{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20743525751142514,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005185881437785629,
      "grad_norm": 247.97032165527344,
      "learning_rate": 2.5499999999999996e-05,
      "loss": 145.23812255859374,
      "original_ce_loss": 9.0141,
      "step": 10
    },
    {
      "epoch": 0.010371762875571258,
      "grad_norm": 248.38844299316406,
      "learning_rate": 6.8e-05,
      "loss": 144.60938720703126,
      "original_ce_loss": 8.9749,
      "step": 20
    },
    {
      "epoch": 0.015557644313356886,
      "grad_norm": 385.3697204589844,
      "learning_rate": 0.00010625,
      "loss": 141.92376708984375,
      "original_ce_loss": 8.8072,
      "step": 30
    },
    {
      "epoch": 0.020743525751142515,
      "grad_norm": 250.706787109375,
      "learning_rate": 0.00014450000000000002,
      "loss": 129.28629150390626,
      "original_ce_loss": 8.0175,
      "step": 40
    },
    {
      "epoch": 0.025929407188928142,
      "grad_norm": 37.78219985961914,
      "learning_rate": 0.00018275,
      "loss": 118.50413818359375,
      "original_ce_loss": 7.3439,
      "step": 50
    },
    {
      "epoch": 0.031115288626713773,
      "grad_norm": 35.401676177978516,
      "learning_rate": 0.00022525,
      "loss": 112.6171630859375,
      "original_ce_loss": 6.9763,
      "step": 60
    },
    {
      "epoch": 0.0363011700644994,
      "grad_norm": 155.93934631347656,
      "learning_rate": 0.00026775,
      "loss": 105.485986328125,
      "original_ce_loss": 6.5312,
      "step": 70
    },
    {
      "epoch": 0.04148705150228503,
      "grad_norm": 17.077312469482422,
      "learning_rate": 0.00031025,
      "loss": 102.00914916992187,
      "original_ce_loss": 6.3146,
      "step": 80
    },
    {
      "epoch": 0.04667293294007066,
      "grad_norm": 12.143115997314453,
      "learning_rate": 0.00035275,
      "loss": 101.21661376953125,
      "original_ce_loss": 6.2657,
      "step": 90
    },
    {
      "epoch": 0.051858814377856284,
      "grad_norm": 212.8907928466797,
      "learning_rate": 0.00039525,
      "loss": 101.29624633789062,
      "original_ce_loss": 6.2715,
      "step": 100
    },
    {
      "epoch": 0.057044695815641915,
      "grad_norm": 379.0343933105469,
      "learning_rate": 0.00042499874610596206,
      "loss": 100.54356689453125,
      "original_ce_loss": 6.225,
      "step": 110
    },
    {
      "epoch": 0.062230577253427545,
      "grad_norm": 119.57896423339844,
      "learning_rate": 0.000424962070796437,
      "loss": 99.99188232421875,
      "original_ce_loss": 6.1911,
      "step": 120
    },
    {
      "epoch": 0.06741645869121317,
      "grad_norm": 176.70579528808594,
      "learning_rate": 0.0004248746228038075,
      "loss": 99.34671630859376,
      "original_ce_loss": 6.1514,
      "step": 130
    },
    {
      "epoch": 0.0726023401289988,
      "grad_norm": 59.76472473144531,
      "learning_rate": 0.0004247179359861924,
      "loss": 99.34248046875,
      "original_ce_loss": 6.1519,
      "step": 140
    },
    {
      "epoch": 0.07778822156678443,
      "grad_norm": 293.2443542480469,
      "learning_rate": 0.0004245475044883495,
      "loss": 99.488525390625,
      "original_ce_loss": 6.1615,
      "step": 150
    },
    {
      "epoch": 0.08297410300457006,
      "grad_norm": 714.7462158203125,
      "learning_rate": 0.0004243079123379424,
      "loss": 99.61160278320312,
      "original_ce_loss": 6.1695,
      "step": 160
    },
    {
      "epoch": 0.08815998444235569,
      "grad_norm": 886.433837890625,
      "learning_rate": 0.0004239823368702875,
      "loss": 99.01062622070313,
      "original_ce_loss": 6.1322,
      "step": 170
    },
    {
      "epoch": 0.09334586588014132,
      "grad_norm": 200.77587890625,
      "learning_rate": 0.0004235943684185158,
      "loss": 98.5961181640625,
      "original_ce_loss": 6.1064,
      "step": 180
    },
    {
      "epoch": 0.09853174731792694,
      "grad_norm": 48.907493591308594,
      "learning_rate": 0.0004231441214437677,
      "loss": 98.40054931640626,
      "original_ce_loss": 6.0944,
      "step": 190
    },
    {
      "epoch": 0.10371762875571257,
      "grad_norm": 78.08061981201172,
      "learning_rate": 0.00042263172878102487,
      "loss": 98.215380859375,
      "original_ce_loss": 6.0832,
      "step": 200
    },
    {
      "epoch": 0.1089035101934982,
