{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 3330,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.5015015015015014,
      "grad_norm": 6.153151035308838,
      "learning_rate": 1.6996996996997e-05,
      "loss": 0.4513,
      "step": 500
    },
    {
      "epoch": 3.003003003003003,
      "grad_norm": 3.031472682952881,
      "learning_rate": 1.3993993993993995e-05,
      "loss": 0.2028,
      "step": 1000
    },
    {
      "epoch": 4.504504504504505,
      "grad_norm": 5.592371463775635,
      "learning_rate": 1.0990990990990992e-05,
      "loss": 0.0989,
      "step": 1500
    },
    {
      "epoch": 6.006006006006006,
      "grad_norm": 6.730876922607422,
      "learning_rate": 7.987987987987988e-06,
      "loss": 0.0639,
      "step": 2000
    },
    {
      "epoch": 7.5075075075075075,
      "grad_norm": 3.5161945819854736,
      "learning_rate": 4.984984984984985e-06,
      "loss": 0.0354,
      "step": 2500
    },
    {
      "epoch": 9.00900900900901,
      "grad_norm": 1.2440450191497803,
      "learning_rate": 1.9819819819819822e-06,
      "loss": 0.0226,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3330,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 881535684193692.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}