{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.000946857616285951,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 9.46857616285951e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 9.46857616285951e-05,
      "eval_loss": NaN,
      "eval_runtime": 302.4733,
      "eval_samples_per_second": 14.702,
      "eval_steps_per_second": 7.353,
      "step": 1
    },
    {
      "epoch": 0.0001893715232571902,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.0002840572848857853,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0002840572848857853,
      "eval_loss": NaN,
      "eval_runtime": 301.048,
      "eval_samples_per_second": 14.772,
      "eval_steps_per_second": 7.388,
      "step": 3
    },
    {
      "epoch": 0.0003787430465143804,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0004734288081429755,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.0005681145697715706,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0005681145697715706,
      "eval_loss": NaN,
      "eval_runtime": 300.5298,
      "eval_samples_per_second": 14.797,
      "eval_steps_per_second": 7.4,
      "step": 6
    },
    {
      "epoch": 0.0006628003314001657,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0007574860930287608,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0008521718546573559,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0008521718546573559,
      "eval_loss": NaN,
      "eval_runtime": 301.1983,
      "eval_samples_per_second": 14.764,
      "eval_steps_per_second": 7.384,
      "step": 9
    },
    {
      "epoch": 0.000946857616285951,
      "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": 4588076688998400.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}