{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 228,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.3891168855130672,
      "epoch": 0.043859649122807015,
      "grad_norm": 18.536834716796875,
      "learning_rate": 2e-05,
      "loss": 4.281,
      "mean_token_accuracy": 0.5703265547752381,
      "num_tokens": 29513.0,
      "step": 10
    },
    {
      "entropy": 0.749189381301403,
      "epoch": 0.08771929824561403,
      "grad_norm": 3.8398051261901855,
      "learning_rate": 2e-05,
      "loss": 1.9625,
      "mean_token_accuracy": 0.6897866070270539,
      "num_tokens": 58932.0,
      "step": 20
    },
    {
      "entropy": 1.169826951622963,
      "epoch": 0.13157894736842105,
      "grad_norm": 2.5061917304992676,
      "learning_rate": 2e-05,
      "loss": 1.4255,
      "mean_token_accuracy": 0.7357227891683579,
      "num_tokens": 88352.0,
      "step": 30
    },
    {
      "entropy": 1.1334790736436844,
      "epoch": 0.17543859649122806,
      "grad_norm": 1.9473565816879272,
      "learning_rate": 2e-05,
      "loss": 1.1315,
      "mean_token_accuracy": 0.7862708762288093,
      "num_tokens": 117877.0,
      "step": 40
    },
    {
      "entropy": 0.8736076682806015,
      "epoch": 0.21929824561403508,
      "grad_norm": 1.7826578617095947,
      "learning_rate": 2e-05,
      "loss": 0.8549,
      "mean_token_accuracy": 0.8343304082751274,
      "num_tokens": 147392.0,
      "step": 50
    },
    {
      "entropy": 0.5955807730555535,
      "epoch": 0.2631578947368421,
      "grad_norm": 1.6632131338119507,
      "learning_rate": 2e-05,
      "loss": 0.58,
      "mean_token_accuracy": 0.8876266479492188,
      "num_tokens": 176728.0,
      "step": 60
    },
    {
      "entropy": 0.34382262006402015,
      "epoch": 0.30701754385964913,
      "grad_norm": 1.4843252897262573,
      "learning_rate": 2e-05,
      "loss": 0.3445,
      "mean_token_accuracy": 0.9318736225366593,
      "num_tokens": 206184.0,
      "step": 70
    },
    {
      "entropy": 0.19373956136405468,
      "epoch": 0.3508771929824561,
      "grad_norm": 0.904003918170929,
      "learning_rate": 2e-05,
      "loss": 0.189,
      "mean_token_accuracy": 0.9710342198610306,
      "num_tokens": 235688.0,
      "step": 80
    },
    {
      "entropy": 0.12052652426064014,
      "epoch": 0.39473684210526316,
      "grad_norm": 0.7406700849533081,
      "learning_rate": 2e-05,
      "loss": 0.1056,
      "mean_token_accuracy": 0.9886028110980988,
      "num_tokens": 265172.0,
      "step": 90
    },
    {
      "entropy": 0.0992697212845087,
      "epoch": 0.43859649122807015,
      "grad_norm": 0.606019139289856,
      "learning_rate": 2e-05,
      "loss": 0.0817,
      "mean_token_accuracy": 0.989163076877594,
      "num_tokens": 294687.0,
      "step": 100
    },
    {
      "entropy": 0.08367474023252726,
      "epoch": 0.4824561403508772,
      "grad_norm": 0.4705955386161804,
      "learning_rate": 2e-05,
      "loss": 0.0737,
      "mean_token_accuracy": 0.9905414953827858,
      "num_tokens": 324088.0,
      "step": 110
    },
    {
      "entropy": 0.07386345528066159,
      "epoch": 0.5263157894736842,
      "grad_norm": 0.4300910234451294,
      "learning_rate": 2e-05,
      "loss": 0.0631,
      "mean_token_accuracy": 0.9910139158368111,
      "num_tokens": 353582.0,
      "step": 120
    },
    {
      "entropy": 0.06888655042275786,
      "epoch": 0.5701754385964912,
      "grad_norm": 0.45082923769950867,
      "learning_rate": 2e-05,
      "loss": 0.0661,
      "mean_token_accuracy": 0.9910464301705361,
      "num_tokens": 383080.0,
      "step": 130
    },
    {
      "entropy": 0.06553246006369591,
      "epoch": 0.6140350877192983,
      "grad_norm": 0.4258216619491577,
      "learning_rate": 2e-05,
      "loss": 0.0615,
      "mean_token_accuracy": 0.9914803236722947,
      "num_tokens": 412559.0,
      "step": 140
    },
    {
      "entropy": 0.06352790119126439,
      "epoch": 0.6578947368421053,
      "grad_norm": 0.37360644340515137,
      "learning_rate": 2e-05,
      "loss": 0.0579,
      "mean_token_accuracy": 0.9916400715708733,
      "num_tokens": 442008.0,
      "step": 150
    },
    {
      "entropy": 0.060972847137600185,
      "epoch": 0.7017543859649122,
      "grad_norm": 0.3406882584095001,
      "learning_rate": 2e-05,
      "loss": 0.0576,
      "mean_token_accuracy": 0.9914845108985901,
      "num_tokens": 471495.0,
      "step": 160
    },
    {
      "entropy": 0.05891128294169903,
      "epoch": 0.7456140350877193,
      "grad_norm": 0.2854160964488983,
      "learning_rate": 2e-05,
      "loss": 0.057,
      "mean_token_accuracy": 0.9915445119142532,
      "num_tokens": 500954.0,
      "step": 170
    },
    {
      "entropy": 0.0579888011328876,
      "epoch": 0.7894736842105263,
      "grad_norm": 0.40168505907058716,
      "learning_rate": 2e-05,
      "loss": 0.0507,
      "mean_token_accuracy": 0.9923512250185013,
      "num_tokens": 530401.0,
      "step": 180
    },
    {
      "entropy": 0.0573225624859333,
      "epoch": 0.8333333333333334,
      "grad_norm": 0.4589792490005493,
      "learning_rate": 2e-05,
      "loss": 0.0561,
      "mean_token_accuracy": 0.9916056364774704,
      "num_tokens": 559940.0,
      "step": 190
    },
    {
      "entropy": 0.05970530286431312,
      "epoch": 0.8771929824561403,
      "grad_norm": 0.5275149941444397,
      "learning_rate": 2e-05,
      "loss": 0.0573,
      "mean_token_accuracy": 0.9915869951248169,
      "num_tokens": 589427.0,
      "step": 200
    },
    {
      "entropy": 0.059507152158766986,
      "epoch": 0.9210526315789473,
      "grad_norm": 0.2661688029766083,
      "learning_rate": 2e-05,
      "loss": 0.0515,
      "mean_token_accuracy": 0.9923170626163482,
      "num_tokens": 618838.0,
      "step": 210
    },
    {
      "entropy": 0.05687206219881773,
      "epoch": 0.9649122807017544,
      "grad_norm": 0.35179731249809265,
      "learning_rate": 2e-05,
      "loss": 0.0506,
      "mean_token_accuracy": 0.9918064430356026,
      "num_tokens": 648258.0,
      "step": 220
    }
  ],
  "logging_steps": 10,
  "max_steps": 1824,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 8,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 419741502833664.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}