{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.010269576379974325,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0010269576379974327,
      "grad_norm": 6.53356409072876,
      "learning_rate": 2e-05,
      "loss": 10.0927,
      "step": 1
    },
    {
      "epoch": 0.0010269576379974327,
      "eval_loss": 10.528717994689941,
      "eval_runtime": 4.1743,
      "eval_samples_per_second": 98.22,
      "eval_steps_per_second": 49.11,
      "step": 1
    },
    {
      "epoch": 0.0020539152759948653,
      "grad_norm": 7.160462379455566,
      "learning_rate": 4e-05,
      "loss": 10.5907,
      "step": 2
    },
    {
      "epoch": 0.0030808729139922978,
      "grad_norm": 6.975811958312988,
      "learning_rate": 6e-05,
      "loss": 10.8963,
      "step": 3
    },
    {
      "epoch": 0.0030808729139922978,
      "eval_loss": 10.518180847167969,
      "eval_runtime": 4.1966,
      "eval_samples_per_second": 97.699,
      "eval_steps_per_second": 48.849,
      "step": 3
    },
    {
      "epoch": 0.004107830551989731,
      "grad_norm": 6.744149208068848,
      "learning_rate": 8e-05,
      "loss": 10.4339,
      "step": 4
    },
    {
      "epoch": 0.005134788189987163,
      "grad_norm": 6.718221187591553,
      "learning_rate": 0.0001,
      "loss": 10.3246,
      "step": 5
    },
    {
      "epoch": 0.0061617458279845955,
      "grad_norm": 7.47218656539917,
      "learning_rate": 0.00012,
      "loss": 10.335,
      "step": 6
    },
    {
      "epoch": 0.0061617458279845955,
      "eval_loss": 10.36172866821289,
      "eval_runtime": 4.7065,
      "eval_samples_per_second": 87.113,
      "eval_steps_per_second": 43.557,
      "step": 6
    },
    {
      "epoch": 0.007188703465982028,
      "grad_norm": 6.63240909576416,
      "learning_rate": 0.00014,
      "loss": 10.1546,
      "step": 7
    },
    {
      "epoch": 0.008215661103979461,
      "grad_norm": 7.104830265045166,
      "learning_rate": 0.00016,
      "loss": 10.2257,
      "step": 8
    },
    {
      "epoch": 0.009242618741976894,
      "grad_norm": 7.159472465515137,
      "learning_rate": 0.00018,
      "loss": 10.3368,
      "step": 9
    },
    {
      "epoch": 0.009242618741976894,
      "eval_loss": 10.03166675567627,
      "eval_runtime": 4.5408,
      "eval_samples_per_second": 90.292,
      "eval_steps_per_second": 45.146,
      "step": 9
    },
    {
      "epoch": 0.010269576379974325,
      "grad_norm": 6.898739337921143,
      "learning_rate": 0.0002,
      "loss": 10.2581,
      "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": 655585443840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}