{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 54,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 2.244855484366417,
      "epoch": 0.5633802816901409,
      "grad_norm": 0.1324576884508133,
      "learning_rate": 0.00019118998459920902,
      "loss": 2.239246368408203,
      "mean_token_accuracy": 0.4848026029765606,
      "num_tokens": 18782.0,
      "step": 10
    },
    {
      "entropy": 2.1752436344440165,
      "epoch": 1.1126760563380282,
      "grad_norm": 0.10374104976654053,
      "learning_rate": 0.00015173378141776568,
      "loss": 1.9484254837036132,
      "mean_token_accuracy": 0.5156795466557528,
      "num_tokens": 37306.0,
      "step": 20
    },
    {
      "entropy": 2.0852559447288512,
      "epoch": 1.676056338028169,
      "grad_norm": 0.10845215618610382,
      "learning_rate": 9.396215025777139e-05,
      "loss": 1.8074285507202148,
      "mean_token_accuracy": 0.5365702405571937,
      "num_tokens": 56164.0,
      "step": 30
    },
    {
      "entropy": 1.9582344171328423,
      "epoch": 2.2253521126760565,
      "grad_norm": 0.11132995039224625,
      "learning_rate": 3.832811273714569e-05,
      "loss": 1.7026189804077148,
      "mean_token_accuracy": 0.5575806765984266,
      "num_tokens": 74352.0,
      "step": 40
    },
    {
      "entropy": 1.9350761294364929,
      "epoch": 2.788732394366197,
      "grad_norm": 0.11781041324138641,
      "learning_rate": 4.527913349145441e-06,
      "loss": 1.59641695022583,
      "mean_token_accuracy": 0.5745055139064789,
      "num_tokens": 93088.0,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 54,
  "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": 6348749937868800.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}