{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 60,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.5228758169934641,
      "grad_norm": 4.096013598842928,
      "learning_rate": 9.644883599083959e-06,
      "loss": 2.5423198699951173,
      "mean_token_accuracy": 0.5685750585049391,
      "num_tokens": 91495.0,
      "step": 10
    },
    {
      "epoch": 1.0,
      "grad_norm": 6.747715140097201,
      "learning_rate": 8.025871075968828e-06,
      "loss": 1.4160140037536622,
      "mean_token_accuracy": 0.6783009481756654,
      "num_tokens": 176167.0,
      "step": 20
    },
    {
      "epoch": 1.522875816993464,
      "grad_norm": 3.445904738767255,
      "learning_rate": 5.540595092119709e-06,
      "loss": 1.0047502517700195,
      "mean_token_accuracy": 0.7559794817119837,
      "num_tokens": 269468.0,
      "step": 30
    },
    {
      "epoch": 2.0,
      "grad_norm": 7.0459795774794385,
      "learning_rate": 2.9005544921986774e-06,
      "loss": 0.8993229866027832,
      "mean_token_accuracy": 0.77471841075649,
      "num_tokens": 352326.0,
      "step": 40
    },
    {
      "epoch": 2.522875816993464,
      "grad_norm": 3.4201007742517002,
      "learning_rate": 8.615550092155478e-07,
      "loss": 0.5888644695281983,
      "mean_token_accuracy": 0.8531929008662701,
      "num_tokens": 445141.0,
      "step": 50
    },
    {
      "epoch": 3.0,
      "grad_norm": 10.021914538179248,
      "learning_rate": 7.332930744380906e-09,
      "loss": 0.5517744541168212,
      "mean_token_accuracy": 0.8597636925031061,
      "num_tokens": 528638.0,
      "step": 60
    }
  ],
  "logging_steps": 10,
  "max_steps": 60,
  "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": 2.077160188883763e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}