{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 266,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03766478342749529,
      "grad_norm": 4.520346641540527,
      "learning_rate": 0.0001986466165413534,
      "loss": 1.7976,
      "mean_token_accuracy": 0.5935400031507015,
      "num_tokens": 6488.0,
      "step": 10
    },
    {
      "epoch": 0.07532956685499058,
      "grad_norm": 4.291996955871582,
      "learning_rate": 0.00019714285714285716,
      "loss": 1.5155,
      "mean_token_accuracy": 0.648256602883339,
      "num_tokens": 12907.0,
      "step": 20
    },
    {
      "epoch": 0.11299435028248588,
      "grad_norm": 4.346818447113037,
      "learning_rate": 0.00019578947368421054,
      "loss": 1.4412,
      "mean_token_accuracy": 0.6501220405101776,
      "num_tokens": 19242.0,
      "step": 30
    },
    {
      "epoch": 0.15065913370998116,
      "grad_norm": 3.3988215923309326,
      "learning_rate": 0.0001942857142857143,
      "loss": 1.2435,
      "mean_token_accuracy": 0.7024012058973312,
      "num_tokens": 25647.0,
      "step": 40
    },
    {
      "epoch": 0.18832391713747645,
      "grad_norm": 3.1845004558563232,
      "learning_rate": 0.00019278195488721807,
      "loss": 1.2935,
      "mean_token_accuracy": 0.6964049726724625,
      "num_tokens": 32099.0,
      "step": 50
    },
    {
      "epoch": 0.22598870056497175,
      "grad_norm": 4.023508071899414,
      "learning_rate": 0.0001912781954887218,
      "loss": 1.1738,
      "mean_token_accuracy": 0.7159222587943077,
      "num_tokens": 38623.0,
      "step": 60
    },
    {
      "epoch": 0.263653483992467,
      "grad_norm": 3.649766206741333,
      "learning_rate": 0.0001897744360902256,
      "loss": 1.0487,
      "mean_token_accuracy": 0.735117182135582,
      "num_tokens": 45055.0,
      "step": 70
    },
    {
      "epoch": 0.3013182674199623,
      "grad_norm": 4.424032688140869,
      "learning_rate": 0.00018827067669172933,
      "loss": 1.0402,
      "mean_token_accuracy": 0.7437395498156547,
      "num_tokens": 51352.0,
      "step": 80
    },
    {
      "epoch": 0.3389830508474576,
      "grad_norm": 3.893348455429077,
      "learning_rate": 0.0001867669172932331,
      "loss": 0.9936,
      "mean_token_accuracy": 0.7585602343082428,
      "num_tokens": 57835.0,
      "step": 90
    },
    {
      "epoch": 0.3766478342749529,
      "grad_norm": 4.915287494659424,
      "learning_rate": 0.00018526315789473685,
      "loss": 0.9204,
      "mean_token_accuracy": 0.7651444330811501,
      "num_tokens": 64237.0,
      "step": 100
    },
    {
      "epoch": 0.4143126177024482,
      "grad_norm": 3.8559658527374268,
      "learning_rate": 0.00018375939849624062,
      "loss": 0.9346,
      "mean_token_accuracy": 0.7480458408594132,
      "num_tokens": 70645.0,
      "step": 110
    },
    {
      "epoch": 0.4519774011299435,
      "grad_norm": 4.7108025550842285,
      "learning_rate": 0.00018225563909774438,
      "loss": 0.8954,
      "mean_token_accuracy": 0.777623999118805,
      "num_tokens": 76950.0,
      "step": 120
    },
    {
      "epoch": 0.4896421845574388,
      "grad_norm": 3.1379129886627197,
      "learning_rate": 0.00018075187969924814,
      "loss": 0.9075,
      "mean_token_accuracy": 0.769656004011631,
      "num_tokens": 83477.0,
      "step": 130
    },
    {
      "epoch": 0.527306967984934,
      "grad_norm": 3.6787190437316895,
