{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07741935483870968,
  "eval_steps": 3,
  "global_step": 9,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.008602150537634409,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.008602150537634409,
      "eval_loss": NaN,
      "eval_runtime": 2.8729,
      "eval_samples_per_second": 17.056,
      "eval_steps_per_second": 8.702,
      "step": 1
    },
    {
      "epoch": 0.017204301075268817,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.025806451612903226,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.025806451612903226,
      "eval_loss": NaN,
      "eval_runtime": 1.5184,
      "eval_samples_per_second": 32.271,
      "eval_steps_per_second": 16.465,
      "step": 3
    },
    {
      "epoch": 0.034408602150537634,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.043010752688172046,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.05161290322580645,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.05161290322580645,
      "eval_loss": NaN,
      "eval_runtime": 1.4975,
      "eval_samples_per_second": 32.721,
      "eval_steps_per_second": 16.694,
      "step": 6
    },
    {
      "epoch": 0.060215053763440864,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.06881720430107527,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.07741935483870968,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.07741935483870968,
      "eval_loss": NaN,
      "eval_runtime": 1.4894,
      "eval_samples_per_second": 32.899,
      "eval_steps_per_second": 16.785,
      "step": 9
    }
  ],
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1578098592055296.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}