{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 210,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.1651801258325576,
      "epoch": 0.04784688995215311,
      "grad_norm": 4.052286148071289,
      "learning_rate": 9.80952380952381e-05,
      "loss": 2.560974884033203,
      "mean_token_accuracy": 0.5812613397836686,
      "num_tokens": 22163.0,
      "step": 5
    },
    {
      "entropy": 1.7820561587810517,
      "epoch": 0.09569377990430622,
      "grad_norm": 3.3570611476898193,
      "learning_rate": 9.571428571428573e-05,
      "loss": 1.5557975769042969,
      "mean_token_accuracy": 0.7120864883065223,
      "num_tokens": 44774.0,
      "step": 10
    },
    {
      "entropy": 0.9664318569004535,
      "epoch": 0.14354066985645933,
      "grad_norm": 2.2438340187072754,
      "learning_rate": 9.333333333333334e-05,
      "loss": 1.0039640426635743,
      "mean_token_accuracy": 0.8314489215612412,
      "num_tokens": 68554.0,
      "step": 15
    },
    {
      "entropy": 0.7952521093189716,
      "epoch": 0.19138755980861244,
      "grad_norm": 1.4970792531967163,
      "learning_rate": 9.095238095238096e-05,
      "loss": 0.9054213523864746,
      "mean_token_accuracy": 0.8527463525533676,
      "num_tokens": 92672.0,
      "step": 20
    },
    {
      "entropy": 0.7521916493773461,
      "epoch": 0.23923444976076555,
      "grad_norm": 1.1931730508804321,
      "learning_rate": 8.857142857142857e-05,
      "loss": 0.8049167633056641,
      "mean_token_accuracy": 0.8651137307286263,
      "num_tokens": 115556.0,
      "step": 25
    },
    {
      "entropy": 0.8046777091920376,
      "epoch": 0.28708133971291866,
      "grad_norm": 1.1074719429016113,
      "learning_rate": 8.61904761904762e-05,
      "loss": 0.8548135757446289,
      "mean_token_accuracy": 0.8603784069418907,
      "num_tokens": 140637.0,
      "step": 30
    },
    {
      "entropy": 0.6400977578014135,
      "epoch": 0.3349282296650718,
      "grad_norm": 0.9381627440452576,
      "learning_rate": 8.380952380952382e-05,
      "loss": 0.6987390518188477,
      "mean_token_accuracy": 0.8840002715587616,
      "num_tokens": 164217.0,
      "step": 35
    },
    {
      "entropy": 0.6654842033982277,
      "epoch": 0.3827751196172249,
      "grad_norm": 2.1283178329467773,
      "learning_rate": 8.142857142857143e-05,
      "loss": 0.7857039928436279,
      "mean_token_accuracy": 0.8724030137062073,
      "num_tokens": 186852.0,
      "step": 40
    },
    {
      "entropy": 0.619146254658699,
      "epoch": 0.430622009569378,
      "grad_norm": 0.8456487059593201,
      "learning_rate": 7.904761904761905e-05,
      "loss": 0.6680184364318847,
      "mean_token_accuracy": 0.8887932941317558,
      "num_tokens": 210073.0,
      "step": 45
    },
    {
      "entropy": 0.6058806985616684,
      "epoch": 0.4784688995215311,
      "grad_norm": 0.8580911159515381,
      "learning_rate": 7.666666666666667e-05,
      "loss": 0.6658339977264405,
      "mean_token_accuracy": 0.8919811978936195,
      "num_tokens": 233395.0,
      "step": 50
    },
    {
      "entropy": 0.6354636650532484,
      "epoch": 0.5263157894736842,
      "grad_norm": 0.9746028780937195,
      "learning_rate": 7.428571428571429e-05,
      "loss": 0.728534460067749,
      "mean_token_accuracy": 0.8858045786619186,
      "num_tokens": 256677.0,
      "step": 55
    },
    {
      "entropy": 0.5936117857694626,
      "epoch": 0.5741626794258373,
      "grad_norm": 0.9922609925270081,
      "learning_rate": 7.19047619047619e-05,
      "loss": 0.6770713806152344,
      "mean_token_accuracy": 0.8887649178504944,
      "num_tokens": 278351.0,
      "step": 60
    },
    {
      "entropy": 0.6688867088407278,
      "epoch": 0.6220095693779905,
      "grad_norm": 0.9844464659690857,
      "learning_rate": 6.952380952380952e-05,
      "loss": 0.7745152950286865,
      "mean_token_accuracy": 0.8777409210801125,
      "num_tokens": 303271.0,
      "step": 65
    },
    {
      "entropy": 0.7457825832068921,
      "epoch": 0.6698564593301436,
      "grad_norm": 0.9128448367118835,
      "learning_rate": 6.714285714285714e-05,
      "loss": 0.8470640182495117,
      "mean_token_accuracy": 0.8637880578637123,
      "num_tokens": 328315.0,
      "step": 70