      "grad_norm": 123.57373046875,
      "learning_rate": 0.00042205734159992043,
      "loss": 98.25463256835937,
      "original_ce_loss": 6.0864,
      "step": 210
    },
    {
      "epoch": 0.11408939163128383,
      "grad_norm": 394.4930419921875,
      "learning_rate": 0.0004214875275050289,
      "loss": 98.41907348632813,
      "original_ce_loss": 6.0973,
      "step": 220
    },
    {
      "epoch": 0.11927527306906946,
      "grad_norm": NaN,
      "learning_rate": 0.00042086777104881595,
      "loss": 98.69362182617188,
      "original_ce_loss": 6.115,
      "step": 230
    },
    {
      "epoch": 0.12446115450685509,
      "grad_norm": 35506.96484375,
      "learning_rate": 0.0004202750689631276,
      "loss": 99.12110595703125,
      "original_ce_loss": 6.1421,
      "step": 240
    },
    {
      "epoch": 0.12964703594464072,
      "grad_norm": 11162.1083984375,
      "learning_rate": 0.00041964313501643334,
      "loss": 99.37658081054687,
      "original_ce_loss": 6.1583,
      "step": 250
    },
    {
      "epoch": 0.13483291738242634,
      "grad_norm": 1199.7325439453125,
      "learning_rate": 0.00041879823026024296,
      "loss": 99.02756958007812,
      "original_ce_loss": 6.1366,
      "step": 260
    },
    {
      "epoch": 0.14001879882021198,
      "grad_norm": 33510.7578125,
      "learning_rate": 0.0004178924619709821,
      "loss": 98.757275390625,
      "original_ce_loss": 6.1199,
      "step": 270
    },
    {
      "epoch": 0.1452046802579976,
      "grad_norm": NaN,
      "learning_rate": 0.0004170254526824216,
      "loss": 98.8090087890625,
      "original_ce_loss": 6.1234,
      "step": 280
    },
    {
      "epoch": 0.15039056169578324,
      "grad_norm": 7444.04150390625,
      "learning_rate": 0.0004161095673476243,
      "loss": 100.40501098632812,
      "original_ce_loss": 6.2235,
      "step": 290
    },
    {
      "epoch": 0.15557644313356886,
      "grad_norm": 5086.20166015625,
      "learning_rate": 0.0004151450248383901,
      "loss": 102.10885009765624,
      "original_ce_loss": 6.3303,
      "step": 300
    },
    {
      "epoch": 0.16076232457135448,
      "grad_norm": 2572.272216796875,
      "learning_rate": 0.00041401652462566313,
      "loss": 101.41973876953125,
      "original_ce_loss": 6.2876,
      "step": 310
    },
    {
      "epoch": 0.16594820600914012,
      "grad_norm": NaN,
      "learning_rate": 0.00041282857161178824,
      "loss": 101.670556640625,
      "original_ce_loss": 6.3039,
      "step": 320
    },
    {
      "epoch": 0.17113408744692574,
      "grad_norm": 25727.53515625,
      "learning_rate": 0.0004118356381184281,
      "loss": 103.318212890625,
      "original_ce_loss": 6.4075,
      "step": 330
    },
    {
      "epoch": 0.17631996888471138,
      "grad_norm": 35157.0859375,
      "learning_rate": 0.00041054156498848937,
      "loss": 110.7964599609375,
      "original_ce_loss": 6.8758,
      "step": 340
    },
    {
      "epoch": 0.181505850322497,
      "grad_norm": 112891.84375,
      "learning_rate": 0.0004091890642640685,
      "loss": 126.60723876953125,
      "original_ce_loss": 7.8646,
      "step": 350
    },
    {
      "epoch": 0.18669173176028264,
      "grad_norm": 3006.623779296875,
      "learning_rate": 0.000407778534969299,
      "loss": 119.78572998046874,
      "original_ce_loss": 7.4386,
      "step": 360
    },
    {
      "epoch": 0.19187761319806826,
      "grad_norm": 2020.123779296875,
      "learning_rate": 0.0004063103932483052,
      "loss": 114.20302734375,
      "original_ce_loss": 7.0899,
      "step": 370
    },
    {
      "epoch": 0.19706349463585388,
      "grad_norm": 9304.6865234375,
      "learning_rate": 0.0004047850722424284,
      "loss": 108.25167236328124,
      "original_ce_loss": 6.7183,
      "step": 380
    },
    {
      "epoch": 0.20224937607363952,
      "grad_norm": 6329.39794921875,
      "learning_rate": 0.0004032030219624389,
      "loss": 105.06466064453124,
      "original_ce_loss": 6.5199,
      "step": 390
    },
    {
      "epoch": 0.20743525751142514,
      "grad_norm": 852.490478515625,
      "learning_rate": 0.0004015647091557703,
      "loss": 105.2643798828125,
      "original_ce_loss": 6.5331,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 1929,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4249361190838272.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}