{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00041480436788999387,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.148043678899939e-05,
      "grad_norm": 5.157196044921875,
      "learning_rate": 2e-05,
      "loss": 8.953,
      "step": 1
    },
    {
      "epoch": 4.148043678899939e-05,
      "eval_loss": 2.5111091136932373,
      "eval_runtime": 267.0132,
      "eval_samples_per_second": 38.017,
      "eval_steps_per_second": 19.01,
      "step": 1
    },
    {
      "epoch": 8.296087357799878e-05,
      "grad_norm": 9.48502254486084,
      "learning_rate": 4e-05,
      "loss": 12.7244,
      "step": 2
    },
    {
      "epoch": 0.00012444131036699817,
      "grad_norm": 8.044157028198242,
      "learning_rate": 6e-05,
      "loss": 9.1735,
      "step": 3
    },
    {
      "epoch": 0.00012444131036699817,
      "eval_loss": 2.508043050765991,
      "eval_runtime": 263.8855,
      "eval_samples_per_second": 38.467,
      "eval_steps_per_second": 19.236,
      "step": 3
    },
    {
      "epoch": 0.00016592174715599755,
      "grad_norm": 5.637796878814697,
      "learning_rate": 8e-05,
      "loss": 10.6882,
      "step": 4
    },
    {
      "epoch": 0.00020740218394499693,
      "grad_norm": 9.926366806030273,
      "learning_rate": 0.0001,
      "loss": 7.885,
      "step": 5
    },
    {
      "epoch": 0.00024888262073399634,
      "grad_norm": 5.339255332946777,
      "learning_rate": 0.00012,
      "loss": 10.339,
      "step": 6
    },
    {
      "epoch": 0.00024888262073399634,
      "eval_loss": 2.49546217918396,
      "eval_runtime": 267.0878,
      "eval_samples_per_second": 38.006,
      "eval_steps_per_second": 19.005,
      "step": 6
    },
    {
      "epoch": 0.0002903630575229957,
      "grad_norm": 8.164689064025879,
      "learning_rate": 0.00014,
      "loss": 10.9695,
      "step": 7
    },
    {
      "epoch": 0.0003318434943119951,
      "grad_norm": 6.021840572357178,
      "learning_rate": 0.00016,
      "loss": 10.763,
      "step": 8
    },
    {
      "epoch": 0.0003733239311009945,
      "grad_norm": 5.9938836097717285,
      "learning_rate": 0.00018,
      "loss": 8.7998,
      "step": 9
    },
    {
      "epoch": 0.0003733239311009945,
      "eval_loss": 2.4785315990448,
      "eval_runtime": 272.4329,
      "eval_samples_per_second": 37.261,
      "eval_steps_per_second": 18.632,
      "step": 9
    },
    {
      "epoch": 0.00041480436788999387,
      "grad_norm": 4.040714740753174,
      "learning_rate": 0.0002,
      "loss": 7.0398,
      "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": 32375005249536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}