{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.027835768963117607,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027835768963117608,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 15.0527,
      "step": 1
    },
    {
      "epoch": 0.0027835768963117608,
      "eval_loss": 14.916102409362793,
      "eval_runtime": 17.5245,
      "eval_samples_per_second": 34.523,
      "eval_steps_per_second": 4.337,
      "step": 1
    },
    {
      "epoch": 0.0055671537926235215,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 14.9699,
      "step": 2
    },
    {
      "epoch": 0.008350730688935281,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 14.5737,
      "step": 3
    },
    {
      "epoch": 0.008350730688935281,
      "eval_loss": 14.916102409362793,
      "eval_runtime": 17.5591,
      "eval_samples_per_second": 34.455,
      "eval_steps_per_second": 4.328,
      "step": 3
    },
    {
      "epoch": 0.011134307585247043,
      "grad_norm": 12.508493423461914,
      "learning_rate": 2e-05,
      "loss": 15.2401,
      "step": 4
    },
    {
      "epoch": 0.013917884481558803,
      "grad_norm": 12.544662475585938,
      "learning_rate": 4e-05,
      "loss": 15.0459,
      "step": 5
    },
    {
      "epoch": 0.016701461377870562,
      "grad_norm": 13.881077766418457,
      "learning_rate": 6e-05,
      "loss": 14.578,
      "step": 6
    },
    {
      "epoch": 0.016701461377870562,
      "eval_loss": 13.958480834960938,
      "eval_runtime": 16.9894,
      "eval_samples_per_second": 35.61,
      "eval_steps_per_second": 4.473,
      "step": 6
    },
    {
      "epoch": 0.019485038274182326,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 13.8221,
      "step": 7
    },
    {
      "epoch": 0.022268615170494086,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 13.5808,
      "step": 8
    },
    {
      "epoch": 0.025052192066805846,
      "grad_norm": 15.185980796813965,
      "learning_rate": 8e-05,
      "loss": 14.1433,
      "step": 9
    },
    {
      "epoch": 0.025052192066805846,
      "eval_loss": 12.73656177520752,
      "eval_runtime": 16.942,
      "eval_samples_per_second": 35.71,
      "eval_steps_per_second": 4.486,
      "step": 9
    },
    {
      "epoch": 0.027835768963117607,
      "grad_norm": 16.87995147705078,
      "learning_rate": 0.0001,
      "loss": 12.3237,
      "step": 10
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.935098268483584e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}