{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7407407407407407,
  "eval_steps": 500,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.805763495862484,
      "epoch": 0.07407407407407407,
      "grad_norm": 0.6806204319000244,
      "learning_rate": 8.032786885245902e-05,
      "loss": 1.5484,
      "mean_token_accuracy": 0.6665007689595223,
      "num_tokens": 408149.0,
      "step": 50
    },
    {
      "entropy": 0.41144788280129435,
      "epoch": 0.14814814814814814,
      "grad_norm": 0.38455039262771606,
      "learning_rate": 9.990765991730485e-05,
      "loss": 0.3321,
      "mean_token_accuracy": 0.9129975068569184,
      "num_tokens": 816230.0,
      "step": 100
    },
    {
      "entropy": 0.16323913749307395,
      "epoch": 0.2222222222222222,
      "grad_norm": 0.29704713821411133,
      "learning_rate": 9.950545603782162e-05,
      "loss": 0.1447,
      "mean_token_accuracy": 0.9618216013908386,
      "num_tokens": 1224471.0,
      "step": 150
    },
    {
      "entropy": 0.1175146003998816,
      "epoch": 0.2962962962962963,
      "grad_norm": 0.35487300157546997,
      "learning_rate": 9.878674879048427e-05,
      "loss": 0.1071,
      "mean_token_accuracy": 0.9733556269109249,
      "num_tokens": 1632497.0,
      "step": 200
    },
    {
      "entropy": 0.1009879010822624,
      "epoch": 0.37037037037037035,
      "grad_norm": 0.17419321835041046,
      "learning_rate": 9.775613308830824e-05,
      "loss": 0.0925,
      "mean_token_accuracy": 0.9769376286864281,
      "num_tokens": 2041392.0,
      "step": 250
    },
    {
      "entropy": 0.09154447751119733,
      "epoch": 0.4444444444444444,
      "grad_norm": 0.20543242990970612,
      "learning_rate": 9.642019796948866e-05,
      "loss": 0.0836,
      "mean_token_accuracy": 0.9787026332318782,
      "num_tokens": 2450311.0,
      "step": 300
    },
    {
      "entropy": 0.08632300381548702,
      "epoch": 0.5185185185185185,
      "grad_norm": 0.17172595858573914,
      "learning_rate": 9.478748447168449e-05,
      "loss": 0.0812,
      "mean_token_accuracy": 0.9789653661847114,
      "num_tokens": 2858744.0,
      "step": 350
    },
    {
      "entropy": 0.08412999271415174,
      "epoch": 0.5925925925925926,
      "grad_norm": 0.1447569578886032,
      "learning_rate": 9.28684310265789e-05,
      "loss": 0.0805,
      "mean_token_accuracy": 0.9786932443082332,
      "num_tokens": 3265542.0,
      "step": 400
    },
    {
      "entropy": 0.08065679710358381,
      "epoch": 0.6666666666666666,
      "grad_norm": 0.19630704820156097,
      "learning_rate": 9.067530672382544e-05,
      "loss": 0.0773,
      "mean_token_accuracy": 0.9797722736001014,
      "num_tokens": 3674162.0,
      "step": 450
    },
    {
      "entropy": 0.07874332463368773,
      "epoch": 0.7407407407407407,
      "grad_norm": 0.08524929732084274,
      "learning_rate": 8.822213287104348e-05,
      "loss": 0.0762,
      "mean_token_accuracy": 0.9801681047677994,
      "num_tokens": 4082734.0,
      "step": 500
    }
  ],
  "logging_steps": 50,
  "max_steps": 2025,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7054669570308915e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}