    },
    {
      "entropy": 0.6116038627922535,
      "epoch": 0.7177033492822966,
      "grad_norm": 0.9624145030975342,
      "learning_rate": 6.476190476190477e-05,
      "loss": 0.6843190670013428,
      "mean_token_accuracy": 0.8896616101264954,
      "num_tokens": 351963.0,
      "step": 75
    },
    {
      "entropy": 0.622330765798688,
      "epoch": 0.7655502392344498,
      "grad_norm": 0.9209601879119873,
      "learning_rate": 6.238095238095239e-05,
      "loss": 0.6767851829528808,
      "mean_token_accuracy": 0.8867631480097771,
      "num_tokens": 375023.0,
      "step": 80
    },
    {
      "entropy": 0.6198485180735588,
      "epoch": 0.8133971291866029,
      "grad_norm": 0.946159303188324,
      "learning_rate": 6e-05,
      "loss": 0.6652565956115722,
      "mean_token_accuracy": 0.8853679791092872,
      "num_tokens": 399277.0,
      "step": 85
    },
    {
      "entropy": 0.5564446035772562,
      "epoch": 0.861244019138756,
      "grad_norm": 0.8137181401252747,
      "learning_rate": 5.761904761904762e-05,
      "loss": 0.6248233795166016,
      "mean_token_accuracy": 0.8972864270210266,
      "num_tokens": 421249.0,
      "step": 90
    },
    {
      "entropy": 0.5795138332992792,
      "epoch": 0.9090909090909091,
      "grad_norm": 0.851652204990387,
      "learning_rate": 5.5238095238095244e-05,
      "loss": 0.6658082008361816,
      "mean_token_accuracy": 0.8966752380132675,
      "num_tokens": 444070.0,
      "step": 95
    },
    {
      "entropy": 0.6267214026302099,
      "epoch": 0.9569377990430622,
      "grad_norm": 0.8740034103393555,
      "learning_rate": 5.285714285714286e-05,
      "loss": 0.7174222946166993,
      "mean_token_accuracy": 0.880531644821167,
      "num_tokens": 467253.0,
      "step": 100
    },
    {
      "entropy": 0.6104649793770578,
      "epoch": 1.0,
      "grad_norm": 1.397324800491333,
      "learning_rate": 5.047619047619048e-05,
      "loss": 0.723299789428711,
      "mean_token_accuracy": 0.8877596159776052,
      "num_tokens": 489018.0,
      "step": 105
    },
    {
      "entropy": 0.6409125056117773,
      "epoch": 1.0478468899521531,
      "grad_norm": 0.7727960348129272,
      "learning_rate": 4.80952380952381e-05,
      "loss": 0.646695899963379,
      "mean_token_accuracy": 0.8852975755929947,
      "num_tokens": 513248.0,
      "step": 110
    },
    {
      "entropy": 0.5359640445560216,
      "epoch": 1.0956937799043063,
      "grad_norm": 0.7002193927764893,
      "learning_rate": 4.5714285714285716e-05,
      "loss": 0.5828539848327636,
      "mean_token_accuracy": 0.9033631831407547,
      "num_tokens": 536083.0,
      "step": 115
    },
    {
      "entropy": 0.5877869483083487,
      "epoch": 1.1435406698564594,
      "grad_norm": 0.8519774079322815,
      "learning_rate": 4.3333333333333334e-05,
      "loss": 0.6564444065093994,
      "mean_token_accuracy": 0.8940910667181015,
      "num_tokens": 559396.0,
      "step": 120
    },
    {
      "entropy": 0.5784575771540403,
      "epoch": 1.1913875598086126,
      "grad_norm": 0.8621901273727417,
      "learning_rate": 4.095238095238095e-05,
      "loss": 0.6363758087158203,
      "mean_token_accuracy": 0.8952302411198616,
      "num_tokens": 582746.0,
      "step": 125
    },
    {
      "entropy": 0.6027569387108087,
      "epoch": 1.2392344497607655,
      "grad_norm": 0.9358822703361511,
      "learning_rate": 3.857142857142858e-05,
      "loss": 0.6765194416046143,
      "mean_token_accuracy": 0.8874293357133866,
      "num_tokens": 606214.0,
      "step": 130
    },
    {
      "entropy": 0.611118633300066,
      "epoch": 1.2870813397129186,
      "grad_norm": 0.8267807960510254,
      "learning_rate": 3.619047619047619e-05,
      "loss": 0.6723567008972168,
      "mean_token_accuracy": 0.8883729502558708,
      "num_tokens": 630076.0,
      "step": 135
    },
    {
      "entropy": 0.5769705072045326,
      "epoch": 1.3349282296650717,
      "grad_norm": 0.7842361927032471,
      "learning_rate": 3.380952380952381e-05,
      "loss": 0.6243512630462646,
      "mean_token_accuracy": 0.8933283373713493,
      "num_tokens": 653859.0,
      "step": 140
    },
    {
      "entropy": 0.6102541331201792,
      "epoch": 1.3827751196172249,
