{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.005377789728421619,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005377789728421619,
      "grad_norm": 2.304826259613037,
      "learning_rate": 2e-05,
      "loss": 2.6686,
      "step": 1
    },
    {
      "epoch": 0.0005377789728421619,
      "eval_loss": 2.560180187225342,
      "eval_runtime": 29.2628,
      "eval_samples_per_second": 26.758,
      "eval_steps_per_second": 13.396,
      "step": 1
    },
    {
      "epoch": 0.0010755579456843238,
      "grad_norm": 2.74312686920166,
      "learning_rate": 4e-05,
      "loss": 2.4686,
      "step": 2
    },
    {
      "epoch": 0.0016133369185264857,
      "grad_norm": 1.7977912425994873,
      "learning_rate": 6e-05,
      "loss": 2.9726,
      "step": 3
    },
    {
      "epoch": 0.0016133369185264857,
      "eval_loss": 2.52547550201416,
      "eval_runtime": 29.2843,
      "eval_samples_per_second": 26.738,
      "eval_steps_per_second": 13.386,
      "step": 3
    },
    {
      "epoch": 0.0021511158913686476,
      "grad_norm": 4.442842483520508,
      "learning_rate": 8e-05,
      "loss": 2.8486,
      "step": 4
    },
    {
      "epoch": 0.0026888948642108095,
      "grad_norm": 2.7628161907196045,
      "learning_rate": 0.0001,
      "loss": 2.0325,
      "step": 5
    },
    {
      "epoch": 0.0032266738370529714,
      "grad_norm": 2.3133115768432617,
      "learning_rate": 0.00012,
      "loss": 2.3014,
      "step": 6
    },
    {
      "epoch": 0.0032266738370529714,
      "eval_loss": 2.3192427158355713,
      "eval_runtime": 29.3025,
      "eval_samples_per_second": 26.721,
      "eval_steps_per_second": 13.378,
      "step": 6
    },
    {
      "epoch": 0.003764452809895133,
      "grad_norm": 2.357987880706787,
      "learning_rate": 0.00014,
      "loss": 2.023,
      "step": 7
    },
    {
      "epoch": 0.004302231782737295,
      "grad_norm": 3.123420000076294,
      "learning_rate": 0.00016,
      "loss": 2.4067,
      "step": 8
    },
    {
      "epoch": 0.004840010755579457,
      "grad_norm": 4.577430725097656,
      "learning_rate": 0.00018,
      "loss": 2.3827,
      "step": 9
    },
    {
      "epoch": 0.004840010755579457,
      "eval_loss": 2.1229164600372314,
      "eval_runtime": 29.3275,
      "eval_samples_per_second": 26.698,
      "eval_steps_per_second": 13.366,
      "step": 9
    },
    {
      "epoch": 0.005377789728421619,
      "grad_norm": 3.9270293712615967,
      "learning_rate": 0.0002,
      "loss": 2.1457,
      "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": 1958868701675520.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}