05,
      "loss": 0.7104,
      "mean_token_accuracy": 0.7841034054756164,
      "step": 255
    },
    {
      "epoch": 0.18505338078291814,
      "grad_norm": 0.6758095067389677,
      "learning_rate": 4.780778868437481e-05,
      "loss": 0.6912,
      "mean_token_accuracy": 0.7872965097427368,
      "step": 260
    },
    {
      "epoch": 0.18861209964412812,
      "grad_norm": 0.6654497461754171,
      "learning_rate": 4.769231473048598e-05,
      "loss": 0.7035,
      "mean_token_accuracy": 0.7856454253196716,
      "step": 265
    },
    {
      "epoch": 0.19217081850533807,
      "grad_norm": 0.6692448464596932,
      "learning_rate": 4.757404109151184e-05,
      "loss": 0.6956,
      "mean_token_accuracy": 0.7881039142608642,
      "step": 270
    },
    {
      "epoch": 0.19572953736654805,
      "grad_norm": 0.6384295872220533,
      "learning_rate": 4.745298416621336e-05,
      "loss": 0.6941,
      "mean_token_accuracy": 0.7865496397018432,
      "step": 275
    },
    {
      "epoch": 0.199288256227758,
      "grad_norm": 0.6917569136927582,
      "learning_rate": 4.7329160739257035e-05,
      "loss": 0.6653,
      "mean_token_accuracy": 0.7947100758552551,
      "step": 280
    },
    {
      "epoch": 0.20284697508896798,
      "grad_norm": 0.6237053314088369,
      "learning_rate": 4.720258797888762e-05,
      "loss": 0.6954,
      "mean_token_accuracy": 0.787773597240448,
      "step": 285
    },
    {
      "epoch": 0.20640569395017794,
      "grad_norm": 0.6404989768357283,
      "learning_rate": 4.707328343454777e-05,
      "loss": 0.7143,
      "mean_token_accuracy": 0.7825374364852905,
      "step": 290
    },
    {
      "epoch": 0.2099644128113879,
      "grad_norm": 0.6609383386205755,
      "learning_rate": 4.694126503444479e-05,
      "loss": 0.7104,
      "mean_token_accuracy": 0.7829306364059448,
      "step": 295
    },
    {
      "epoch": 0.21352313167259787,
      "grad_norm": 0.6390075364325144,
      "learning_rate": 4.680655108306484e-05,
      "loss": 0.7068,
      "mean_token_accuracy": 0.7846204996109009,
      "step": 300
    },
    {
      "epoch": 0.21708185053380782,
      "grad_norm": 0.7320785611015472,
      "learning_rate": 4.666916025863505e-05,
      "loss": 0.6866,
      "mean_token_accuracy": 0.7891976118087769,
      "step": 305
    },
    {
      "epoch": 0.2206405693950178,
      "grad_norm": 0.6542388529582787,
      "learning_rate": 4.652911161053369e-05,
      "loss": 0.6684,
      "mean_token_accuracy": 0.7946648597717285,
      "step": 310
    },
    {
      "epoch": 0.22419928825622776,
      "grad_norm": 0.6387809858585279,
      "learning_rate": 4.6386424556649046e-05,
      "loss": 0.7067,
      "mean_token_accuracy": 0.784406590461731,
      "step": 315
    },
    {
      "epoch": 0.2277580071174377,
      "grad_norm": 0.6511518481529157,
      "learning_rate": 4.624111888068704e-05,
      "loss": 0.6669,
      "mean_token_accuracy": 0.7934553146362304,
      "step": 320
    },
    {
      "epoch": 0.2313167259786477,
      "grad_norm": 0.7857269281531926,
      "learning_rate": 4.6093214729428236e-05,
      "loss": 0.6977,
      "mean_token_accuracy": 0.7871865391731262,
      "step": 325
    },
    {
      "epoch": 0.23487544483985764,
      "grad_norm": 0.708401390320286,
      "learning_rate": 4.5942732609934436e-05,
      "loss": 0.6917,
      "mean_token_accuracy": 0.7883163809776306,
      "step": 330
    },
    {
      "epoch": 0.23843416370106763,
