{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 228,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 3.949260765314102,
      "epoch": 0.06611570247933884,
      "grad_norm": 0.0,
      "learning_rate": 1e-05,
      "loss": 233.2270751953125,
      "mean_token_accuracy": 0.026110622729174793,
      "num_tokens": 30341.0,
      "step": 5
    },
    {
      "entropy": 3.926559180021286,
      "epoch": 0.1322314049586777,
      "grad_norm": 0.0,
      "learning_rate": 2.25e-05,
      "loss": 233.90556640625,
      "mean_token_accuracy": 0.025600465817842633,
      "num_tokens": 60184.0,
      "step": 10
    },
    {
      "entropy": 3.9399050384759904,
      "epoch": 0.19834710743801653,
      "grad_norm": 0.0,
      "learning_rate": 3.5e-05,
      "loss": 233.5798828125,
      "mean_token_accuracy": 0.026415328145958483,
      "num_tokens": 90535.0,
      "step": 15
    },
    {
      "entropy": 3.9297859936952593,
      "epoch": 0.2644628099173554,
      "grad_norm": 0.0,
      "learning_rate": 4.75e-05,
      "loss": 233.126611328125,
      "mean_token_accuracy": 0.02820728103397414,
      "num_tokens": 116077.0,
      "step": 20
    },
    {
      "entropy": 3.962813687324524,
      "epoch": 0.3305785123966942,
      "grad_norm": 0.0,
      "learning_rate": 4.9038461538461536e-05,
      "loss": 232.579443359375,
      "mean_token_accuracy": 0.026059218565933406,
      "num_tokens": 147898.0,
      "step": 25
    },
    {
      "entropy": 3.959607166051865,
      "epoch": 0.39669421487603307,
      "grad_norm": 0.0,
      "learning_rate": 4.783653846153847e-05,
      "loss": 233.8760986328125,
      "mean_token_accuracy": 0.02393958643078804,
      "num_tokens": 179807.0,
      "step": 30
    },
    {
      "entropy": 3.942630410194397,
      "epoch": 0.4628099173553719,
      "grad_norm": 0.0,
      "learning_rate": 4.6634615384615384e-05,
      "loss": 232.322216796875,
      "mean_token_accuracy": 0.026402945548761637,
      "num_tokens": 207991.0,
      "step": 35
    },
    {
      "entropy": 3.926275482773781,
      "epoch": 0.5289256198347108,
      "grad_norm": 0.0,
      "learning_rate": 4.543269230769231e-05,
      "loss": 232.013916015625,
      "mean_token_accuracy": 0.02679328005760908,
      "num_tokens": 236639.0,
      "step": 40
    },
    {
      "entropy": 3.9455344051122667,
      "epoch": 0.5950413223140496,
      "grad_norm": 0.0,
      "learning_rate": 4.423076923076923e-05,
      "loss": 233.5448974609375,
      "mean_token_accuracy": 0.028373240097425877,
      "num_tokens": 263099.0,
      "step": 45
    },
    {
      "entropy": 3.938176819682121,
      "epoch": 0.6611570247933884,
      "grad_norm": 0.0,
      "learning_rate": 4.302884615384616e-05,
      "loss": 231.9595703125,
      "mean_token_accuracy": 0.024394837359432132,
      "num_tokens": 294450.0,
      "step": 50
    },
    {
      "entropy": 3.945117491483688,
      "epoch": 0.7272727272727273,
      "grad_norm": 0.0,
      "learning_rate": 4.182692307692308e-05,
      "loss": 234.357421875,
      "mean_token_accuracy": 0.026401228457689285,
      "num_tokens": 323322.0,
      "step": 55
    },
    {
      "entropy": 3.958406376838684,
      "epoch": 0.7933884297520661,
      "grad_norm": 0.0,
      "learning_rate": 4.0625000000000005e-05,
      "loss": 234.3664306640625,
      "mean_token_accuracy": 0.02587177858222276,
      "num_tokens": 353600.0,
      "step": 60
    },
    {
      "entropy": 3.9519979149103164,
      "epoch": 0.859504132231405,
      "grad_norm": 0.0,
      "learning_rate": 3.942307692307692e-05,
      "loss": 232.3470947265625,
      "mean_token_accuracy": 0.027900667279027402,
      "num_tokens": 382910.0,
      "step": 65
    },
    {
      "entropy": 3.937412214279175,
      "epoch": 0.9256198347107438,
      "grad_norm": 0.0,
      "learning_rate": 3.8221153846153846e-05,
      "loss": 230.767626953125,
      "mean_token_accuracy": 0.028427720058243722,
      "num_tokens": 410956.0,
      "step": 70
    },
    {
      "entropy": 3.942065638303757,
      "epoch": 0.9917355371900827,
      "grad_norm": 0.0,
      "learning_rate": 3.701923076923077e-05,
      "loss": 233.8431396484375,
      "mean_token_accuracy": 0.02679448336130008,
      "num_tokens": 436905.0,
      "step": 75
    },
    {
      "entropy": 3.9374109313294694,
