{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 4500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "entropy": 0.31903962667783103,
      "epoch": 1.0,
      "grad_norm": 3.5418779850006104,
      "learning_rate": 5e-05,
      "loss": 0.3342,
      "mean_token_accuracy": 0.9157681801584032,
      "num_tokens": 4499836.0,
      "step": 2250
    },
    {
      "epoch": 1.0,
      "eval_entropy": 0.23254949676990508,
      "eval_loss": 0.2607364356517792,
      "eval_mean_token_accuracy": 0.9283432579040527,
      "eval_num_tokens": 4499836.0,
      "eval_runtime": 31.0459,
      "eval_samples_per_second": 32.21,
      "eval_steps_per_second": 4.026,
      "step": 2250
    },
    {
      "entropy": 0.22166679374045795,
      "epoch": 2.0,
      "grad_norm": 4.510587692260742,
      "learning_rate": 5e-05,
      "loss": 0.2374,
      "mean_token_accuracy": 0.9321232258478801,
      "num_tokens": 8999672.0,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_entropy": 0.21246080088615418,
      "eval_loss": 0.23861302435398102,
      "eval_mean_token_accuracy": 0.9319414987564086,
      "eval_num_tokens": 8999672.0,
      "eval_runtime": 31.0907,
      "eval_samples_per_second": 32.164,
      "eval_steps_per_second": 4.02,
      "step": 4500
    }
  ],
  "logging_steps": 10,
  "max_steps": 6750,
  "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": 1.5034715209728e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}