{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06866952789699571,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013733905579399141,
      "grad_norm": NaN,
      "learning_rate": 1e-05,
      "loss": 550.0793,
      "step": 1
    },
    {
      "epoch": 0.013733905579399141,
      "eval_loss": NaN,
      "eval_runtime": 19.7847,
      "eval_samples_per_second": 6.217,
      "eval_steps_per_second": 3.134,
      "step": 1
    },
    {
      "epoch": 0.027467811158798282,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.027467811158798282,
      "eval_loss": NaN,
      "eval_runtime": 0.2871,
      "eval_samples_per_second": 428.352,
      "eval_steps_per_second": 215.917,
      "step": 2
    },
    {
      "epoch": 0.041201716738197426,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.054935622317596564,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.054935622317596564,
      "eval_loss": NaN,
      "eval_runtime": 0.2879,
      "eval_samples_per_second": 427.237,
      "eval_steps_per_second": 215.355,
      "step": 4
    },
    {
      "epoch": 0.06866952789699571,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1026592604160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}