      "epoch": 1.052892561983471,
      "grad_norm": 0.0,
      "learning_rate": 3.5817307692307695e-05,
      "loss": 215.2375,
      "mean_token_accuracy": 0.02448466032542087,
      "num_tokens": 465647.0,
      "step": 80
    },
    {
      "entropy": 3.953054502606392,
      "epoch": 1.1190082644628099,
      "grad_norm": 0.0,
      "learning_rate": 3.461538461538462e-05,
      "loss": 234.6711181640625,
      "mean_token_accuracy": 0.02631221548654139,
      "num_tokens": 492908.0,
      "step": 85
    },
    {
      "entropy": 3.94879230260849,
      "epoch": 1.1851239669421487,
      "grad_norm": 0.0,
      "learning_rate": 3.3413461538461536e-05,
      "loss": 230.2646240234375,
      "mean_token_accuracy": 0.026181722863111646,
      "num_tokens": 521382.0,
      "step": 90
    },
    {
      "entropy": 3.936227795481682,
      "epoch": 1.2512396694214876,
      "grad_norm": 0.0,
      "learning_rate": 3.221153846153847e-05,
      "loss": 232.071826171875,
      "mean_token_accuracy": 0.025906398333609103,
      "num_tokens": 549041.0,
      "step": 95
    },
    {
      "entropy": 3.930509549379349,
      "epoch": 1.3173553719008264,
      "grad_norm": 0.0,
      "learning_rate": 3.1009615384615384e-05,
      "loss": 232.701025390625,
      "mean_token_accuracy": 0.027634602575562894,
      "num_tokens": 578290.0,
      "step": 100
    },
    {
      "entropy": 3.9412417501211165,
      "epoch": 1.3834710743801653,
      "grad_norm": 0.0,
      "learning_rate": 2.9807692307692308e-05,
      "loss": 233.9791259765625,
      "mean_token_accuracy": 0.026698815589770674,
      "num_tokens": 607499.0,
      "step": 105
    },
    {
      "entropy": 3.957675591111183,
      "epoch": 1.449586776859504,
      "grad_norm": 0.0,
      "learning_rate": 2.860576923076923e-05,
      "loss": 232.7337158203125,
      "mean_token_accuracy": 0.026053250976838173,
      "num_tokens": 637795.0,
      "step": 110
    },
    {
      "entropy": 3.9587122440338134,
      "epoch": 1.515702479338843,
      "grad_norm": 0.0,
      "learning_rate": 2.7403846153846156e-05,
      "loss": 232.01123046875,
      "mean_token_accuracy": 0.026154680154286326,
      "num_tokens": 666226.0,
      "step": 115
    },
    {
      "entropy": 3.9355483412742616,
      "epoch": 1.5818181818181818,
      "grad_norm": 0.0,
      "learning_rate": 2.620192307692308e-05,
      "loss": 233.4347900390625,
      "mean_token_accuracy": 0.027279651118442418,
      "num_tokens": 694227.0,
      "step": 120
    },
    {
      "entropy": 3.9471412718296053,
      "epoch": 1.6479338842975206,
      "grad_norm": 0.0,
      "learning_rate": 2.5e-05,
      "loss": 233.40400390625,
      "mean_token_accuracy": 0.027405926771461964,
      "num_tokens": 722605.0,
      "step": 125
    },
    {
      "entropy": 3.948015907406807,
      "epoch": 1.7140495867768595,
      "grad_norm": 0.0,
      "learning_rate": 2.3798076923076922e-05,
      "loss": 233.548486328125,
      "mean_token_accuracy": 0.028720574569888413,
      "num_tokens": 750872.0,
      "step": 130
    },
    {
      "entropy": 3.9404551655054094,
      "epoch": 1.7801652892561983,
      "grad_norm": 0.0,
      "learning_rate": 2.2596153846153846e-05,
      "loss": 235.551025390625,
      "mean_token_accuracy": 0.0262312832986936,
      "num_tokens": 778888.0,
      "step": 135
    },
    {
      "entropy": 3.9351486653089522,
      "epoch": 1.8462809917355372,
      "grad_norm": 0.0,
      "learning_rate": 2.139423076923077e-05,
      "loss": 231.918896484375,
      "mean_token_accuracy": 0.025760800496209414,
      "num_tokens": 810828.0,
      "step": 140
    },
    {
      "entropy": 3.948241111636162,
      "epoch": 1.912396694214876,
      "grad_norm": 0.0,
      "learning_rate": 2.0192307692307694e-05,
      "loss": 233.4085205078125,
      "mean_token_accuracy": 0.02667535947402939,
      "num_tokens": 843110.0,
      "step": 145
    },
    {
      "entropy": 3.94561530649662,
      "epoch": 1.9785123966942149,
      "grad_norm": 0.0,
      "learning_rate": 1.8990384615384615e-05,
      "loss": 234.3532958984375,
      "mean_token_accuracy": 0.025313910108525305,
      "num_tokens": 871729.0,
      "step": 150
    },
    {
      "entropy": 3.943527849944862,
      "epoch": 2.0396694214876034,
      "grad_norm": 0.0,
