{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.5240228176116943,
      "epoch": 0.04,
      "grad_norm": 37.29308319091797,
      "learning_rate": 2e-05,
      "loss": 6.9422,
      "mean_token_accuracy": 0.47347480058670044,
      "num_tokens": 758.0,
      "step": 1
    },
    {
      "entropy": 0.5185598134994507,
      "epoch": 0.08,
      "grad_norm": 37.85886764526367,
      "learning_rate": 2e-05,
      "loss": 6.8565,
      "mean_token_accuracy": 0.47270306944847107,
      "num_tokens": 1513.0,
      "step": 2
    },
    {
      "entropy": 0.5363126993179321,
      "epoch": 0.12,
      "grad_norm": 36.92781066894531,
      "learning_rate": 2e-05,
      "loss": 6.6136,
      "mean_token_accuracy": 0.47562581300735474,
      "num_tokens": 2276.0,
      "step": 3
    },
    {
      "entropy": 0.5541151762008667,
      "epoch": 0.16,
      "grad_norm": 37.46426773071289,
      "learning_rate": 2e-05,
      "loss": 6.4114,
      "mean_token_accuracy": 0.47200000286102295,
      "num_tokens": 3030.0,
      "step": 4
    },
    {
      "entropy": 0.6072134375572205,
      "epoch": 0.2,
      "grad_norm": 36.258392333984375,
      "learning_rate": 2e-05,
      "loss": 5.9563,
      "mean_token_accuracy": 0.4704301059246063,
      "num_tokens": 3778.0,
      "step": 5
    },
    {
      "entropy": 0.6346766948699951,
      "epoch": 0.24,
      "grad_norm": 34.2164421081543,
      "learning_rate": 2e-05,
      "loss": 5.4104,
      "mean_token_accuracy": 0.48868176341056824,
      "num_tokens": 4533.0,
      "step": 6
    },
    {
      "entropy": 0.699142575263977,
      "epoch": 0.28,
      "grad_norm": 31.32328987121582,
      "learning_rate": 2e-05,
      "loss": 4.9817,
      "mean_token_accuracy": 0.48806366324424744,
      "num_tokens": 5291.0,
      "step": 7
    },
    {
      "entropy": 0.7639284133911133,
      "epoch": 0.32,
      "grad_norm": 27.981550216674805,
      "learning_rate": 2e-05,
      "loss": 4.5891,
      "mean_token_accuracy": 0.5134048461914062,
      "num_tokens": 6041.0,
      "step": 8
    },
    {
      "entropy": 0.8184663653373718,
      "epoch": 0.36,
      "grad_norm": 23.888887405395508,
      "learning_rate": 2e-05,
      "loss": 4.1021,
      "mean_token_accuracy": 0.535380482673645,
      "num_tokens": 6794.0,
      "step": 9
    },
    {
      "entropy": 0.8713943362236023,
      "epoch": 0.4,
      "grad_norm": 21.27410125732422,
      "learning_rate": 2e-05,
      "loss": 3.863,
      "mean_token_accuracy": 0.5392809510231018,
      "num_tokens": 7549.0,
      "step": 10
    },
    {
      "entropy": 0.9519356489181519,
      "epoch": 0.44,
      "grad_norm": 18.26158905029297,
      "learning_rate": 2e-05,
      "loss": 3.5874,
      "mean_token_accuracy": 0.5420560836791992,
      "num_tokens": 8302.0,
      "step": 11
    },
    {
      "entropy": 1.025558352470398,
      "epoch": 0.48,
      "grad_norm": 16.051610946655273,
      "learning_rate": 2e-05,
      "loss": 3.3905,
      "mean_token_accuracy": 0.5483443737030029,
      "num_tokens": 9061.0,
      "step": 12
    },
    {
      "entropy": 1.0597870349884033,
      "epoch": 0.52,
      "grad_norm": 13.387225151062012,
      "learning_rate": 2e-05,
      "loss": 3.1501,
      "mean_token_accuracy": 0.5702811479568481,