      "learning_rate": 0.00017924812030075188,
      "loss": 0.8276,
      "mean_token_accuracy": 0.7966844961047173,
      "num_tokens": 89666.0,
      "step": 140
    },
    {
      "epoch": 0.5649717514124294,
      "grad_norm": 3.936288595199585,
      "learning_rate": 0.00017774436090225567,
      "loss": 0.754,
      "mean_token_accuracy": 0.7978162422776223,
      "num_tokens": 96045.0,
      "step": 150
    },
    {
      "epoch": 0.6026365348399246,
      "grad_norm": 3.9623541831970215,
      "learning_rate": 0.0001762406015037594,
      "loss": 0.7443,
      "mean_token_accuracy": 0.8057964265346527,
      "num_tokens": 102612.0,
      "step": 160
    },
    {
      "epoch": 0.64030131826742,
      "grad_norm": 3.3509137630462646,
      "learning_rate": 0.00017473684210526317,
      "loss": 0.7718,
      "mean_token_accuracy": 0.8012749120593071,
      "num_tokens": 109028.0,
      "step": 170
    },
    {
      "epoch": 0.6779661016949152,
      "grad_norm": 3.897428512573242,
      "learning_rate": 0.00017323308270676693,
      "loss": 0.7048,
      "mean_token_accuracy": 0.8161927372217178,
      "num_tokens": 115373.0,
      "step": 180
    },
    {
      "epoch": 0.7156308851224106,
      "grad_norm": 2.7902867794036865,
      "learning_rate": 0.0001717293233082707,
      "loss": 0.6571,
      "mean_token_accuracy": 0.8328385710716247,
      "num_tokens": 121714.0,
      "step": 190
    },
    {
      "epoch": 0.7532956685499058,
      "grad_norm": 3.233376979827881,
      "learning_rate": 0.00017022556390977443,
      "loss": 0.6449,
      "mean_token_accuracy": 0.8228127270936966,
      "num_tokens": 128163.0,
      "step": 200
    },
    {
      "epoch": 0.7909604519774012,
      "grad_norm": 3.536149501800537,
      "learning_rate": 0.00016872180451127822,
      "loss": 0.5095,
      "mean_token_accuracy": 0.8665768191218376,
      "num_tokens": 134507.0,
      "step": 210
    },
    {
      "epoch": 0.8286252354048964,
      "grad_norm": 3.885110378265381,
      "learning_rate": 0.00016721804511278196,
      "loss": 0.6011,
      "mean_token_accuracy": 0.8428927510976791,
      "num_tokens": 140804.0,
      "step": 220
    },
    {
      "epoch": 0.8662900188323918,
      "grad_norm": 3.187678098678589,
      "learning_rate": 0.00016571428571428575,
      "loss": 0.6367,
      "mean_token_accuracy": 0.8326474368572235,
      "num_tokens": 147072.0,
      "step": 230
    },
    {
      "epoch": 0.903954802259887,
      "grad_norm": 3.375328779220581,
      "learning_rate": 0.00016421052631578948,
      "loss": 0.5193,
      "mean_token_accuracy": 0.8652853280305862,
      "num_tokens": 153356.0,
      "step": 240
    },
    {
      "epoch": 0.9416195856873822,
      "grad_norm": 3.7706921100616455,
      "learning_rate": 0.00016270676691729325,
      "loss": 0.5301,
      "mean_token_accuracy": 0.8526319354772568,
      "num_tokens": 159757.0,
      "step": 250
    },
    {
      "epoch": 0.9792843691148776,
      "grad_norm": 3.51759934425354,
      "learning_rate": 0.00016135338345864663,
      "loss": 0.5719,
      "mean_token_accuracy": 0.847623547911644,
      "num_tokens": 166079.0,
      "step": 260
    }
  ],
  "logging_steps": 10,
  "max_steps": 1330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "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": 7741528751800320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}