      "learning_rate": 1.778846153846154e-05,
      "loss": 215.9062255859375,
      "mean_token_accuracy": 0.025429070713250217,
      "num_tokens": 900426.0,
      "step": 155
    },
    {
      "entropy": 3.94203040599823,
      "epoch": 2.105785123966942,
      "grad_norm": 0.0,
      "learning_rate": 1.6586538461538463e-05,
      "loss": 230.911865234375,
      "mean_token_accuracy": 0.02837887905770913,
      "num_tokens": 928864.0,
      "step": 160
    },
    {
      "entropy": 3.9532357156276703,
      "epoch": 2.171900826446281,
      "grad_norm": 0.0,
      "learning_rate": 1.5384615384615387e-05,
      "loss": 234.5886962890625,
      "mean_token_accuracy": 0.02579844092251733,
      "num_tokens": 957054.0,
      "step": 165
    },
    {
      "entropy": 3.938724213838577,
      "epoch": 2.2380165289256198,
      "grad_norm": 0.0,
      "learning_rate": 1.4182692307692308e-05,
      "loss": 233.734033203125,
      "mean_token_accuracy": 0.026959190622437745,
      "num_tokens": 986375.0,
      "step": 170
    },
    {
      "entropy": 3.9513088554143905,
      "epoch": 2.304132231404959,
      "grad_norm": 0.0,
      "learning_rate": 1.2980769230769232e-05,
      "loss": 234.519482421875,
      "mean_token_accuracy": 0.02572885201079771,
      "num_tokens": 1016379.0,
      "step": 175
    },
    {
      "entropy": 3.9490306466817855,
      "epoch": 2.3702479338842974,
      "grad_norm": 0.0,
      "learning_rate": 1.1778846153846154e-05,
      "loss": 232.4193115234375,
      "mean_token_accuracy": 0.02734465190442279,
      "num_tokens": 1045506.0,
      "step": 180
    },
    {
      "entropy": 3.9409770250320433,
      "epoch": 2.4363636363636365,
      "grad_norm": 0.0,
      "learning_rate": 1.0576923076923077e-05,
      "loss": 234.274267578125,
      "mean_token_accuracy": 0.025954201573040337,
      "num_tokens": 1075203.0,
      "step": 185
    },
    {
      "entropy": 3.945644071698189,
      "epoch": 2.502479338842975,
      "grad_norm": 0.0,
      "learning_rate": 9.375000000000001e-06,
      "loss": 233.009033203125,
      "mean_token_accuracy": 0.025436178874224426,
      "num_tokens": 1105840.0,
      "step": 190
    },
    {
      "entropy": 3.9378468334674834,
      "epoch": 2.568595041322314,
      "grad_norm": 0.0,
      "learning_rate": 8.173076923076923e-06,
      "loss": 231.7622802734375,
      "mean_token_accuracy": 0.02464213842758909,
      "num_tokens": 1136555.0,
      "step": 195
    },
    {
      "entropy": 3.9481330841779707,
      "epoch": 2.634710743801653,
      "grad_norm": 0.0,
      "learning_rate": 6.9711538461538465e-06,
      "loss": 234.6160888671875,
      "mean_token_accuracy": 0.024175548332277686,
      "num_tokens": 1166980.0,
      "step": 200
    },
    {
      "entropy": 3.942607444524765,
      "epoch": 2.700826446280992,
      "grad_norm": 0.0,
      "learning_rate": 5.76923076923077e-06,
      "loss": 232.27705078125,
      "mean_token_accuracy": 0.02845959346741438,
      "num_tokens": 1191975.0,
      "step": 205
    },
    {
      "entropy": 3.94253448843956,
      "epoch": 2.7669421487603305,
      "grad_norm": 0.0,
      "learning_rate": 4.567307692307692e-06,
      "loss": 231.2766357421875,
      "mean_token_accuracy": 0.026302760490216313,
      "num_tokens": 1222197.0,
      "step": 210
    },
    {
      "entropy": 3.9235304445028305,
      "epoch": 2.8330578512396696,
      "grad_norm": 0.0,
      "learning_rate": 3.3653846153846154e-06,
      "loss": 233.171337890625,
      "mean_token_accuracy": 0.02858651557471603,
      "num_tokens": 1250391.0,
      "step": 215
    },
    {
      "entropy": 3.9577153235673905,
      "epoch": 2.899173553719008,
      "grad_norm": 0.0,
      "learning_rate": 2.1634615384615387e-06,
      "loss": 233.0808349609375,
      "mean_token_accuracy": 0.025711765605956317,
      "num_tokens": 1281477.0,
      "step": 220
    },
    {
      "entropy": 3.941769191622734,
      "epoch": 2.9652892561983473,
      "grad_norm": 0.0,
      "learning_rate": 9.615384615384617e-07,
      "loss": 232.8261962890625,
      "mean_token_accuracy": 0.02683557631680742,
      "num_tokens": 1310280.0,
      "step": 225
    }
  ],
  "logging_steps": 5,
  "max_steps": 228,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3.582163831136659e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}