{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022249003430054697,
  "eval_steps": 3,
  "global_step": 3,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007416334476684898,
      "grad_norm": 12.539473533630371,
      "learning_rate": 2e-05,
      "loss": 18.8184,
      "step": 1
    },
    {
      "epoch": 0.0007416334476684898,
      "eval_loss": 2.656465768814087,
      "eval_runtime": 71.3819,
      "eval_samples_per_second": 7.957,
      "eval_steps_per_second": 7.957,
      "step": 1
    },
    {
      "epoch": 0.0014832668953369797,
      "grad_norm": 14.706053733825684,
      "learning_rate": 4e-05,
      "loss": 24.6349,
      "step": 2
    },
    {
      "epoch": 0.0022249003430054697,
      "grad_norm": 11.934353828430176,
      "learning_rate": 6e-05,
      "loss": 19.4363,
      "step": 3
    },
    {
      "epoch": 0.0022249003430054697,
      "eval_loss": 2.645974636077881,
      "eval_runtime": 71.0304,
      "eval_samples_per_second": 7.997,
      "eval_steps_per_second": 7.997,
      "step": 3
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 243943958642688.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}