      "num_tokens": 9812.0,
      "step": 13
    },
    {
      "entropy": 1.1256167888641357,
      "epoch": 0.56,
      "grad_norm": 11.642187118530273,
      "learning_rate": 2e-05,
      "loss": 2.9905,
      "mean_token_accuracy": 0.5778961181640625,
      "num_tokens": 10567.0,
      "step": 14
    },
    {
      "entropy": 1.1595126390457153,
      "epoch": 0.6,
      "grad_norm": 10.657787322998047,
      "learning_rate": 2e-05,
      "loss": 2.8271,
      "mean_token_accuracy": 0.5927419066429138,
      "num_tokens": 11315.0,
      "step": 15
    },
    {
      "entropy": 1.2265969514846802,
      "epoch": 0.64,
      "grad_norm": 9.537993431091309,
      "learning_rate": 2e-05,
      "loss": 2.749,
      "mean_token_accuracy": 0.5964912176132202,
      "num_tokens": 12060.0,
      "step": 16
    },
    {
      "entropy": 1.2593307495117188,
      "epoch": 0.68,
      "grad_norm": 8.315566062927246,
      "learning_rate": 2e-05,
      "loss": 2.5743,
      "mean_token_accuracy": 0.6169934868812561,
      "num_tokens": 12829.0,
      "step": 17
    },
    {
      "entropy": 1.3245295286178589,
      "epoch": 0.72,
      "grad_norm": 7.915526390075684,
      "learning_rate": 2e-05,
      "loss": 2.5367,
      "mean_token_accuracy": 0.6194332242012024,
      "num_tokens": 13574.0,
      "step": 18
    },
    {
      "entropy": 1.3604302406311035,
      "epoch": 0.76,
      "grad_norm": 7.328187942504883,
      "learning_rate": 2e-05,
      "loss": 2.4018,
      "mean_token_accuracy": 0.6255033612251282,
      "num_tokens": 14323.0,
      "step": 19
    },
    {
      "entropy": 1.3951760530471802,
      "epoch": 0.8,
      "grad_norm": 6.733570098876953,
      "learning_rate": 2e-05,
      "loss": 2.317,
      "mean_token_accuracy": 0.635046124458313,
      "num_tokens": 15086.0,
      "step": 20
    },
    {
      "entropy": 1.4354883432388306,
      "epoch": 0.84,
      "grad_norm": 6.525688648223877,
      "learning_rate": 2e-05,
      "loss": 2.2795,
      "mean_token_accuracy": 0.6360052824020386,
      "num_tokens": 15851.0,
      "step": 21
    },
    {
      "entropy": 1.4653663635253906,
      "epoch": 0.88,
      "grad_norm": 6.118790149688721,
      "learning_rate": 2e-05,
      "loss": 2.1621,
      "mean_token_accuracy": 0.6416107416152954,
      "num_tokens": 16600.0,
      "step": 22
    },
    {
      "entropy": 1.4949076175689697,
      "epoch": 0.92,
      "grad_norm": 5.929473400115967,
      "learning_rate": 2e-05,
      "loss": 2.1265,
      "mean_token_accuracy": 0.6526458859443665,
      "num_tokens": 17341.0,
      "step": 23
    },
    {
      "entropy": 1.4969980716705322,
      "epoch": 0.96,
      "grad_norm": 5.519643783569336,
      "learning_rate": 2e-05,
      "loss": 2.0365,
      "mean_token_accuracy": 0.6627296805381775,
      "num_tokens": 18107.0,
      "step": 24
    },
    {
      "entropy": 1.5308914184570312,
      "epoch": 1.0,
      "grad_norm": 5.461964130401611,
      "learning_rate": 2e-05,
      "loss": 1.9552,
      "mean_token_accuracy": 0.6851119995117188,
      "num_tokens": 18870.0,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 200,
  "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": 12017461091328.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}