      "grad_norm": 0.6537859721831119,
      "learning_rate": 4.57896933867054e-05,
      "loss": 0.7016,
      "mean_token_accuracy": 0.785762631893158,
      "step": 335
    },
    {
      "epoch": 0.24199288256227758,
      "grad_norm": 0.6322721246524066,
      "learning_rate": 4.563411827878591e-05,
      "loss": 0.6591,
      "mean_token_accuracy": 0.7976097822189331,
      "step": 340
    },
    {
      "epoch": 0.24555160142348753,
      "grad_norm": 0.613702823629008,
      "learning_rate": 4.5476028856823774e-05,
      "loss": 0.6831,
      "mean_token_accuracy": 0.7909620523452758,
      "step": 345
    },
    {
      "epoch": 0.2491103202846975,
      "grad_norm": 0.6470379557892744,
      "learning_rate": 4.531544704007899e-05,
      "loss": 0.6877,
      "mean_token_accuracy": 0.7888366222381592,
      "step": 350
    },
    {
      "epoch": 0.2526690391459075,
      "grad_norm": 0.6349334832549038,
      "learning_rate": 4.5152395093384655e-05,
      "loss": 0.6855,
      "mean_token_accuracy": 0.7899898767471314,
      "step": 355
    },
    {
      "epoch": 0.25622775800711745,
      "grad_norm": 0.6462491719466713,
      "learning_rate": 4.4986895624059934e-05,
      "loss": 0.6932,
      "mean_token_accuracy": 0.7873799800872803,
      "step": 360
    },
    {
      "epoch": 0.2597864768683274,
      "grad_norm": 0.630603740544669,
      "learning_rate": 4.481897157877545e-05,
      "loss": 0.709,
      "mean_token_accuracy": 0.7845431327819824,
      "step": 365
    },
    {
      "epoch": 0.26334519572953735,
      "grad_norm": 0.6086861709084705,
      "learning_rate": 4.464864624037182e-05,
      "loss": 0.6825,
      "mean_token_accuracy": 0.7913990497589112,
      "step": 370
    },
    {
      "epoch": 0.2669039145907473,
      "grad_norm": 1.2548196206715339,
      "learning_rate": 4.447594322463137e-05,
      "loss": 0.6954,
      "mean_token_accuracy": 0.7860358953475952,
      "step": 375
    },
    {
      "epoch": 0.2704626334519573,
      "grad_norm": 0.7181263405100091,
      "learning_rate": 4.4300886477003836e-05,
      "loss": 0.6813,
      "mean_token_accuracy": 0.7917158126831054,
      "step": 380
    },
    {
      "epoch": 0.27402135231316727,
      "grad_norm": 0.6711130910236095,
      "learning_rate": 4.412350026928628e-05,
      "loss": 0.6896,
      "mean_token_accuracy": 0.7883881092071533,
      "step": 385
    },
    {
      "epoch": 0.2775800711743772,
      "grad_norm": 0.6035405028151128,
      "learning_rate": 4.3943809196257794e-05,
      "loss": 0.6848,
      "mean_token_accuracy": 0.7895100355148316,
      "step": 390
    },
    {
      "epoch": 0.28113879003558717,
      "grad_norm": 0.5844919307530534,
      "learning_rate": 4.37618381722694e-05,
      "loss": 0.6668,
      "mean_token_accuracy": 0.7936931371688842,
      "step": 395
    },
    {
      "epoch": 0.2846975088967972,
      "grad_norm": 0.6492460475437084,
      "learning_rate": 4.357761242778965e-05,
      "loss": 0.6684,
      "mean_token_accuracy": 0.7950313925743103,
      "step": 400
    },
    {
      "epoch": 0.2846975088967972,
      "step": 400,
      "total_flos": 38010460569600.0,
      "train_loss": 0.0,
      "train_runtime": 2.1351,
      "train_samples_per_second": 2851.346,
      "train_steps_per_second": 44.962
    }
  ],
  "logging_steps": 5,
  "max_steps": 96,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 38010460569600.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}