{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.017660044150110375,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017660044150110375,
      "grad_norm": 16.0111083984375,
      "learning_rate": 2e-05,
      "loss": 11.6766,
      "step": 1
    },
    {
      "epoch": 0.0017660044150110375,
      "eval_loss": 3.2583110332489014,
      "eval_runtime": 2.6992,
      "eval_samples_per_second": 88.546,
      "eval_steps_per_second": 44.458,
      "step": 1
    },
    {
      "epoch": 0.003532008830022075,
      "grad_norm": 22.975067138671875,
      "learning_rate": 4e-05,
      "loss": 14.5763,
      "step": 2
    },
    {
      "epoch": 0.005298013245033113,
      "grad_norm": 17.789430618286133,
      "learning_rate": 6e-05,
      "loss": 12.3859,
      "step": 3
    },
    {
      "epoch": 0.005298013245033113,
      "eval_loss": 3.2383251190185547,
      "eval_runtime": 1.547,
      "eval_samples_per_second": 154.489,
      "eval_steps_per_second": 77.568,
      "step": 3
    },
    {
      "epoch": 0.00706401766004415,
      "grad_norm": 16.208463668823242,
      "learning_rate": 8e-05,
      "loss": 12.2721,
      "step": 4
    },
    {
      "epoch": 0.008830022075055188,
      "grad_norm": 17.541433334350586,
      "learning_rate": 0.0001,
      "loss": 13.2107,
      "step": 5
    },
    {
      "epoch": 0.010596026490066225,
      "grad_norm": 20.636184692382812,
      "learning_rate": 0.00012,
      "loss": 11.6557,
      "step": 6
    },
    {
      "epoch": 0.010596026490066225,
      "eval_loss": 3.1124987602233887,
      "eval_runtime": 1.5786,
      "eval_samples_per_second": 151.401,
      "eval_steps_per_second": 76.017,
      "step": 6
    },
    {
      "epoch": 0.012362030905077263,
      "grad_norm": 22.77167320251465,
      "learning_rate": 0.00014,
      "loss": 12.8872,
      "step": 7
    },
    {
      "epoch": 0.0141280353200883,
      "grad_norm": 18.597755432128906,
      "learning_rate": 0.00016,
      "loss": 13.1089,
      "step": 8
    },
    {
      "epoch": 0.015894039735099338,
      "grad_norm": 18.6827449798584,
      "learning_rate": 0.00018,
      "loss": 13.8305,
      "step": 9
    },
    {
      "epoch": 0.015894039735099338,
      "eval_loss": 2.8598744869232178,
      "eval_runtime": 1.552,
      "eval_samples_per_second": 153.992,
      "eval_steps_per_second": 77.318,
      "step": 9
    },
    {
      "epoch": 0.017660044150110375,
      "grad_norm": 17.794754028320312,
      "learning_rate": 0.0002,
      "loss": 12.369,
      "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": 25475413966848.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}