{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.00038395822534508244,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.8395822534508245e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 3.8395822534508245e-05,
      "eval_loss": NaN,
      "eval_runtime": 504.5056,
      "eval_samples_per_second": 21.738,
      "eval_steps_per_second": 10.87,
      "step": 1
    },
    {
      "epoch": 7.679164506901649e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.3193,
      "step": 2
    },
    {
      "epoch": 0.00011518746760352474,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 1.0554,
      "step": 3
    },
    {
      "epoch": 0.00011518746760352474,
      "eval_loss": NaN,
      "eval_runtime": 503.2339,
      "eval_samples_per_second": 21.793,
      "eval_steps_per_second": 10.898,
      "step": 3
    },
    {
      "epoch": 0.00015358329013803298,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.9444,
      "step": 4
    },
    {
      "epoch": 0.00019197911267254122,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00023037493520704948,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 1.7599,
      "step": 6
    },
    {
      "epoch": 0.00023037493520704948,
      "eval_loss": NaN,
      "eval_runtime": 503.3243,
      "eval_samples_per_second": 21.789,
      "eval_steps_per_second": 10.896,
      "step": 6
    },
    {
      "epoch": 0.0002687707577415577,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.2948,
      "step": 7
    },
    {
      "epoch": 0.00030716658027606596,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 1.3192,
      "step": 8
    },
    {
      "epoch": 0.0003455624028105742,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003455624028105742,
      "eval_loss": NaN,
      "eval_runtime": 503.4591,
      "eval_samples_per_second": 21.783,
      "eval_steps_per_second": 10.893,
      "step": 9
    },
    {
      "epoch": 0.00038395822534508244,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 2610117728010240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}