{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 115,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 1.6573707230389119,
      "epoch": 0.2176278563656148,
      "grad_norm": 0.0654296875,
      "learning_rate": 0.00018440244840299506,
      "loss": 1.6920187377929687,
      "mean_token_accuracy": 0.6198506566882134,
      "num_tokens": 160909.0,
      "step": 25
    },
    {
      "entropy": 1.2382403728365898,
      "epoch": 0.4352557127312296,
      "grad_norm": 0.119140625,
      "learning_rate": 0.00012928227712765504,
      "loss": 1.170916290283203,
      "mean_token_accuracy": 0.7113918185234069,
      "num_tokens": 326278.0,
      "step": 50
    },
    {
      "entropy": 0.8297647612914443,
      "epoch": 0.6528835690968444,
      "grad_norm": 0.1630859375,
      "learning_rate": 6.010346486845837e-05,
      "loss": 0.761020278930664,
      "mean_token_accuracy": 0.80675925552845,
      "num_tokens": 488512.0,
      "step": 75
    },
    {
      "entropy": 0.5981892856955529,
      "epoch": 0.8705114254624592,
      "grad_norm": 0.1484375,
      "learning_rate": 1.0079278510416313e-05,
      "loss": 0.518447265625,
      "mean_token_accuracy": 0.8673335748910904,
      "num_tokens": 651559.0,
      "step": 100
    }
  ],
  "logging_steps": 25,
  "max_steps": 115,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 3.201720093332275e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}