      "grad_norm": 0.8129627704620361,
      "learning_rate": 3.142857142857143e-05,
      "loss": 0.6874077796936036,
      "mean_token_accuracy": 0.8832434669137001,
      "num_tokens": 677327.0,
      "step": 145
    },
    {
      "entropy": 0.6099541481584311,
      "epoch": 1.430622009569378,
      "grad_norm": 0.7526546716690063,
      "learning_rate": 2.9047619047619052e-05,
      "loss": 0.6641890048980713,
      "mean_token_accuracy": 0.8834606483578682,
      "num_tokens": 701682.0,
      "step": 150
    },
    {
      "entropy": 0.6001380123198032,
      "epoch": 1.4784688995215312,
      "grad_norm": 0.8635663986206055,
      "learning_rate": 2.6666666666666667e-05,
      "loss": 0.6789334774017334,
      "mean_token_accuracy": 0.8867474034428596,
      "num_tokens": 725375.0,
      "step": 155
    },
    {
      "entropy": 0.6042792610824108,
      "epoch": 1.526315789473684,
      "grad_norm": 0.8883793354034424,
      "learning_rate": 2.4285714285714288e-05,
      "loss": 0.6333177089691162,
      "mean_token_accuracy": 0.8881407305598259,
      "num_tokens": 748854.0,
      "step": 160
    },
    {
      "entropy": 0.524115451797843,
      "epoch": 1.5741626794258372,
      "grad_norm": 0.7244672775268555,
      "learning_rate": 2.1904761904761906e-05,
      "loss": 0.5796619892120362,
      "mean_token_accuracy": 0.9032144501805306,
      "num_tokens": 771536.0,
      "step": 165
    },
    {
      "entropy": 0.5471004392951727,
      "epoch": 1.6220095693779903,
      "grad_norm": 0.8835629224777222,
      "learning_rate": 1.9523809523809524e-05,
      "loss": 0.6003574371337891,
      "mean_token_accuracy": 0.8971484303474426,
      "num_tokens": 793900.0,
      "step": 170
    },
    {
      "entropy": 0.6230863776057959,
      "epoch": 1.6698564593301435,
      "grad_norm": 0.8581238389015198,
      "learning_rate": 1.7142857142857145e-05,
      "loss": 0.7287740707397461,
      "mean_token_accuracy": 0.8850353598594666,
      "num_tokens": 818273.0,
      "step": 175
    },
    {
      "entropy": 0.5712798546999693,
      "epoch": 1.7177033492822966,
      "grad_norm": 0.8643863797187805,
      "learning_rate": 1.4761904761904763e-05,
      "loss": 0.6351244926452637,
      "mean_token_accuracy": 0.8935175597667694,
      "num_tokens": 841778.0,
      "step": 180
    },
    {
      "entropy": 0.5254735369235277,
      "epoch": 1.7655502392344498,
      "grad_norm": 0.9475647807121277,
      "learning_rate": 1.2380952380952381e-05,
      "loss": 0.5964117527008057,
      "mean_token_accuracy": 0.9012993037700653,
      "num_tokens": 864591.0,
      "step": 185
    },
    {
      "entropy": 0.5567632585763931,
      "epoch": 1.813397129186603,
      "grad_norm": 0.7951871156692505,
      "learning_rate": 1e-05,
      "loss": 0.5931246280670166,
      "mean_token_accuracy": 0.897057680785656,
      "num_tokens": 887876.0,
      "step": 190
    },
    {
      "entropy": 0.6068938117474317,
      "epoch": 1.861244019138756,
      "grad_norm": 0.8280668258666992,
      "learning_rate": 7.6190476190476205e-06,
      "loss": 0.676881980895996,
      "mean_token_accuracy": 0.8875841274857521,
      "num_tokens": 912470.0,
      "step": 195
    },
    {
      "entropy": 0.49752707965672016,
      "epoch": 1.9090909090909092,
      "grad_norm": 0.8685581684112549,
      "learning_rate": 5.2380952380952384e-06,
      "loss": 0.5316107749938965,
      "mean_token_accuracy": 0.9095863461494446,
      "num_tokens": 934358.0,
      "step": 200
    },
    {
      "entropy": 0.5345557902008296,
      "epoch": 1.9569377990430623,
      "grad_norm": 0.9313185214996338,
      "learning_rate": 2.8571428571428573e-06,
      "loss": 0.5797445774078369,
      "mean_token_accuracy": 0.9045627474784851,
      "num_tokens": 956852.0,
      "step": 205
    },
    {
      "entropy": 0.5808272701170709,
      "epoch": 2.0,
      "grad_norm": 1.4462640285491943,
      "learning_rate": 4.761904761904763e-07,
      "loss": 0.6747049331665039,
      "mean_token_accuracy": 0.893244668841362,
      "num_tokens": 978036.0,
      "step": 210
    }
  ],
  "logging_steps": 5,
  "max_steps": 210,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 2960533186942464.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}